Medical centrifuge rotating speed calibration method and system based on base force sensor

By predicting the actual rotation speed of a medical centrifuge by a neural network model based on the base force sensor, the problem of large calibration errors at high speeds in the prior art is solved, and the accuracy of speed calibration and the reliability of experimental results are improved.

CN119001150AActive Publication Date: 2024-11-22深圳天溯计量检测股份有限公司

Patent Information

Application Number
CN202411282094.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-13
Publication Date
2024-11-22
Estimated Expiration
2044-09-13

AI Technical Summary

Technical Problem

The actual speed calibration of medical centrifuges has a large error at high speeds, and the calibration accuracy of existing Hall sensors or grating sensors is low, so it cannot effectively adapt to different samples and experimental needs.

Method used

Using a base force sensor method, by obtaining the vibration frequency of the centrifuge and the rotation control signal output from the drive chip, a neural network model is established for iterative calculations, predicting the actual rotation speed, and calibrating the rotation speed displayed by the centrifuge using the prediction results.

Benefits of technology

The accuracy of centrifuge speed calibration is improved, making the displayed speed closer to the real speed, and enhancing the accuracy of measurement and the reliability of experimental results.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119001150A_ABST
    Figure CN119001150A_ABST
Patent Text Reader

Abstract

The invention provides a medical centrifugal machine rotating speed calibration method based on a base force sensor, and belongs to the technical field of centrifugal machines, a medical centrifugal machine comprises a controller, the method is suitable for the controller, and the method comprises the steps that the first vibration frequency of the medical centrifugal machine in a first period is obtained; acquiring a first rotation control signal output by the driving chip in the first period, and determining a first rotation speed based on the first rotation control signal; obtaining a first actual rotation speed according to the input measurement result; taking the first vibration frequency, the first rotation speed and the first actual rotation speed as a training set, importing the training set into a target neural network model, and inputting the target vibration frequency and the target rotation speed into the target neural network model to obtain a predicted target actual rotation speed; and calibrating the rotating speed displayed on the medical centrifuge based on the target actual rotating speed. The invention provides a rotating speed calibration system for a medical centrifugal machine.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of centrifuges, and in particular to a medical centrifuge speed calibration method and system based on a base force sensor. Background Art

[0002] A medical centrifuge is a device specifically used in medical laboratories. It generates strong centrifugal force through high-speed rotation, thereby separating and concentrating various biological samples. This equipment plays a vital role in medical research, clinical diagnosis, and the preparation of biological products. Medical centrifuges usually have a variety of speed and centrifugal force options to adapt to different types of samples and experimental requirements. Their design usually focuses on safety and ease of use to ensure the safety of laboratory personnel during operation and improve work efficiency.

[0003] The actual speed of a medical centrifuge is usually obtained by combining the control signal output by the motor control chip. However, in actual use, due to various factors such as sample weight and air resistance, there is a certain error between the actual speed and the speed obtained by the control signal. The actual speed of the centrifuge is generally calibrated using a Hall sensor or a grating sensor. However, when the centrifuge speed is high, the error of the Hall sensor or grating sensor is large and the calibration accuracy is low. Summary of the invention

[0004] The embodiments of the present application provide a medical centrifuge speed calibration method and system based on a base force sensor to improve the above-mentioned problems.

[0005] In order to achieve the above objectives, this application adopts the following technical solutions: In a first aspect, an embodiment of the present application proposes a medical centrifuge speed calibration method based on a base force sensor, characterized in that the medical centrifuge includes a controller, and the method is applicable to the controller, including: The controller obtains a first vibration frequency of the medical centrifuge in a first cycle; The controller obtains a first rotation control signal output by the driving chip in a first cycle, and determines a first rotation speed based on the first rotation control signal; The controller obtains a first actual rotation speed according to the input measurement result; The controller uses the first vibration frequency, the first rotation speed and the first actual rotation speed as a training set and imports them into a target neural network model. The target neural network model is used to iteratively calculate the first vibration frequency, the first rotation speed and the first actual rotation speed, and output a predicted actual rotation speed according to the input vibration frequency and the target rotation speed; The controller obtains the target vibration frequency of the medical centrifuge within the target period and the target rotation control signal output by the driving chip within the target period, and determines the target rotation speed based on the target rotation control signal; The controller inputs the target vibration frequency and the target rotation speed into the target neural network model to obtain the predicted target actual rotation speed; The speed displayed on a medical centrifuge is calibrated based on the target actual speed.

[0006] In combination with the first aspect, in some embodiments, the controller obtains a target vibration frequency of the medical centrifuge within a target period and a target rotation control signal output by the driving chip within the target period, and determines a target rotation speed based on the target rotation control signal, including: The controller determines a second rotation speed based on the first rotation speed, and a speed difference between the first rotation speed and the second rotation speed is a conditional rotation speed; The controller obtains a second vibration frequency of the medical centrifuge in a second period; The controller inputs the first vibration frequency, the second vibration frequency and the conditional rotation speed into a first neural network prediction model, and the first neural network prediction model is used to output a predicted second vibration frequency according to the input conditional rotation speed and the input first vibration frequency; The controller determines a target conditional rotation speed based on the target rotation speed and the first rotation speed; The controller inputs the target rotation speed and the first vibration frequency into the first neural network prediction model, and determines the target vibration frequency according to the output result of the first neural network training model.

[0007] In conjunction with the first aspect, in some embodiments, the method further comprises: The controller obtains the weight of multiple sample parameters in the medical centrifuge during the first cycle; The controller uses the first vibration frequency, the first rotation speed and the first actual rotation speed as a training set and imports them into a target neural network model. The target neural network model is used to iteratively calculate the first vibration frequency, the first rotation speed and the first actual rotation speed, and output a predicted actual rotation speed according to the input vibration frequency and the target rotation speed, and also includes: The controller takes the first vibration frequency, the first rotation speed, multiple sample parameter weights, and the first actual rotation speed as a training set and imports them into the target neural network model. The target neural network model is used to iteratively calculate the first vibration frequency, the first rotation speed, multiple sample parameter weights and the first actual rotation speed, and output the predicted actual rotation speed based on the input vibration frequency, sample parameter weight and target rotation speed.

[0008] In combination with the first aspect, in some embodiments, the controller uses the first vibration frequency, the first rotation speed, a plurality of sample parameter weights, and the first actual rotation speed as a training set and imports them into a target neural network model. The target neural network model is used to iteratively calculate the first vibration frequency, the first rotation speed, a sample parameter weight, and the first actual rotation speed, and output a predicted actual rotation speed based on the input vibration frequency, sample parameter weight, and target rotation speed, including: The controller performs data processing on the first vibration frequency, the first rotation speed, a sample parameter weight and the first actual rotation speed, wherein the first vibration frequency, the first rotation speed and the sample parameter weight are used as three different dimensions, and the three dimensions constitute a characteristic vector of the actual rotation speed; The controller controls the target neural network training model to perform iterative calculations based on the feature vector.

[0009] In combination with the first aspect, in some embodiments, the controller uses the first vibration frequency, the first rotation speed, a plurality of sample parameter weights, and the first actual rotation speed as a training set and imports them into a target neural network model. The target neural network model is used to iteratively calculate the first vibration frequency, the first rotation speed, a sample parameter weight, and the first actual rotation speed, and output a predicted actual rotation speed based on the input vibration frequency, sample parameter weight, and target rotation speed, including: The controller obtains the predicted actual rotation speed, and feeds the predicted actual rotation speed back to the target neural network training model, and determines the error value according to the feedback result; If the error value is greater than the preset threshold, the target neural network training model continues to perform iterative calculations; If the error value is less than or equal to the preset threshold, the target neural network training model stops iterative calculation and outputs the predicted actual rotation speed.

[0010] In combination with the first aspect, in some implementations, the controller obtains the predicted actual rotation speed, and feeds the predicted actual rotation speed back to the target neural network training model, and determines the error value according to the feedback result, including: The predicted actual rotation speed is compared with the first actual rotation speed. If the first actual rotation speed is greater than the predicted actual rotation speed, the relationship between the error value, the first actual rotation speed and the predicted actual rotation speed satisfies: =( - ) in, is the error value, is the first actual rotation speed, is the predicted actual rotation speed.

[0011] In combination with the first aspect, in some implementations, the predicted actual rotation speed is compared with the first actual rotation speed. If the first actual rotation speed is less than the predicted actual rotation speed, the relationship between the error value, the first actual rotation speed and the predicted actual rotation speed satisfies: =( - ) in, is the error value, is the first actual rotation speed, is the predicted actual rotation speed.

[0012] The second aspect of the present application provides a medical centrifuge speed calibration system, the medical centrifuge includes a controller, and the system is configured as follows: The controller obtains a first vibration frequency of the medical centrifuge in a first cycle; The controller obtains a first rotation control signal output by the driving chip in a first cycle, and determines a first rotation speed based on the first rotation control signal; The controller obtains a first actual rotation speed according to the input measurement result; The controller uses the first vibration frequency, the first rotation speed and the first actual rotation speed as a training set and imports them into a target neural network model. The target neural network model is used to iteratively calculate the first vibration frequency, the first rotation speed and the first actual rotation speed, and output a predicted actual rotation speed according to the input vibration frequency and the target rotation speed; The controller obtains the target vibration frequency of the medical centrifuge within the target period and the target rotation control signal output by the driving chip within the target period, and determines the target rotation speed based on the target rotation control signal; The controller inputs the target vibration frequency and the target rotation speed into the target neural network model to obtain the predicted target actual rotation speed; The speed displayed on a medical centrifuge is calibrated based on the target actual speed.

[0013] In conjunction with the second aspect, in some embodiments, the system is configured as follows: The controller obtains the target vibration frequency of the medical centrifuge within the target period and the target rotation control signal output by the driving chip within the target period, and determines the target rotation speed based on the target rotation control signal, including: The controller determines a second rotation speed based on the first rotation speed, and a speed difference between the first rotation speed and the second rotation speed is a conditional rotation speed; The controller obtains a second vibration frequency of the medical centrifuge in a second period; The controller inputs the first vibration frequency, the second vibration frequency and the conditional rotation speed into a first neural network prediction model, and the first neural network prediction model is used to output a predicted second vibration frequency according to the input conditional rotation speed and the input first vibration frequency; The controller determines a target conditional rotation speed based on the target rotation speed and the first rotation speed; The controller inputs the target rotation speed and the first vibration frequency into the first neural network prediction model, and determines the target vibration frequency according to the output result of the first neural network training model.

[0014] In conjunction with the second aspect, in some embodiments, the system is configured as follows: The controller obtains the weight of multiple sample parameters in the medical centrifuge during the first cycle; The controller uses the first vibration frequency, the first rotation speed and the first actual rotation speed as a training set and imports them into a target neural network model. The target neural network model is used to iteratively calculate the first vibration frequency, the first rotation speed and the first actual rotation speed, and output a predicted actual rotation speed according to the input vibration frequency and the target rotation speed, and also includes: The controller takes the first vibration frequency, the first rotation speed, multiple sample parameter weights, and the first actual rotation speed as a training set and imports them into the target neural network model. The target neural network model is used to iteratively calculate the first vibration frequency, the first rotation speed, multiple sample parameter weights and the first actual rotation speed, and output the predicted actual rotation speed based on the input vibration frequency, sample parameter weight and target rotation speed.

[0015] In conjunction with the second aspect, in some embodiments, the system is configured as follows: The controller uses the first vibration frequency, the first rotation speed, a plurality of sample parameter weights, and the first actual rotation speed as a training set and imports them into a target neural network model. The target neural network model is used to iteratively calculate the first vibration frequency, the first rotation speed, a sample parameter weight, and the first actual rotation speed, and output a predicted actual rotation speed according to the input vibration frequency, sample parameter weight, and target rotation speed, including: The controller performs data processing on the first vibration frequency, the first rotation speed, a sample parameter weight and the first actual rotation speed, wherein the first vibration frequency, the first rotation speed and the sample parameter weight are used as three different dimensions, and the three dimensions constitute a characteristic vector of the actual rotation speed; The controller controls the target neural network training model to perform iterative calculations based on the feature vector.

[0016] In conjunction with the second aspect, in some embodiments, the system is configured as follows: The controller uses the first vibration frequency, the first rotation speed, a plurality of sample parameter weights, and the first actual rotation speed as a training set and imports them into a target neural network model. The target neural network model is used to iteratively calculate the first vibration frequency, the first rotation speed, a sample parameter weight, and the first actual rotation speed, and output a predicted actual rotation speed according to the input vibration frequency, sample parameter weight, and target rotation speed, including: The controller obtains the predicted actual rotation speed, and feeds the predicted actual rotation speed back to the target neural network training model, and determines the error value according to the feedback result; If the error value is greater than the preset threshold, the target neural network training model continues to perform iterative calculations; If the error value is less than or equal to the preset threshold, the target neural network training model stops iterative calculation and outputs the predicted actual rotation speed.

[0017] In conjunction with the second aspect, in some embodiments, the system is configured as follows: The controller obtains the predicted actual rotation speed and feeds the predicted actual rotation speed back to the target neural network training model, and determines the error value according to the feedback result, including: The predicted actual rotation speed is compared with the first actual rotation speed. If the first actual rotation speed is greater than the predicted actual rotation speed, the relationship between the error value, the first actual rotation speed and the predicted actual rotation speed satisfies: =( - ) in, is the error value, is the first actual rotation speed, is the predicted actual rotation speed.

[0018] In conjunction with the second aspect, in some embodiments, the system is configured as follows: The predicted actual rotation speed is compared with the first actual rotation speed. If the first actual rotation speed is less than the predicted actual rotation speed, the error value, the relationship between the first actual rotation speed and the predicted actual rotation speed satisfies: =( - ) in, is the error value, is the first actual rotation speed, is the predicted actual rotation speed.

[0019] A third aspect of an embodiment of the present invention provides an electronic device, the electronic device comprising: At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method proposed in the first aspect of the embodiment of the present invention.

[0020] A fourth aspect of an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method provided in the first aspect of the embodiment of the present invention.

[0021] In summary, the above method and device have the following technical effects: The present application proposes a medical centrifuge speed calibration system, which establishes a neural network training model by acquiring a first vibration frequency of the centrifuge in a first cycle, a first rotation control signal output by a driving chip in the first cycle, and a rotation speed obtained by direct measurement in the first cycle. After the trained neural network training model is obtained through iterative training of multiple data, the vibration frequency in actual use and the rotation speed output by the control chip are introduced into the neural network training model, and the actual rotation speed is output according to the predicted result, and the speed displayed by the centrifuge is calibrated using the speed, so that the speed displayed by the centrifuge is closer to the actual rotation speed rather than the input rotation speed, thereby improving the accuracy of measurement. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 A schematic flow chart of a medical centrifuge speed calibration method based on a base force sensor proposed in an embodiment of the present application. DETAILED DESCRIPTION

[0023] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are 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 creative work are within the scope of protection of the present invention.

[0024] The embodiment of the present application proposes a medical centrifuge speed calibration method based on a base force sensor. The medical centrifuge includes a controller. The method is applicable to the controller and includes: S101: The controller obtains the first vibration frequency of the medical centrifuge in the first cycle.

[0025] It is understandable that the vibration frequency is often related to the actual rotation speed, but due to the interference of other noise signals, it is not advisable and accurate to directly obtain the rotation speed from the vibration frequency. In this embodiment, the method for obtaining the vibration frequency can use accessories such as acceleration sensors, or other feasible methods, which are not limited in this embodiment.

[0026] S102: The controller obtains a first rotation control signal output by the driving chip in a first cycle, and determines a first rotation speed based on the first rotation control signal.

[0027] It can be understood that the first rotation control signal output by the driving chip, the rotation speed data therein, is a signal of the actual rotation speed without being affected by external conditions.

[0028] S103: The controller obtains the first actual rotation speed according to the input measurement result.

[0029] It can be understood that the rotation speed is relatively slow in the first cycle, and at this time, a device such as a grating or a Hall sensor can be used to collect a more accurate actual rotation speed.

[0030] S104: The controller uses the first vibration frequency, the first rotation speed and the first actual rotation speed as a training set and imports them into a target neural network model. The target neural network model is used to iteratively calculate the first vibration frequency, the first rotation speed and the first actual rotation speed, and output a predicted actual rotation speed based on the input vibration frequency and the target rotation speed.

[0031] It can be understood that the controller is responsible for integrating a series of key parameters, including the first vibration frequency, the first rotation speed, and the first actual rotation speed, into a training set. This training set is then imported into a specific target neural network model. The role of this target neural network model is to perform a series of complex iterative calculation processes. Through these calculations, the model is able to process the input vibration frequency data and the preset target rotation speed information. After analysis and learning by the model, a predicted actual rotation speed value is finally output. This predicted value is based on the model's learning and understanding of previous training data, and aims to be as close to the actual rotation speed as possible, thereby providing an important reference for the optimization of related equipment or systems.

[0032] After the training set is imported into the target neural network model, the model will first perform a series of data preprocessing steps. These steps may include data cleaning, normalization or standardization to ensure the consistency of input data and the training efficiency of the model. Next, the model will use the preset algorithm and architecture to perform in-depth iterative calculations on the first vibration frequency, the first rotation speed, and the first actual rotation speed.

[0033] During the iterative calculation process, the model continuously adjusts its internal parameters to minimize the difference between the predicted actual rotation speed and the actual actual rotation speed. This adjustment is achieved through the back-propagation algorithm, which can guide the model how to update its weights and bias terms based on the error signal.

[0034] As the number of iterations increases, the model's predictive ability gradually improves. The training process ends when the model's performance on the training set reaches a preset threshold or stopping condition. At this point, the model has learned how to infer the predicted actual rotation speed from the input vibration frequency and target rotation speed.

[0035] In addition to the training set, the model may also need to be evaluated by the validation set and test set to ensure its generalization ability and stability. The validation set is used to adjust the model's hyperparameters during the training process to avoid overfitting; while the test set is used to evaluate the final performance of the model after the training is completed.

[0036] Since the weight of the sample is one of the main conditions that cause vibration, in some embodiments, the controller can also use the first vibration frequency, the first rotation speed, multiple sample parameter weights, and the first actual rotation speed as a training set and import them into the target neural network model. The target neural network model is used to iteratively calculate the first vibration frequency, the first rotation speed, multiple sample parameter weights and the first actual rotation speed, and output the predicted actual rotation speed based on the input vibration frequency, sample parameter weight and target rotation speed.

[0037] Specifically, as an implementation mode, the controller performs data processing on a first vibration frequency, a first rotation speed, a sample parameter weight and a first actual rotation speed, wherein the first vibration frequency, the first rotation speed and a sample parameter weight are three different dimensions, and the three dimensions constitute a feature vector of the actual rotation speed. Then, the controller controls the target neural network training model to perform iterative calculations based on the feature vector.

[0038] It is understandable that the controller will perform a comprehensive analysis on the four key parameters of the first vibration frequency, the first rotation speed, a sample parameter weight and the first actual rotation speed. Here, the first vibration frequency, the first rotation speed and the sample parameter weight are regarded as three different dimensions, which together constitute a feature vector, and the feature vector can comprehensively describe the characteristics of the actual rotation speed.

[0039] The controller uses this feature vector as input and passes it to the target neural network training model. The neural network training model iterates and calculates based on this feature vector, and continuously adjusts and optimizes the internal weights and biases to achieve the purpose of accurately predicting and controlling the actual rotation speed. In this way, the controller can effectively use data from multiple dimensions to improve the accuracy and reliability of the actual rotation speed prediction, thereby achieving precise control of the entire system.

[0040] It is understandable that how to define the end of the iterative calculation can be determined by the size of the error value in some embodiments. Specifically, the controller obtains the predicted actual rotation speed, and feeds the predicted actual rotation speed back to the target neural network training model, and determines the error value based on the feedback result. If the error value is greater than the preset threshold, the target neural network training model continues to perform iterative calculations. It is understandable that the preset threshold is artificially determined. When the error value is less than a certain level, it proves that the predicted value is getting closer to the true value. If the error value is less than or equal to the preset threshold, the target neural network training model stops the iterative calculation and outputs the predicted actual rotation speed.

[0041] Specifically, the predicted actual rotation speed may be compared with the first actual rotation speed. If the first actual rotation speed is greater than the predicted actual rotation speed, the relationship between the error value, the first actual rotation speed and the predicted actual rotation speed satisfies: =( - ) Of course, if the first actual rotation speed is less than the predicted actual rotation speed, the relationship between the error value, the first actual rotation speed and the predicted actual rotation speed satisfies: =( - ) in, is the error value, is the first actual rotation speed, is the predicted actual rotation speed.

[0042] It is understandable that when the error value is less than the preset value, the training process of the neural network training model is stopped. This is because when the error value is less than a certain threshold, the model has predicted the data accurately enough, and continuing to train the model will not be effective and may cause problems such as overfitting.

[0043] S105: The controller obtains the target vibration frequency of the medical centrifuge within the target period and the target rotation control signal output by the driving chip within the target period, and determines the target rotation speed based on the target rotation control signal.

[0044] It is understandable that in this embodiment, the target cycle is also the actual cycle. In actual use, the rotation speed of the target cycle is relatively high, and the error is relatively large when the rotation speed is directly obtained by using a grating or Hall sensor. Therefore, a more accurate actual rotation speed can be determined from the frequency of vibration by machine learning.

[0045] S106: The controller inputs the target vibration frequency and the target rotation speed into the target neural network model to obtain the predicted target actual rotation speed. The controller inputs two key parameters, the target vibration frequency and the target rotation speed, into the pre-set target neural network model. Through the complex calculation and learning process of this model, the system can predict the actual rotation speed of the target object in actual operation. In this way, the controller can adjust and optimize the vibration frequency and rotation speed of the target object in real time to achieve the best working state.

[0046] S107: Calibrate the speed displayed on the medical centrifuge based on the target actual speed Understandably, in order to ensure the accuracy and reliability of medical centrifuges, the speed displayed on the centrifuge needs to be accurately calibrated according to the target actual speed. This process involves comparing the speed displayed on the centrifuge display with the actual measured speed to ensure consistency between the two. Through this calibration, it can be ensured that the centrifuge can achieve the expected separation effect during actual use, thereby improving the accuracy and repeatability of experimental results.

[0047] The present application proposes a medical centrifuge speed calibration method based on a base force sensor. A neural network training model is established by acquiring a first vibration frequency of the centrifuge in a first cycle, a first rotation control signal output by a driving chip in the first cycle, and a rotation speed obtained by direct measurement in the first cycle. After the trained neural network training model is obtained through iterative training of multiple data, the vibration frequency in actual use and the rotation speed output by the control chip are introduced into the neural network training model, and the actual rotation speed is output according to the predicted result. The speed is used to calibrate the speed displayed by the centrifuge, so that the speed displayed by the centrifuge is closer to the actual rotation speed rather than the input rotation speed, thereby improving the accuracy of measurement.

[0048] Based on the same inventive concept, the embodiment of the present application also proposes a medical centrifuge speed calibration system, the medical centrifuge includes a controller, and the system is configured as follows: The controller obtains a first vibration frequency of the medical centrifuge in a first cycle; The controller obtains a first rotation control signal output by the driving chip in a first cycle, and determines a first rotation speed based on the first rotation control signal; The controller obtains a first actual rotation speed according to the input measurement result; The controller uses the first vibration frequency, the first rotation speed and the first actual rotation speed as a training set and imports them into a target neural network model. The target neural network model is used to iteratively calculate the first vibration frequency, the first rotation speed and the first actual rotation speed, and output a predicted actual rotation speed according to the input vibration frequency and the target rotation speed; The controller obtains the target vibration frequency of the medical centrifuge within the target period and the target rotation control signal output by the driving chip within the target period, and determines the target rotation speed based on the target rotation control signal; The controller inputs the target vibration frequency and the target rotation speed into the target neural network model to obtain the predicted target actual rotation speed; The speed displayed on a medical centrifuge is calibrated based on the target actual speed.

[0049] In some embodiments, the system is configured to: The controller obtains the target vibration frequency of the medical centrifuge within the target period and the target rotation control signal output by the driving chip within the target period, and determines the target rotation speed based on the target rotation control signal, including: The controller determines a second rotation speed based on the first rotation speed, and a speed difference between the first rotation speed and the second rotation speed is a conditional rotation speed; The controller obtains a second vibration frequency of the medical centrifuge in a second period; The controller inputs the first vibration frequency, the second vibration frequency and the conditional rotation speed into a first neural network prediction model, and the first neural network prediction model is used to output a predicted second vibration frequency according to the input conditional rotation speed and the input first vibration frequency; The controller determines a target conditional rotation speed based on the target rotation speed and the first rotation speed; The controller inputs the target rotation speed and the first vibration frequency into the first neural network prediction model, and determines the target vibration frequency according to the output result of the first neural network training model.

[0050] In some embodiments, the system is configured to: The controller obtains the weight of multiple sample parameters in the medical centrifuge during the first cycle; The controller uses the first vibration frequency, the first rotation speed and the first actual rotation speed as a training set and imports them into a target neural network model. The target neural network model is used to iteratively calculate the first vibration frequency, the first rotation speed and the first actual rotation speed, and output a predicted actual rotation speed according to the input vibration frequency and the target rotation speed, and also includes: The controller takes the first vibration frequency, the first rotation speed, multiple sample parameter weights, and the first actual rotation speed as a training set and imports them into the target neural network model. The target neural network model is used to iteratively calculate the first vibration frequency, the first rotation speed, multiple sample parameter weights and the first actual rotation speed, and output the predicted actual rotation speed based on the input vibration frequency, sample parameter weight and target rotation speed.

[0051] In some embodiments, the system is configured to: The controller uses the first vibration frequency, the first rotation speed, a plurality of sample parameter weights, and the first actual rotation speed as a training set and imports them into a target neural network model. The target neural network model is used to iteratively calculate the first vibration frequency, the first rotation speed, a sample parameter weight, and the first actual rotation speed, and output a predicted actual rotation speed according to the input vibration frequency, sample parameter weight, and target rotation speed, including: The controller performs data processing on the first vibration frequency, the first rotation speed, a sample parameter weight and the first actual rotation speed, wherein the first vibration frequency, the first rotation speed and the sample parameter weight are used as three different dimensions, and the three dimensions constitute a characteristic vector of the actual rotation speed; The controller controls the target neural network training model to perform iterative calculations based on the feature vector.

[0052] In some embodiments, the system is configured to: The controller uses the first vibration frequency, the first rotation speed, a plurality of sample parameter weights, and the first actual rotation speed as a training set and imports them into a target neural network model. The target neural network model is used to iteratively calculate the first vibration frequency, the first rotation speed, a sample parameter weight, and the first actual rotation speed, and output a predicted actual rotation speed according to the input vibration frequency, sample parameter weight, and target rotation speed, including: The controller obtains the predicted actual rotation speed, and feeds the predicted actual rotation speed back to the target neural network training model, and determines the error value according to the feedback result; If the error value is greater than the preset threshold, the target neural network training model continues to perform iterative calculations; If the error value is less than or equal to the preset threshold, the target neural network training model stops iterative calculation and outputs the predicted actual rotation speed.

[0053] In some embodiments, the system is configured to: The controller obtains the predicted actual rotation speed and feeds the predicted actual rotation speed back to the target neural network training model, and determines the error value according to the feedback result, including: The predicted actual rotation speed is compared with the first actual rotation speed. If the first actual rotation speed is greater than the predicted actual rotation speed, the relationship between the error value, the first actual rotation speed and the predicted actual rotation speed satisfies: =( - ) in, is the error value, is the first actual rotation speed, is the predicted actual rotation speed.

[0054] In conjunction with the second aspect, in some embodiments, the system is configured as follows: The predicted actual rotation speed is compared with the first actual rotation speed. If the first actual rotation speed is less than the predicted actual rotation speed, the error value, the relationship between the first actual rotation speed and the predicted actual rotation speed satisfies: =( - ) in, is the error value, is the first actual rotation speed, is the predicted actual rotation speed.

[0055] The present application proposes a medical centrifuge speed calibration system, which establishes a neural network training model by acquiring a first vibration frequency of the centrifuge in a first cycle, a first rotation control signal output by a driving chip in the first cycle, and a rotation speed obtained by direct measurement in the first cycle. After the trained neural network training model is obtained through iterative training of multiple data, the vibration frequency in actual use and the rotation speed output by the control chip are introduced into the neural network training model, and the actual rotation speed is output according to the predicted result, and the speed displayed by the centrifuge is calibrated using the speed, so that the speed displayed by the centrifuge is closer to the actual rotation speed rather than the input rotation speed, thereby improving the accuracy of measurement.

[0056] Based on the same inventive concept, an embodiment of the present application further proposes an electronic device, the electronic device comprising: At least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the medical centrifuge speed calibration method of the embodiment of the present application.

[0057] In addition, to achieve the above-mentioned purpose, an embodiment of the present application further proposes a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the medical centrifuge speed calibration method of the embodiment of the present application.

[0058] The following is a detailed introduction to the various components of electronic equipment: The processor is the control center of the electronic device, which can be a processor or a general term for multiple processing elements. For example, the processor is one or more central processing units (CPUs), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention, such as one or more microprocessors (digital signal processors, DSPs), or one or more field programmable gate arrays (field programmable gate arrays, FPGAs).

[0059] Optionally, the processor can perform various functions of the electronic device by running or executing a software program stored in the memory, and calling data stored in the memory.

[0060] The memory is used to store the software program for executing the solution of the present invention, and the execution is controlled by the processor. The specific implementation method can refer to the above method embodiment and will not be repeated here.

[0061] Optionally, the memory may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory may be integrated with the processor, or may exist independently and be coupled to the processor through an interface circuit of the electronic device, which is not specifically limited in the embodiments of the present invention.

[0062] A transceiver is used to communicate with a network device or a terminal device.

[0063] Optionally, the transceiver may include a receiver and a transmitter, wherein the receiver is used to implement a receiving function, and the transmitter is used to implement a sending function.

[0064] Optionally, the transceiver may be integrated with the processor, or may exist independently and be coupled to the processor via an interface circuit of the router, which is not specifically limited in the embodiment of the present invention.

[0065] In addition, the technical effects of the electronic device can refer to the technical effects of the data transmission method in the above method embodiment, which will not be repeated here.

[0066] It should be understood that the processor in the embodiment of the present invention may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0067] It should also be understood that the memory in the embodiments of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), and direct RAM bus RAM (DR RAM).

[0068] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When a computer instruction or computer program is loaded or executed on a computer, a process or function according to an embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. Computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0069] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0070] In the present invention, "at least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0071] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0072] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

Claims

1. A medical centrifuge speed calibration method based on a base force sensor, characterized in that: The medical centrifuge includes a controller, and the method is applicable to the controller, including: The controller obtains a first vibration frequency of the medical centrifuge in a first cycle; The controller acquires a first rotation control signal output by the driving chip in the first period, and determines a first rotation speed based on the first rotation control signal; The controller obtains a first actual rotation speed according to the input measurement result; The controller uses the first vibration frequency, the first rotation speed and the first actual rotation speed as a training set and imports them into a target neural network model, wherein the target neural network model is used to iteratively calculate the first vibration frequency, the first rotation speed and the first actual rotation speed, and output a predicted actual rotation speed according to the input vibration frequency and target rotation speed; The controller obtains a target vibration frequency of the medical centrifuge within a target period and a target rotation control signal output by the driving chip within the target period, and determines a target rotation speed based on the target rotation control signal; The controller inputs the target vibration frequency and the target rotation speed into the target neural network model to obtain a predicted target actual rotation speed; The rotation speed displayed on the medical centrifuge is calibrated based on the target actual rotation speed.

2. A medical centrifuge speed calibration method based on a base force sensor according to claim 1, characterized in that: The controller obtains a target vibration frequency of the medical centrifuge within a target period and a target rotation control signal output by the driving chip within the target period, and determines a target rotation speed based on the target rotation control signal, including: The controller determines a second rotation speed based on the first rotation speed, and a speed difference between the first rotation speed and the second rotation speed is a conditional rotation speed; The controller obtains a second vibration frequency of the medical centrifuge in a second period; The controller inputs the first vibration frequency, the second vibration frequency and the conditional rotation speed into a first neural network prediction model, and the first neural network prediction model is used to output a predicted second vibration frequency according to the input conditional rotation speed and the input first vibration frequency; The controller determines a target conditional rotation speed based on the target rotation speed and the first rotation speed; The controller inputs the target rotation speed and the first vibration frequency into the first neural network prediction model, and determines the target vibration frequency according to the output result of the first neural network training model.

3. A medical centrifuge speed calibration method based on a base force sensor according to claim 2, characterized in that: The method further comprises: The controller obtains a plurality of sample parameter weights in the medical centrifuge during the first cycle; The controller uses the first vibration frequency, the first rotation speed and the first actual rotation speed as a training set and imports them into a target neural network model, wherein the target neural network model is used to iteratively calculate the first vibration frequency, the first rotation speed and the first actual rotation speed, and output a predicted actual rotation speed according to the input vibration frequency and target rotation speed, and further includes: The controller uses the first vibration frequency, the first rotation speed, multiple sample parameter weights, and the first actual rotation speed as a training set and imports them into a target neural network model. The target neural network model is used to iteratively calculate the first vibration frequency, the first rotation speed, multiple sample parameter weights, and the first actual rotation speed, and output the predicted actual rotation speed based on the input vibration frequency, sample parameter weight, and target rotation speed.

4. A medical centrifuge speed calibration method based on a base force sensor according to claim 3, characterized in that: The controller uses the first vibration frequency, the first rotation speed, a plurality of the sample parameter weights, and the first actual rotation speed as a training set and imports them into a target neural network model. The target neural network model is used to iteratively calculate the first vibration frequency, the first rotation speed, a sample parameter weight, and the first actual rotation speed, and output a predicted actual rotation speed according to the input vibration frequency, sample parameter weight, and target rotation speed, including: The controller performs data processing on the first vibration frequency, the first rotation speed, one of the sample parameter weights, and the first actual rotation speed, wherein the first vibration frequency, the first rotation speed, and one of the sample parameter weights are used as three different dimensions, and the three dimensions constitute a feature vector of the actual rotation speed; The controller controls the target neural network training model to perform iterative calculation based on the feature vector.

5. A medical centrifuge speed calibration method based on a base force sensor according to claim 4, characterized in that: The controller uses the first vibration frequency, the first rotation speed, a plurality of the sample parameter weights, and the first actual rotation speed as a training set and imports them into a target neural network model. The target neural network model is used to iteratively calculate the first vibration frequency, the first rotation speed, a sample parameter weight, and the first actual rotation speed, and output a predicted actual rotation speed according to the input vibration frequency, sample parameter weight, and target rotation speed, including: The controller obtains the predicted actual rotation speed, feeds back the predicted actual rotation speed to the target neural network training model, and determines an error value according to the feedback result; If the error value is greater than a preset threshold, the target neural network training model continues to perform iterative calculations; If the error value is less than or equal to the preset threshold, the target neural network training model stops iterative calculation and outputs the predicted actual rotation speed.

6. A medical centrifuge speed calibration method based on a base force sensor according to claim 5, characterized in that: The controller obtains the predicted actual rotation speed, feeds back the predicted actual rotation speed to the target neural network training model, and determines an error value according to the feedback result, including: The predicted actual rotation speed is compared with the first actual rotation speed. If the first actual rotation speed is greater than the predicted actual rotation speed, the relationship between the error value, the first actual rotation speed and the predicted actual rotation speed satisfies: =( - ) in, is the error value, is the first actual rotation speed, is the predicted actual rotation speed.

7. A medical centrifuge speed calibration method based on a base force sensor according to claim 6, characterized in that: The predicted actual rotation speed is compared with the first actual rotation speed. If the first actual rotation speed is less than the predicted actual rotation speed, the relationship between the error value, the first actual rotation speed and the predicted actual rotation speed satisfies: =( - ) in, is the error value, is the first actual rotation speed, is the predicted actual rotation speed.

8. A medical centrifuge speed calibration system based on a base force sensor, characterized in that: The medical centrifuge includes a controller, the system being configured to: The controller obtains a first vibration frequency of the medical centrifuge in a first cycle; The controller acquires a first rotation control signal output by the driving chip in the first period, and determines a first rotation speed based on the first rotation control signal; The controller obtains a first actual rotation speed according to the input measurement result; The controller uses the first vibration frequency, the first rotation speed and the first actual rotation speed as a training set and imports them into a target neural network model, wherein the target neural network model is used to iteratively calculate the first vibration frequency, the first rotation speed and the first actual rotation speed, and output a predicted actual rotation speed according to the input vibration frequency and target rotation speed; The controller obtains a target vibration frequency of the medical centrifuge within a target period and a target rotation control signal output by the driving chip within the target period, and determines a target rotation speed based on the target rotation control signal; The controller inputs the target vibration frequency and the target rotation speed into the target neural network model to obtain a predicted target actual rotation speed; The rotation speed displayed on the medical centrifuge is calibrated based on the target actual rotation speed.

9. An electronic device, characterized in that: include: at least one processor; And, a memory communicatively connected to at least one of the processors; wherein the memory stores instructions executable by at least one of the processors, and the instructions are executed by at least one of the processors so that at least one of the processors can execute the method as set forth in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, wherein when the program is executed by a processor, the method as claimed in any one of claims 1 to 7 is implemented.

Citation Information

Patent Citations

  • Neural-network self-correcting control method of permanent magnet synchronous motor speed loop

    CN102497156A

  • Deep learning-based rotation speed detection method and system

    CN110018322A

  • Rotating speed measurement and control method based on high-precision centrifugal acceleration system

    CN113359885A

  • Method and system for controlling rotating speed of brushless direct current motor

    CN117477993A

  • Determination of Machine Rotational Speed based on Vibration Spectral Plots

    US20210199492A1

Cited By

  • Intelligent monitoring method for ultracentrifuge tube based on sensor network

    CN120346921A

  • Rotating speed calibration method and system for centrifugal machine

    CN120587014A