Fault prediction method for stone needle electronic pot therapy instrument
By obtaining the status index of each component of the Bianstone electronic cupping device in real time for nonlinear calculation and constructing a logistic regression model, the failure rate problem caused by equipment complexity was solved, comprehensive fault prediction and health management were achieved, and the adaptability and accuracy of the prediction were improved.
Patent Information
- Application Number
- CN202510772452.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-06-11
- Publication Date
- 2025-09-12
AI Technical Summary
The integration of electronic devices in Bianstone electronic cupping therapy devices increases the complexity of traditional cupping therapy and whetstone therapy equipment, resulting in an increased failure rate, requiring a multi-dimensional and comprehensive fault prediction method.
The working status index of each component of the Bianstone electronic cupping device is obtained in real time, nonlinear calculation is performed, and a logistic regression fault prediction model is constructed. Fault prediction is performed by inputting the status index to determine whether the working status of the equipment is abnormal.
It realizes multi-dimensional and comprehensive fault prediction and health management of Bianstone electronic cupping therapy device, and improves the adaptability, generalization and robustness of fault prediction.
Smart Images
Figure CN120636743A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of fault prediction of physical therapy equipment, and in particular to a fault prediction method for a Bianstone electronic cupping therapy device. Background Art
[0002] The Bianstone Electronic Cupping Device is a physiotherapy device that combines traditional Chinese medicine (TCM) Bianstone therapy with modern electronic technology. It is primarily used for health and wellness treatments such as meridian conditioning and pain relief. Bianstone is a traditional TCM physiotherapy tool with a warming effect and energy conduction. The device features a built-in heating function that heats the Bianstone, simulating traditional hot compresses. It also emits far-infrared and ultrasonic pulses with wavelengths ranging from 8μm to 15μm. The Bianstone Electronic Cupping Device utilizes the principle of electric negative pressure, with an electronic control device adjusting the cup's suction force. This replaces the combustion and exhaust method of traditional fire cupping, achieving a safe and adjustable "cupping" effect. It is commonly used to relieve neck, shoulder, waist, leg pain, and joint discomfort.
[0003] However, the integration of electronic devices in Bianstone electronic cupping therapy devices increases the complexity of traditional cupping therapy and whetstone therapy equipment, which will cause failure rates to a certain extent. Since health care and therapy equipment have high safety requirements, it is necessary to obtain the status index of each part and component in a multi-dimensional and comprehensive manner for fault prediction. Summary of the Invention
[0004] The purpose of the present invention is to provide a fault prediction method for a Bianstone electronic cupping therapy device, aiming to solve the problem that the Bianstone electronic cupping therapy device integrates electronic devices, increases the complexity of traditional cupping therapy and whetstone physiotherapy equipment, and to a certain extent causes a failure rate. It requires multi-dimensional and comprehensive acquisition of the status index of each part and component for fault prediction.
[0005] In view of the above problems, the present application provides a method for predicting faults of a Bianstone electronic cupping device.
[0006] The first aspect disclosed in the present application provides a method for predicting a fault of a Bianstone electronic cupping device, the method comprising the following steps: Obtaining the working state indexes of the grinding stone heating component, the infrared component, and the ultrasonic component in real time, performing combined nonlinear calculations, and generating a first state index; Obtain the working status index of the electric negative pressure component of the electronic cupping therapy part in real time, perform nonlinear calculation, and generate a second status index; Constructing a logistic regression fault prediction model and performing parameter training, inputting the first state index and the second state index into the parameter-trained logistic regression fault prediction model to generate a fault prediction confidence level; Whether the working state of the Bianstone electronic cupping therapy device is abnormal is determined based on whether the fault prediction confidence exceeds a preset threshold.
[0007] Preferably, the real-time acquisition of the working state indexes of the grinding stone heating component, the infrared component and the ultrasonic component, performing combined nonlinear calculation to generate the first state index specifically includes the following steps: The temperature of the heating component is obtained in real time, and the maximum and minimum values are normalized according to the maximum and minimum rated temperatures of the heating component to generate a temperature normalization value T; Obtain the infrared wavelength of the infrared component in real time, perform maximum and minimum value normalization based on the maximum and minimum rated wavelengths of the infrared component, and generate a wavelength normalization value ; Acquire the ultrasonic frequency of the ultrasonic component in real time, normalize the maximum and minimum values according to the maximum and minimum rated frequencies of the ultrasonic component, and generate a frequency normalization value , and obtain the ultrasonic duty cycle k; The combined nonlinear calculation is performed using formula (1), where A is the first state index: Formula (1).
[0008] Preferably, the real-time acquisition of the working state index of the electric negative pressure component of the electronic cupping therapy part, performing nonlinear calculation, and generating the second state index specifically includes the following steps: Obtain the negative pressure index generated by the electric negative pressure component in real time, where the negative pressure index is expressed as a multiple of standard atmospheric pressure, with a value range of 0 to 1; The second state index is generated by nonlinear calculation using formula (2), where p is the negative pressure index, e is the natural base, and B is the second state index: Formula (2).
[0009] Preferably, the method of constructing a logistic regression fault prediction model, performing parameter training, inputting the first state index and the second state index into the parameter-trained logistic regression fault prediction model, and generating a fault prediction confidence level specifically includes the following steps: The first state index and the second state index of the Bianstone electronic cupping device in normal working state and fault state are collected, and the corresponding working state and fault state of each sample are labeled in the form of a one-hot vector to generate a training sample data set; Construct a logistic regression fault prediction model and sample from a standard normal distribution to initialize parameters. Input the training sample dataset into the logistic regression fault prediction model and iteratively update the parameters using gradient descent or Newton's method. Regularize the parameters at the same time until the loss function value of the logistic regression fault prediction model converges, completing parameter training. The first state index and the second state index acquired and generated in real time are input into the logistic regression fault prediction model that has completed parameter training to generate a fault prediction confidence.
[0010] The second aspect disclosed in the present application provides a device for predicting a fault of a Bianstone electronic cupping device, which is used in the above-mentioned method for predicting a fault of a Bianstone electronic cupping device. The device comprises: A first acquisition module, the first acquisition module is used to obtain the working state index of the grinding stone heating component, the infrared component and the ultrasonic component in real time, perform combined nonlinear calculation, and generate a first state index; A second acquisition module, which is used to obtain the working state index of the electric negative pressure component of the electronic cupping therapy part in real time, perform nonlinear calculation, and generate a second state index; A prediction model module, wherein the prediction model module is used to construct a logistic regression fault prediction model and perform parameter training, input the first state index and the second state index into the logistic regression fault prediction model after parameter training, and generate a fault prediction confidence; The determination module is used to determine whether the working state of the Bianstone electronic cupping therapy instrument is abnormal based on whether the fault prediction confidence exceeds a preset threshold.
[0011] The third aspect disclosed in the present application provides a computer device including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above-mentioned method for predicting faults of a Bianstone electronic cupping device when executing the computer program.
[0012] The fourth aspect disclosed in the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-mentioned method for predicting faults of a Bianstone electronic cupping therapy device.
[0013] The fifth aspect disclosed in the present application provides a computer program product, including a computer program or instructions, which, when executed by a processor, implements the steps of the above-mentioned method for predicting faults of a Bianstone electronic cupping device.
[0014] The beneficial effects of the present invention are: (1) Obtain the status index of each part and component of the Bianshi electronic cupping device in real time, perform nonlinear transformation, and input the logistic regression fault prediction model trained based on historical status index to achieve multi-dimensional and comprehensive fault prediction and health management for the Bianshi electronic cupping device; (2) Based on the nonlinear transformation method disclosed in the present invention, corresponding nonlinear transformation is performed on the numerical change characteristics of the state index of each component of the Bianstone electronic cupping device to improve the adaptability, generalization and robustness of the fault prediction method. BRIEF DESCRIPTION OF THE DRAWINGS
[0015] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0016] Figure 1 The figure is an overall flow chart of a fault prediction method for a Bianstone electronic cupping device.
[0017] Figure 2 This is a diagram of the overall structure of a fault prediction device for a Bianstone electronic cupping therapy instrument. DETAILED DESCRIPTION
[0018] 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 the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.
[0019] Example 1: like Figure 1 As shown, the embodiment of the present application provides a method for predicting faults of a Bianstone electronic cupping device, the method comprising the following steps: Step 1: Obtain the working state indexes of the grinding stone heating component, infrared component and ultrasonic component in real time, perform combined nonlinear calculation, and generate a first state index.
[0020] Step 1 specifically includes the following steps: Step 1.1, obtaining the temperature of the heating component in real time, performing maximum and minimum value normalization based on the maximum rated temperature and minimum rated temperature of the heating component, and generating a temperature normalization value T; Step 1.2: Obtain the infrared wavelength of the infrared component in real time, perform maximum and minimum value normalization based on the maximum and minimum rated wavelengths of the infrared component, and generate a wavelength normalization value. ; Step 1.3, obtain the ultrasonic frequency of the ultrasonic component in real time, normalize the maximum and minimum values according to the maximum rated frequency and minimum rated frequency of the ultrasonic component, and generate a frequency normalization value , and obtain the ultrasonic duty cycle k; Step 1.4: Use formula (1) to perform combined nonlinear calculation, where A is the first state index: Formula (1).
[0021] Step 2: Obtain the working state index of the electric negative pressure component of the electronic cupping therapy part in real time, perform nonlinear calculation, and generate a second state index.
[0022] Step 2 specifically includes the following steps: Step 2.1, obtaining the negative pressure index generated by the electric negative pressure component in real time, wherein the negative pressure index is expressed as a multiple of the standard atmospheric pressure, and the value range is 0 to 1; Step 2.2: Use formula (2) to calculate nonlinearly and generate the second state index, where p is the negative pressure index, e is the natural base, and B is the second state index: Formula (2).
[0023] Step 3: construct a logistic regression fault prediction model and perform parameter training. Input the first state index and the second state index obtained and generated in real time into the logistic regression fault prediction model that has completed parameter training to generate a fault prediction confidence.
[0024] Step 3 specifically includes the following steps: Step 3.1: Collect the first state index and the second state index of the Bianstone electronic cupping device in normal working state and fault state, and use the form of a one-hot vector to label the corresponding working state and fault state for each sample, with 1 representing the fault state and 0 representing the working state, to generate a training sample data set; Step 3.2: Construct a logistic regression fault prediction model in the form of formula (3), where y is the output of the logistic regression fault prediction model, that is, the fault prediction confidence, 、 and is a parameter, A and B are the first state index and the second state index respectively.
[0025] Random sampling is performed from a standard normal distribution with a variance of 1 and a mean of 0 to initialize parameters. The training sample dataset is input into the logistic regression fault prediction model. The loss function adopts the binary cross entropy loss function, which is back-propagated. The parameters are iteratively updated using the gradient descent method or the Newton method. At the same time, the parameters are regularized. The learning rate is set to 0.001 until the loss function value of the logistic regression fault prediction model converges. The parameter training is completed. The training goal is that the output of the logistic regression fault prediction model for each sample in the training sample dataset continuously approaches its corresponding one-hot vector label. Formula (3); Step 3.3: Input the first state index and the second state index acquired and generated in real time into the logistic regression fault prediction model that has completed parameter training to generate a fault prediction confidence.
[0026] Step 4: Determine whether the Bianshi electronic cupping device is operating abnormally based on whether the fault prediction confidence exceeds a preset threshold. The fault prediction confidence ranges from 0 to 1. If the preset threshold is set to 0.5, then the Bianshi electronic cupping device is considered to be operating abnormally when the fault prediction confidence exceeds 0.5. Obviously, the smaller the preset threshold, the higher the sensitivity of the fault determination.
[0027] In summary, the fault prediction method for a Bianstone electronic cupping device provided in the embodiments of the present application has the following technical effects: (1) Obtain the status index of each part and component of the Bianshi electronic cupping device in real time, perform nonlinear transformation, and input the logistic regression fault prediction model trained based on historical status index to achieve multi-dimensional and comprehensive fault prediction and health management for the Bianshi electronic cupping device; (2) Based on the nonlinear transformation method disclosed in the present invention, corresponding nonlinear transformation is performed on the numerical change characteristics of the state index of each component of the Bianstone electronic cupping device to improve the adaptability, generalization and robustness of the fault prediction method.
[0028] Example 2: Based on the same inventive concept as the method for predicting a fault of a Bianstone electronic cupping device in Example 1, Figure 2 As shown, the present application provides a device for predicting faults of a Bianstone electronic cupping device, the device comprising: A first acquisition module, the first acquisition module is used to obtain the working state index of the grinding stone heating component, the infrared component and the ultrasonic component in real time, perform combined nonlinear calculation, and generate a first state index; A second acquisition module, which is used to obtain the working state index of the electric negative pressure component of the electronic cupping therapy part in real time, perform nonlinear calculation, and generate a second state index; A prediction model module, wherein the prediction model module is used to construct a logistic regression fault prediction model and perform parameter training, input the first state index and the second state index into the logistic regression fault prediction model after parameter training, and generate a fault prediction confidence; The determination module is used to determine whether the working state of the Bianstone electronic cupping therapy instrument is abnormal based on whether the fault prediction confidence exceeds a preset threshold.
[0029] Through the above detailed description of a method for predicting a fault of a Bianstone electronic cupping therapy device, those skilled in the art can clearly understand a device for predicting a fault of a Bianstone electronic cupping therapy device in this embodiment. Since it corresponds to the method disclosed in the embodiment, the description is relatively simple. For relevant details, please refer to the description of the method part.
[0030] Example 3: In the third embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps of the above-mentioned method for predicting faults of a Bianstone electronic cupping device when executing the computer program.
[0031] Example 4: In a fourth embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned method for predicting faults of a Bianstone electronic cupping device are implemented.
[0032] Embodiment 5: In the fifth embodiment, a computer program product is provided, including a computer program or instructions. When the computer program or instructions are executed by a processor, the steps of the above-mentioned method for predicting the failure of a Bianstone electronic cupping device are implemented.
[0033] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0034] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present application. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application is not limited to the embodiments shown herein, but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. A method for predicting faults of a Bianstone electronic cupping device, characterized in that: The method comprises the following steps: Obtaining the working state indexes of the grinding stone heating component, the infrared component, and the ultrasonic component in real time, performing combined nonlinear calculations, and generating a first state index; Obtain the working status index of the electric negative pressure component of the electronic cupping therapy part in real time, perform nonlinear calculation, and generate a second status index; Constructing a logistic regression fault prediction model and performing parameter training, inputting the first state index and the second state index into the parameter-trained logistic regression fault prediction model to generate a fault prediction confidence level; Whether the working state of the Bianstone electronic cupping therapy device is abnormal is determined based on whether the fault prediction confidence exceeds a preset threshold.
2. The method for predicting a fault of a Bianstone electronic cupping device according to claim 1, wherein: The method of acquiring the working state indexes of the grinding stone heating component, the infrared component, and the ultrasonic component in real time, performing combined nonlinear calculation, and generating a first state index specifically includes the following steps: The temperature of the heating component is obtained in real time, and the maximum and minimum values are normalized according to the maximum and minimum rated temperatures of the heating component to generate a temperature normalization value T; Obtain the infrared wavelength of the infrared component in real time, perform maximum and minimum value normalization based on the maximum and minimum rated wavelengths of the infrared component, and generate a wavelength normalization value ; Acquire the ultrasonic frequency of the ultrasonic component in real time, normalize the maximum and minimum values according to the maximum and minimum rated frequencies of the ultrasonic component, and generate a frequency normalization value , and obtain the ultrasonic duty cycle k; The combined nonlinear calculation is performed using formula (1), where A is the first state index: Formula (1).
3. The method for predicting a fault of a Bianstone electronic cupping device according to claim 1, wherein: The method of obtaining the working state index of the electric negative pressure component of the electronic cupping therapy part in real time, performing nonlinear calculation, and generating a second state index specifically includes the following steps: Obtain the negative pressure index generated by the electric negative pressure component in real time, where the negative pressure index is expressed as a multiple of standard atmospheric pressure, with a value range of 0 to 1; The second state index is generated by nonlinear calculation using formula (2), where p is the negative pressure index, e is the natural base, and B is the second state index: Formula (2).
4. The method for predicting a fault of a Bianstone electronic cupping device according to claim 1, wherein: The method of constructing a logistic regression fault prediction model, performing parameter training, inputting the first state index and the second state index into the parameter-trained logistic regression fault prediction model, and generating a fault prediction confidence level specifically includes the following steps: The first state index and the second state index of the Bianstone electronic cupping device in normal working state and fault state are collected, and the corresponding working state and fault state of each sample are labeled in the form of a one-hot vector to generate a training sample data set; Construct a logistic regression fault prediction model and sample from a standard normal distribution to initialize parameters. Input the training sample dataset into the logistic regression fault prediction model and iteratively update the parameters using gradient descent or Newton's method. Regularize the parameters at the same time until the loss function value of the logistic regression fault prediction model converges, completing parameter training. The first state index and the second state index acquired and generated in real time are input into the logistic regression fault prediction model that has completed parameter training to generate a fault prediction confidence.
5. A device for predicting faults of a Bianstone electronic cupping therapy instrument, comprising: A first acquisition module, the first acquisition module is used to obtain the working state index of the grinding stone heating component, the infrared component and the ultrasonic component in real time, perform combined nonlinear calculation, and generate a first state index; A second acquisition module, which is used to obtain the working state index of the electric negative pressure component of the electronic cupping therapy part in real time, perform nonlinear calculation, and generate a second state index; A prediction model module, wherein the prediction model module is used to construct a logistic regression fault prediction model and perform parameter training, input the first state index and the second state index into the logistic regression fault prediction model after parameter training, and generate a fault prediction confidence; The determination module is used to determine whether the working state of the Bianstone electronic cupping therapy instrument is abnormal based on whether the fault prediction confidence exceeds a preset threshold.
6. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of a method for predicting a fault of a Bianstone electronic cupping device according to any one of claims 1 to 4 are implemented.
7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of a method for predicting a fault of a Bianstone electronic cupping device according to any one of claims 1 to 4 are implemented.
8. A computer program product comprising a computer program or instructions, characterized in that When the computer program or instruction is executed by a processor, the steps of a method for predicting a fault of a Bianstone electronic cupping device according to any one of claims 1 to 4 are implemented.