A method and system for dental electric motor speed control for dental chairs

Abstract

The present application relates to the technical field of electromechanical control, and in particular to a dental electric motor rotating speed control method and system for a dental chair, comprising: acquiring a torque constant of a dental electric motor, current data of a current time node and a plurality of historical time nodes thereof; taking the product of the current data acquired at each time node and the torque constant as an instantaneous load at each time node; taking the average of the instantaneous loads at each time node as a dynamic reference load, calculating a load ratio and a load gradient at each time node, constructing a calibration hardness index based on the load ratio and the load gradient, and improving a loss function in a machine learning model based on the calibration hardness index; predicting an operating state of the dental electric motor at a next time point by using the improved machine learning model, and controlling the start and stop of the rotating speed of the dental electric motor based on the operating state. The present application solves the problem of poor control effect of the existing model.

Description

Technical Field

[0001] This invention relates to the field of electromechanical control technology. More specifically, this invention relates to a method and system for controlling the speed of a dental electric motor for a dental chair. Background Technology

[0002] In modern dental medicine, the dental chair, as a key medical device, plays an indispensable role in clinical operation with its accompanying dental motor. Dental motors are typically used to remove plaque, tartar, and other deposits from the tooth surface, and their speed control directly affects operational efficiency, patient comfort, and the safety of the tooth surface. However, traditional dental motor speed control relies heavily on fixed settings or simple manual adjustments, lacking intelligent responsiveness to changes in actual operational load. This method cannot adaptively adjust to differences in tooth hardness, tartar thickness, or operator posture among patients, easily leading to excessive motor load and vibration during operation, and even the risk of overheating or enamel damage. Insufficient speed can also affect cleaning effectiveness, reducing clinical efficiency and patient satisfaction.

[0003] In attempting to achieve intelligent control, existing research often utilizes logistic regression algorithms to predict or classify motor load states. Logistic regression algorithms determine whether an operational state is abnormal by constructing a relationship between input features and binary classification outputs, using probabilistic methods.

[0004] However, this method has significant shortcomings in dental cleaning procedures. First, logistic regression is essentially a linear model, making it difficult to fully capture the non-linear characteristics of motor load changes instantaneously during operation. For example, the load may spike dramatically upon contact with tartar or plaque, and linear models often fail to accurately reflect such abrupt changes, leading to prediction lag or misjudgment. Second, logistic regression is sensitive to noise and outliers. In actual operation, the current signal of a dental electric motor may be affected by sensor noise, subtle patient movements, or changes in the operator's technique. Traditional logistic regression easily misjudges these short-term fluctuations as abnormal states, reducing the model's robustness. Furthermore, logistic regression has limited effectiveness when processing high-dimensional time-series data, failing to fully utilize the dynamic trend information in historical load sequences. It lacks the ability to adjust the motor's instantaneous response, making it difficult to achieve continuous, smooth, and safe speed control, resulting in poor control performance. Summary of the Invention

[0005] To address the problem of poor control performance mentioned in the background art, the present invention provides solutions in the following aspects.

[0006] In a first aspect, the present invention provides a method for controlling the rotational speed of a dental electric motor for a dental chair, comprising: acquiring the torque constant of the dental electric motor, current data at the current time point and at multiple historical time points; multiplying the current data acquired at each time point by the torque constant as the instantaneous load at each time point; using the average instantaneous load at each time point as the dynamic reference load, calculating the load ratio at each time point, wherein the load ratio is the ratio of the instantaneous load at each time point to the dynamic reference load; calculating the load gradient at each time point, wherein the load gradient is used to characterize the rate of change of load over time; acquiring a calibration hardness index at each time point, wherein the calibration hardness index is positively correlated with the load ratio and load gradient at each time point; predicting the operating state of the dental electric motor at the next moment using an improved machine learning model, and controlling the start and stop of the dental electric motor rotational speed based on the operating state; wherein the improved machine learning model includes a loss function, wherein the loss function is positively correlated with the calibration hardness index at each time point and negatively correlated with the average calibration hardness index at multiple historical time points.

[0007] The above-mentioned technical solution can not only effectively capture sudden load changes caused by high-hardness targets such as tartar or plaque during operation, improving the sensitivity and response speed to abnormal working conditions, but also take into account the operational stability under stable working conditions, making the teeth cleaning process safer, more efficient and adaptive, thereby significantly improving the control effect during the teeth cleaning operation.

[0008] Furthermore, Load gradient at time node for: , for Instantaneous load at a given time point for Instantaneous load at a given time point To set the time interval.

[0009] The above technical solution transforms static load signals into dynamic gradient features, thereby enabling it to sensitively capture the load fluctuations of dental electric motors in a short period of time. Whether it is a small load fluctuation during normal enamel manipulation or a sudden increase in load when contacting high-hardness targets such as tartar or plaque, it can be accurately reflected.

[0010] Furthermore, Calibration hardness index at a given time point for: , for Load ratio at a given time point It is the hyperbolic tangent function. for Load gradient at time node is the gradient normalization constant.

[0011] The above technical solution organically combines the load ratio and load gradient, and uses the hyperbolic tangent function to perform nonlinear mapping of the gradient, thereby realizing the adaptive response of the calibration hardness index to load changes. This ensures that the index remains flat when the load is stable, guaranteeing operational stability, while the index rapidly amplifies when the load suddenly increases or when contacting high-hardness targets, thus enabling it to keenly reflect instantaneous impacts and abnormal states. This not only enhances the ability to distinguish between different hardness objects, but also provides a reliable basis for intelligent speed control.

[0012] Furthermore, the loss function for: , for Calibrated hardness index at a specific time point. This represents the average of the calibrated hardness index across multiple historical time points. This represents the total number of historical time points.

[0013] The above technical solution constructs a loss function that quantifies the degree of deviation of the instantaneous state from the normal operating condition by summing the squares of the deviations of the calibration hardness index at each time point from the historical average. This ensures that the loss value remains low and stable when the scaler head is working on healthy tooth enamel, while the loss value increases rapidly when it comes into contact with tartar or other high-hardness materials. This provides a sensitive and reliable abnormality detection signal that can drive intelligent speed adjustment and safety protection mechanisms, significantly improving the real-time response capability, accuracy, and operational safety of the scaling operation.

[0014] Furthermore, the machine learning model is a logistic regression model.

[0015] Furthermore, the operating state includes: normal state and abnormal state.

[0016] Furthermore, the start and stop of the dental electric motor speed is controlled based on the operating state, specifically: if the operating state is abnormal, the dental electric motor is controlled to stop running.

[0017] Furthermore, the current data is cleaned and missing value filling is performed.

[0018] The above technical solution effectively eliminates abnormal fluctuations caused by sensor noise, transient interference, and data loss by cleaning and filling missing values ​​in the collected current data. This makes the subsequent calculations of instantaneous load, load ratio, and load gradient more accurate and stable, thereby improving the monitoring accuracy and reliability of the dental electric motor's operating status.

[0019] Furthermore, it also includes training the machine learning model, specifically: inputting the training set into the pre-built machine learning model for training; during the training process, calculating the loss between the output predicted value and the label; adjusting the model parameters using gradient descent to minimize the prediction error; iteratively adjusting the parameters of the machine learning model until the loss is less than a set value or the set number of training iterations is reached, and finally obtaining the trained machine learning model.

[0020] In a second aspect, the present invention provides a dental electric motor speed control system for a dental chair, comprising a memory and a processor, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a dental electric motor speed control method for a dental chair as described above is implemented.

[0021] The beneficial effects of this invention are as follows:

[0022] This invention utilizes an improved machine learning model to predict the operating state, thereby achieving intelligent control of speed start-stop. Simultaneously, it quantifies the deviation of the current state from historical normal states through a loss function, driving the optimization of model parameters and adjustment of control strategies. This allows for the sensitive detection of sudden load changes caused by high-hardness targets such as tartar or plaque during operation, improving response speed and detection accuracy to abnormal conditions. Furthermore, it maintains operational stability and safety under stable conditions. Through model training and iterative optimization, it continuously improves predictive capabilities, achieving efficient, safe, intelligent, and adaptive control of the dental cleaning process, significantly enhancing the control effect during the cleaning procedure. Attached Figure Description

[0023] Figure 1 This is a flowchart schematically illustrating a method for controlling the speed of a dental electric motor for a dental chair according to an embodiment of the present invention;

[0024] Figure 2 This is a schematic block diagram illustrating the structure of a dental electric motor speed control system for a dental chair according to an embodiment of the present invention. Detailed Implementation

[0025] An embodiment of a method for controlling the speed of a dental electric motor for use in a dental chair.

[0026] like Figure 1 The flowchart shown is a method for controlling the speed of a dental electric motor in a dental chair according to an embodiment of the present invention, which includes the following steps:

[0027] S1: Obtain the torque constant of the dental electric motor, the current time point and the current data of multiple historical time points, and calculate the instantaneous load at each time point.

[0028] In a preferred embodiment, the torque constant of the dental electric motor is obtained from the motor specifications provided by the motor manufacturer or through experimental calibration. The experimental calibration involves measuring the linear relationship between the output torque and the input current under constant load conditions and calculating its proportionality coefficient as the torque constant. Current data is acquired by installing a Hall effect current sensor or current transformer in the power supply circuit of the dental electric motor to output the instantaneous current value of the motor at various time points in real time.

[0029] Furthermore, since the acquired raw current data often contains noise, interference, or missing points, data preprocessing is necessary. In this embodiment, firstly, a moving average filter or Kalman filter algorithm is used to smooth the current signal to eliminate high-frequency components introduced by power supply fluctuations, environmental electromagnetic interference, or sensor noise itself. Secondly, missing values ​​in the acquisition sequence are filled, for example, by using linear interpolation for compensation, to avoid abnormal calculation results due to missing data. Thirdly, in the data cleaning stage, unreasonable data points can be removed according to a preset current threshold range to ensure the validity and reliability of the data input. Finally, the product of the current data acquired at each time point and the torque constant is used as the instantaneous load at each time point.

[0030] S2: The average instantaneous load at each time point is used as the dynamic reference load, and then the load ratio and load gradient at each time point are calculated.

[0031] In a preferred embodiment, the average instantaneous load at each time point is used as the dynamic reference load, and the ratio of the instantaneous load at each time point to the dynamic reference load is used as the load ratio.

[0032] When the scaler tip works on healthy tooth enamel, the instantaneous load is approximately equal to the dynamic reference load, and the load ratio fluctuates slightly around 1. When the scaler tip comes into contact with harder materials such as plaque or tartar, the instantaneous load increases significantly, resulting in a value much greater than 1. By converting the load signal into a dimensionless ratio form, adaptive normalization processing of load changes under different operating conditions is achieved. This allows for stable judgment during normal enamel operations, while significantly amplifying the load difference when encountering harder targets such as plaque or tartar, thereby improving the sensitivity and accuracy of identifying abnormal areas.

[0033] Load gradient at time node for: , for Instantaneous load at a given time point for Instantaneous load at a given time point The time interval can be set to 5, or it can be set according to the actual situation.

[0034] By calculating the load change rate within a set time interval on the time series, the originally static load signal is transformed into a dynamic characteristic quantity. This enables the motor to sensitively capture load fluctuations in a short period of time, achieving rapid response to instantaneous impacts, sudden operations, or abnormal contact states. This helps improve real-time performance and sensitivity under complex working conditions, while providing more reliable and detailed judgment criteria for subsequent anomaly detection and intelligent control.

[0035] S3: Obtain calibration hardness indices at each time point based on load ratio and load gradient.

[0036] In a preferred embodiment, Calibration hardness index at a given time point for: , for Load ratio at a given time point It is the hyperbolic tangent function. for Load gradient at time node is the gradient normalization constant.

[0037] When the dental scaler head comes into contact with a real and hard obstacle (such as tartar), it not only causes the motor to exhibit a high load ratio at that moment, but is also often accompanied by a rapid load change at the instant of contact, resulting in a significantly increased load gradient. Based on this physical characteristic, this technical solution uses the load ratio as a basic indicator to reflect the relative load level borne by the motor under different operating conditions, thereby intuitively characterizing the hardness difference of the object being processed in a macroscopic sense. Simultaneously, the load gradient is introduced as a dynamic feature into the indicator construction to capture the load fluctuations of the motor over a short period of time, thus reflecting the hardness response characteristics of the object being processed in a microscopic transient state.

[0038] To avoid computational instability caused by excessively large gradient values, this scheme introduces a hyperbolic tangent function to perform nonlinear mapping and normalization of the gradient. This ensures that when the load variation is small, the fluctuation of the calibration hardness index remains smooth, guaranteeing the stability of the testing process. However, when the load suddenly increases, the function mapping rapidly amplifies its impact, enabling the index to sensitively reflect instantaneous impacts or abnormal situations. In this way, the calibration hardness index achieves a balance between stability and sensitivity. It can not only accurately reflect the relative hardness differences of different tissues or substances such as enamel, plaque, and tartar, but also effectively identify sudden states and irregular fluctuations that occur during the operation. This provides a more reliable real-time monitoring basis for the teeth cleaning process, improving adaptability and testing accuracy in complex oral environments.

[0039] S4: Predict the operating state of the dental electric motor at the next moment using an improved machine learning model, and control the start and stop of the dental electric motor speed based on the operating state.

[0040] In a preferred embodiment, the operating state includes a normal state and an abnormal state. The start and stop of the dental electric motor speed are controlled based on the operating state. Specifically, if the operating state is an abnormal state, the dental electric motor is controlled to stop running.

[0041] The improved machine learning model includes a loss function, which... for: , for Calibrated hardness index at a specific time point. This represents the average of the calibrated hardness index across multiple historical time points. This represents the total number of historical time points.

[0042] By using the average calibration hardness index under historical conditions as an ideal benchmark, and taking the difference between the current index and the benchmark as an anomaly measure, and quantifying this deviation using the form of squared loss, the impact of significant anomalies is amplified at the numerical level. This ensures that the loss remains at an extremely low level when the scaler tip is working on healthy enamel, but increases rapidly once it comes into contact with tartar or other materials with higher hardness. This numerical change not only accurately reflects the difference between the current working condition and the normal state, but also serves as a sensitive trigger signal to drive subsequent intelligent control and feedback mechanisms, thereby improving the real-time detection capability and response accuracy in complex oral environments.

[0043] The machine learning model is a logistic regression model.

[0044] Furthermore, the machine learning model is trained. For example, a logistic regression model is trained as follows: First, a training set is constructed and obtained. This training set includes the torque constant of a dental electric motor, current data at the current time point, and current data at multiple historical time points. Labels are manually set. The training set is then input into a pre-constructed logistic regression model for training. During training, the loss between the output predicted value and the label is calculated. The model parameters are adjusted using gradient descent to minimize the prediction error. The parameters of the logistic regression model are iteratively adjusted until the loss is less than a set value or the set number of training iterations is reached, ultimately resulting in a trained logistic regression model.

[0045] The present invention utilizes an improved machine learning model to accurately predict future operating states, enabling intelligent start-stop control of the dental electric motor's speed. This allows for stable operation during normal enamel procedures, while rapidly identifying and adjusting the motor's state when encountering high-hardness targets such as tartar or plaque. This significantly improves the sensitivity and accuracy of load detection, ensuring operational safety and comfort. Furthermore, the optimized model enhances real-time response and robustness in complex oral environments, thereby significantly improving control during teeth cleaning procedures.

[0046] An embodiment of a dental electric motor speed control system for a dental chair:

[0047] like Figure 2 As shown, a structural block diagram of a dental electric motor speed control system for a dental chair according to an embodiment of the present invention includes a processor and a memory.

[0048] The present invention also provides a dental electric motor speed control system for dental chairs. For example... Figure 2 As shown, the system includes a processor and a memory, the memory storing computer program instructions, which, when executed by the processor, implement the above-described method for controlling the speed of a dental electric motor for a dental chair according to the present invention.

[0049] The dental electric motor speed control system for dental chairs also includes other components well known to those skilled in the art, such as communication interfaces. The settings and functions of these components are known in the art and will not be described in detail here.

[0050] In this invention, the aforementioned memory can be any tangible medium containing or storing a program that can be used or combined with an instruction execution system, apparatus, or device. For example, a computer-readable storage medium can be any suitable magnetic 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 desired information and can be accessed by an application, module, or both. Any such computer storage medium can be part of a device or accessible to or connected to a device. Any application or module described in this invention can be implemented using computer-readable / executable instructions stored or otherwise maintained by such a computer-readable medium.

[0051] In the description of this specification, "multiple" or "several" means at least two, such as two, three or more, unless otherwise explicitly specified.

[0052] While this specification has shown and described numerous embodiments of the invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Many modifications, alterations, and alternatives will occur to those skilled in the art without departing from the spirit and essence of the invention. It should be understood that various alternatives to the embodiments of the invention described herein may be employed in the practice of this invention.

Claims

1. A method for controlling the speed of a dental electric motor for a dental chair, characterized in that, include: Obtain the torque constant of the dental electric motor, the current data at the current time point and the current data at multiple historical time points; multiply the current data obtained at each time point by the torque constant as the instantaneous load at each time point; The average instantaneous load at each time point is used as the dynamic reference load. The load ratio at each time point is calculated, which is the ratio of the instantaneous load to the dynamic reference load at each time point. The load gradient at each time point is calculated, which is used to characterize the rate of change of load over time. The calibration hardness index is obtained at each time point, and the calibration hardness index is positively correlated with the load ratio and load gradient at each time point. An improved machine learning model is used to predict the operating state of a dental electric motor at the next moment, and the start and stop of the dental electric motor speed is controlled based on the operating state. The improved machine learning model includes a loss function, which is positively correlated with the calibration hardness index at each time point and negatively correlated with the mean of the calibration hardness index at multiple historical time points.

2. The method for controlling the speed of a dental electric motor for a dental chair according to claim 1, characterized in that, Load gradient at time node for: , for Instantaneous load at a given time point for Instantaneous load at a given time point To set the time interval.

3. The method for controlling the speed of a dental electric motor for a dental chair according to claim 1, characterized in that, Calibration hardness index at a given time point for: , for Load ratio at a given time point It is the hyperbolic tangent function. for Load gradient at time node is the gradient normalization constant.

4. The method for controlling the speed of a dental electric motor for a dental chair according to claim 1, characterized in that, loss function for: , for Calibrated hardness index at a specific time point This represents the average of the calibrated hardness index across multiple historical time points. This represents the total number of historical time points.

5. A method for controlling the speed of a dental electric motor for a dental chair according to claim 1, characterized in that, The machine learning model is a logistic regression model.

6. The method for controlling the speed of a dental electric motor for a dental chair according to claim 1, characterized in that, The operating status includes: normal status and abnormal status.

7. A method for controlling the speed of a dental electric motor for a dental chair according to claim 1, characterized in that, The starting and stopping of the dental electric motor speed is controlled based on the operating status. Specifically, if the operating status is abnormal, the dental electric motor is controlled to stop running.

8. A method for controlling the speed of a dental electric motor for a dental chair according to claim 1, characterized in that, The current data is cleaned and missing value filling is performed.

9. A method for controlling the speed of a dental electric motor for a dental chair according to claim 1, characterized in that, This also includes training machine learning models, specifically: The training set is input into a pre-built machine learning model for training. During training, the loss between the output prediction value and the label is calculated; the model parameters are adjusted using gradient descent to minimize the prediction error; the parameters of the machine learning model are iteratively adjusted until the loss is less than a set value or the set number of training iterations is reached, and finally a trained machine learning model is obtained.

10. A dental electric motor speed control system for a dental chair, characterized in that, It includes a memory and a processor, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a method for controlling the speed of a dental electric motor for a dental chair as described in any one of claims 1 to 9 is implemented.

Images