A method and system for calibrating the rotational speed of a medical centrifuge based on a base force sensor

Abstract

The present application provides a method for calibrating the rotational speed of a medical centrifuge based on a base force sensor, belonging to the technical field of centrifuges. The medical centrifuge includes a controller. The method is applicable to the controller and includes: obtaining the first vibration frequency of the medical centrifuge within the first period; obtaining the first rotation control signal output by the drive chip within the first period, and determining the first rotation speed based on the first rotation control signal; obtaining the first actual rotation speed according to the input measurement result; using the first vibration frequency, the first rotation speed, and the first actual rotation speed as a training set, importing it into the target neural network model, inputting the target vibration frequency and the target rotation speed into the target neural network model, and obtaining the predicted target actual rotation speed; calibrating the rotation speed displayed on the medical centrifuge based on the target actual rotation speed. The present application provides a system for calibrating the rotational speed of a medical centrifuge.

Description

Technical Field

[0001] This application relates to the technical field of centrifuges, and particularly to a method and system for calibrating the rotational speed of a medical centrifuge based on a base force sensor. Background Art

[0002] A medical centrifuge is a device specifically used in medical laboratories. It generates a strong centrifugal force through high-speed rotation to achieve the separation and concentration of various biological samples. This device plays a crucial role in medical research, clinical diagnosis, and the preparation of biological products. Medical centrifuges usually have multiple rotational speeds and centrifugal force options to adapt to different types of samples and experimental requirements. Their designs generally focus on safety and ease of use to ensure the safety of laboratory personnel during operation and improve work efficiency.

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

[0004] Embodiments of this application provide a method and system for calibrating the rotational speed of a medical centrifuge based on a base force sensor to improve the above problems.

[0005] To achieve the above objective, this application adopts the following technical solutions:

[0006] In a first aspect, embodiments of this application propose a method for calibrating the rotational speed of a medical centrifuge based on a base force sensor. The medical centrifuge includes a controller, and the method is applicable to the controller and includes:

[0007] The controller obtains the first vibration frequency of the medical centrifuge within the first period;

[0008] The controller obtains the first rotation control signal output by the drive chip within the first period, and determines the first rotation speed based on the first rotation control signal;

[0009] The controller obtains the first actual rotation speed according to the input measurement result;

[0010] The controller takes the first vibration frequency, the first rotation speed, 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 perform iterative calculations on the first vibration frequency, the first rotation speed, and the first actual rotation speed, and based on the input vibration frequency and the target rotation speed, outputs the predicted actual rotation speed;

[0011] The controller obtains the target vibration frequency of the medical centrifuge within the target period and the target rotation control signal output by the drive chip within the target period, and determines the target rotation speed based on the target rotation control signal;

[0012] 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;

[0013] Calibrate the rotation speed displayed on the medical centrifuge based on the target actual rotation speed.

[0014] Combined with the first aspect, in some embodiments, the controller obtains the target vibration frequency of the medical centrifuge within the target period and the target rotation control signal output by the drive chip within the target period, and determining the target rotation speed based on the target rotation control signal includes:

[0015] The controller determines the second rotation speed based on the first rotation speed, and the speed difference between the first rotation speed and the second rotation speed is the conditional rotation speed;

[0016] The controller obtains the second vibration frequency of the medical centrifuge within the second period;

[0017] The controller inputs the first vibration frequency, the second vibration frequency, and the conditional rotation speed into the first neural network prediction model. The first neural network prediction model is used to output the predicted second vibration frequency according to the input conditional rotation speed and the input first vibration frequency;

[0018] The controller determines the target conditional rotation speed based on the target rotation speed and the first rotation speed;

[0019] 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.

[0020] Combined with the first aspect, in some embodiments, the method further includes:

[0021] The controller obtains the weights of multiple sample parameters in the medical centrifuge within the first period;

[0022] The controller uses the first vibration frequency, the first rotation speed, and the first actual rotation speed as a training set and imports it into the target neural network model. The target neural network model is used to perform iterative calculations on the first vibration frequency, the first rotation speed, and the first actual rotation speed, and according to the input vibration frequency and the target rotation speed, outputs the predicted actual rotation speed. It further includes:

[0023] 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 it into the target neural network model. The target neural network model is used to perform iterative calculations on the first vibration frequency, the first rotation speed, multiple sample parameter weights, and the first actual rotation speed, and according to the input vibration frequency, sample parameter weights, and the target rotation speed, outputs the predicted actual rotation speed.

[0024] Combined with the first aspect, in some embodiments, 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 it into the target neural network model. The target neural network model is used to perform iterative calculations on the first vibration frequency, the first rotation speed, one sample parameter weight, and the first actual rotation speed, and according to the input vibration frequency, sample parameter weights, and the target rotation speed, outputs the predicted actual rotation speed, including:

[0025] The controller processes the data of the first vibration frequency, the first rotation speed, one sample parameter weight, and the first actual rotation speed. Among them, the first vibration frequency, the first rotation speed, and one sample parameter weight are used as three different dimensions, and the three dimensions form the feature vector of the actual rotation speed;

[0026] The controller controls the target neural network training model to perform iterative calculations based on the feature vector.

[0027] Combined with the first aspect, in some embodiments, 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 it into the target neural network model. The target neural network model is used to perform iterative calculations on the first vibration frequency, the first rotation speed, one sample parameter weight, and the first actual rotation speed, and according to the input vibration frequency, sample parameter weights, and the target rotation speed, outputs the predicted actual rotation speed, including:

[0028] The controller obtains the predicted actual rotation speed, feeds the predicted actual rotation speed back to the target neural network training model, and determines the error value according to the feedback result;

[0029] If the error value is greater than the preset threshold, the target neural network training model continues to perform iterative calculations;

[0030] 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.

[0031] Combined with the first aspect, in some embodiments, the controller obtains the predicted actual rotation speed, and feeds back the predicted actual rotation speed to the target neural network training model, and determines the error value according to the feedback result, including:

[0032] Compare the predicted actual rotation speed with the first actual rotation speed. If the first actual rotation speed is greater than the predicted actual rotation speed, the error value, the relationship between the first actual rotation speed and the predicted actual rotation speed satisfies:

[0033] = ( - )

[0034] Wherein, is the error value, is the first actual rotation speed, is the predicted actual rotation speed.

[0035] Combined with the first aspect, in some embodiments, compare the predicted actual rotation speed 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:

[0036] = ( - )

[0037] Wherein, is the error value, is the first actual rotation speed, is the predicted actual rotation speed.

[0038] A second aspect of the present application proposes a medical centrifuge rotation speed calibration system. The medical centrifuge includes a controller. The system is configured to:

[0039] The controller obtains the first vibration frequency of the medical centrifuge in the first period;

[0040] The controller obtains the first rotation control signal output by the drive chip in the first period, and determines the first rotation speed based on the first rotation control signal;

[0041] The controller obtains the first actual rotation speed according to the input measurement result;

[0042] The controller takes the first vibration frequency, the first rotation speed, 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 perform iterative calculations on the first vibration frequency, the first rotation speed, and the first actual rotation speed, and output the predicted actual rotation speed according to the input vibration frequency and the target rotation speed;

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

[0044] 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;

[0045] Calibrate the rotation speed displayed on the medical centrifuge based on the target actual rotation speed.

[0046] Combined with the second aspect, in some embodiments, the system is configured to:

[0047] The controller obtains the target vibration frequency of the medical centrifuge within the target period and the target rotation control signal output by the drive chip within the target period, and determines the target rotation speed based on the target rotation control signal, including:

[0048] The controller determines a second rotation speed based on the first rotation speed, and the speed difference between the first rotation speed and the second rotation speed is the conditional rotation speed;

[0049] The controller obtains the second vibration frequency of the medical centrifuge within the second period;

[0050] The controller inputs the first vibration frequency, the second vibration frequency, and the conditional rotation speed into the first neural network prediction model. The first neural network prediction model is used to output the predicted second vibration frequency according to the input conditional rotation speed and the input first vibration frequency;

[0051] The controller determines the target conditional rotation speed based on the target rotation speed and the first rotation speed;

[0052] 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.

[0053] Combined with the second aspect, in some embodiments, the system is configured to:

[0054] The controller obtains the weights of multiple sample parameters in the medical centrifuge within the first period;

[0055] The controller takes the first vibration frequency, the first rotation speed, and the first actual rotation speed as a training set and imports it into the target neural network model. The target neural network model is used to perform iterative calculations on the first vibration frequency, the first rotation speed, and the first actual rotation speed, and according to the input vibration frequency and the target rotation speed, outputs the predicted actual rotation speed. It further includes:

[0056] 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 it into the target neural network model. The target neural network model is used to perform iterative calculations on the first vibration frequency, the first rotation speed, multiple sample parameter weights, and the first actual rotation speed, and according to the input vibration frequency, sample parameter weights, and the target rotation speed, outputs the predicted actual rotation speed.

[0057] Combined with the second aspect, in some embodiments, the system is configured to:

[0058] 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 it into the target neural network model. The target neural network model is used to perform iterative calculations on the first vibration frequency, the first rotation speed, one sample parameter weight, and the first actual rotation speed, and according to the input vibration frequency, sample parameter weight, and the target rotation speed, outputs the predicted actual rotation speed, including:

[0059] The controller performs data processing on the first vibration frequency, the first rotation speed, one sample parameter weight, and the first actual rotation speed. Among them, the first vibration frequency, the first rotation speed, and one sample parameter weight serve as three different dimensions, and the three dimensions form the feature vector of the actual rotation speed;

[0060] The controller controls the target neural network training model to perform iterative calculations based on the feature vector.

[0061] Combined with the second aspect, in some embodiments, the system is configured to:

[0062] 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 it into the target neural network model. The target neural network model is used to perform iterative calculations on the first vibration frequency, the first rotation speed, one sample parameter weight, and the first actual rotation speed, and according to the input vibration frequency, sample parameter weight, and the target rotation speed, outputs the predicted actual rotation speed, including:

[0063] The controller obtains the predicted actual rotation speed and feeds it back to the target neural network training model, and determines the error value according to the feedback result;

[0064] If the error value is greater than the preset threshold, the target neural network training model continues to perform iterative calculations;

[0065] If the error value is less than or equal to the preset threshold, the target neural network training model stops iterative calculations and outputs the predicted actual rotation speed.

[0066] Combined with the second aspect, in some embodiments, the system is configured to:

[0067] The controller obtains the predicted actual rotation speed and feeds back the predicted actual rotation speed to the target neural network training model, and determines the error value according to the feedback result, including:

[0068] Compare the predicted actual rotation speed 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:

[0069] =( - )

[0070] where, is the error value, is the first actual rotation speed, is the predicted actual rotation speed.

[0071] Combined with the second aspect, in some embodiments, the system is configured to:

[0072] Compare the predicted actual rotation speed 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:

[0073] =( - )

[0074] where, is the error value, is the first actual rotation speed, is the predicted actual rotation speed.

[0075] A third aspect of the embodiments of the present invention provides an electronic device, and the electronic device includes:

[0076] 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 to enable the at least one processor to execute the method proposed in the first aspect of the embodiments of the present invention.

[0077] The fourth aspect of the embodiments of the present invention proposes a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, it implements the method proposed in the first aspect of the embodiments of the present invention.

[0078] In summary, the above method and device have the following technical effects:

[0079] A medical centrifuge speed calibration system proposed in this application establishes a neural network training model by obtaining the first vibration frequency of the centrifuge, the first rotation control signal output by the drive chip, and the speed directly measured within the first period. After obtaining the trained neural network training model through iterative training of multiple data, the vibration frequency and the rotation speed output by the control chip during actual use are imported 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 this speed, so that the speed displayed by the centrifuge is closer to the true rotation speed rather than the input rotation speed, improving the measurement accuracy. Description of the Drawings

[0080] Figure 1 It is a schematic flowchart of a medical centrifuge speed calibration method based on a base force sensor proposed in the embodiments of this application. Detailed Embodiments

[0081] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0082] The embodiments of this application propose a medical centrifuge speed calibration method based on a base force sensor. The medical centrifuge includes a controller, and the method is applicable to the controller and includes:

[0083] S101: The controller obtains the first vibration frequency of the medical centrifuge within the first period.

[0084] It can be understood that the vibration frequency is often related to the actual rotational speed. However, due to the interference of other noise signals, it is not advisable and inaccurate to directly obtain the rotational speed from the vibration frequency. In this embodiment, for the method of obtaining the vibration frequency, accessories such as acceleration sensors or other feasible methods can be used, which are not limited in this embodiment.

[0085] S102: The controller obtains the first rotation control signal output by the drive chip within the first period, and determines the first rotation speed based on the first rotation control signal.

[0086] It can be understood that the rotational speed data on the first rotation control signal output by the drive chip is also the signal of the actual rotational speed without the influence of external conditions.

[0087] S103: The controller obtains the first actual rotation speed according to the input measurement result.

[0088] It can be understood that the rotational speed is relatively slow during the first period. At this time, devices such as gratings or Hall sensors can be used to collect more accurate actual rotational speeds.

[0089] S104: The controller takes the first vibration frequency, the first rotation speed, 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 perform iterative calculations on the first vibration frequency, the first rotation speed, and the first actual rotation speed, and output the predicted actual rotation speed according to the input vibration frequency and the target rotation speed.

[0090] 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 can process the input vibration frequency data and the preset target rotation speed information. After the analysis and learning of the model, a predicted actual rotation speed value is finally output. This predicted value is based on the model's learning and understanding of the previous training data, aiming to be as close as possible to the rotational speed in the real situation, so as to provide an important reference basis for the optimization of related devices or systems.

[0091] After importing the training set 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, etc., to ensure the consistency of the input data and the training efficiency of the model. Next, the model will use the preset algorithms and architectures to perform in-depth iterative calculations on the first vibration frequency, the first rotation speed, and the first actual rotation speed.

[0092] During the iterative calculation process, the model continuously adjusts its internal parameters to minimize the difference between the predicted actual rotation speed and the true actual rotation speed. This adjustment is achieved through the backpropagation algorithm, which can guide the model on how to update its weights and bias terms based on the error signal.

[0093] As the number of iterations increases, the prediction ability of the model gradually improves. When the performance of the model on the training set reaches the preset threshold or stopping condition, the training process ends. At this time, the model has learned how to infer the predicted actual rotation speed from the input vibration frequency and target rotation speed.

[0094] In addition to the training set, the model may also need to be evaluated using a validation set and a test set to ensure its generalization ability and stability. The validation set is used to adjust the hyperparameters of the model during the training process to avoid overfitting; while the test set is used to evaluate the final performance of the model after training is completed.

[0095] Since the weight of the sample is one of the main conditional factors causing vibration, in some embodiments, the controller can also use the first vibration frequency, the first rotation speed, the weights of multiple sample parameters, and the first actual rotation speed as the training set and import them into the target neural network model. The target neural network model is used to perform iterative calculations on the first vibration frequency, the first rotation speed, the weights of multiple sample parameters, 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.

[0096] Specifically, as an embodiment, the controller processes the data of the first vibration frequency, the first rotation speed, the weight of one sample parameter, and the first actual rotation speed. Among them, the first vibration frequency, the first rotation speed, and the weight of one sample parameter are used as three different dimensions, and the three dimensions form the 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.

[0097] It can be understood that the controller will comprehensively analyze these four key parameters: the first vibration frequency, the first rotation speed, the weight of one sample parameter, 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 form a feature vector that can comprehensively describe the characteristics of the actual rotation speed.

[0098] The controller uses this feature vector as input and passes it to the target neural network training model. The neural network training model performs iterative calculations based on this feature vector, continuously adjusting and optimizing the internal weights and biases to accurately predict and control the actual rotation speed. In this way, the controller can effectively utilize data in multiple dimensions, improve the accuracy and reliability of predicting the actual rotation speed, and thus achieve precise control of the entire system.

[0099] It can be understood that in some embodiments, the end of the iterative calculation can be determined by the magnitude of the error value. Specifically, the controller obtains the predicted actual rotation speed and feeds it 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 the iterative calculation. It can be understood that the preset threshold is determined manually. When the error value is less than a certain degree, 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.

[0100] Specifically, the predicted actual rotation speed can 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:

[0101] = ( - )

[0102] 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:

[0103] = ( - )

[0104] Wherein, is the error value, is the first actual rotation speed, is the predicted actual rotation speed.

[0105] It can be understood 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 can already accurately predict the data, and continuing to train the model has little effect and may cause problems such as overfitting.

[0106] 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 drive chip within the target period, and determines the target rotation speed based on the target rotation control signal.

[0107] It can be understood that in this embodiment, the target period is also the actually used period. During the actual use process, the rotation speed in the target period is relatively high. If the rotation speed is directly obtained by using a grating or Hall sensor, the error is relatively large. Therefore, the machine learning method can be used to determine a more accurate actual rotation speed from the vibration frequency.

[0108] S106: The controller inputs the target vibration frequency and the target rotation speed into the target neural network model to obtain the predicted actual rotation speed of the target.

[0109] The controller inputs these two key parameters, namely 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 during 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.

[0110] S107: Calibrate the rotation speed displayed on the medical centrifuge based on the target actual rotation speed.

[0111] It can be understood that in order to ensure the accuracy and reliability of the medical centrifuge, it is necessary to accurately calibrate the rotation speed displayed on the centrifuge according to the target actual rotation speed. This process involves comparing the rotation speed displayed on the centrifuge display screen with the actually measured rotation speed to ensure the 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 the experimental results.

[0112] A method for calibrating the rotation speed of a medical centrifuge based on a base force sensor proposed in this application. By obtaining the first vibration frequency of the centrifuge within the first period, the first rotation control signal output by the drive chip within the first period, and the rotation speed directly measured within the first period to establish a neural network training model. After obtaining the trained neural network training model through iterative training of multiple data, the vibration frequency and the rotation speed output by the control chip during the actual use process are imported into the neural network training model. The actual rotation speed is output according to the predicted result, and the speed displayed on the centrifuge is calibrated by using this speed, so that the speed displayed on the centrifuge is closer to the true rotation speed rather than the input rotation speed, improving the measurement accuracy.

[0113] Based on the same inventive concept, an embodiment of the present application also proposes a medical centrifuge rotation speed calibration system. The medical centrifuge includes a controller, and the system is configured to:

[0114] The controller obtains the first vibration frequency of the medical centrifuge within the first period;

[0115] The controller obtains the first rotation control signal output by the drive chip within the first period, and determines the first rotation speed based on the first rotation control signal;

[0116] The controller obtains the first actual rotation speed according to the input measurement result;

[0117] The controller takes the first vibration frequency, the first rotation speed, 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 perform iterative calculations on the first vibration frequency, the first rotation speed, and the first actual rotation speed, and outputs the predicted actual rotation speed according to the input vibration frequency and the target rotation speed;

[0118] The controller obtains the target vibration frequency of the medical centrifuge within the target period and the target rotation control signal output by the drive chip within the target period, and determines the target rotation speed based on the target rotation control signal;

[0119] 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;

[0120] Calibrate the rotation speed displayed on the medical centrifuge based on the target actual rotation speed.

[0121] In some embodiments, the system is configured to:

[0122] The controller obtains the target vibration frequency of the medical centrifuge within the target period and the target rotation control signal output by the drive chip within the target period, and determines the target rotation speed, including:

[0123] The controller determines the second rotation speed based on the first rotation speed, and the speed difference between the first rotation speed and the second rotation speed is the conditional rotation speed;

[0124] The controller obtains the second vibration frequency of the medical centrifuge within the second period;

[0125] The controller inputs the first vibration frequency, the second vibration frequency, and the conditional rotation speed into the first neural network prediction model. The first neural network prediction model is used to output the predicted second vibration frequency according to the input conditional rotation speed and the input first vibration frequency;

[0126] The controller determines the target conditional rotation speed based on the target rotation speed and the first rotation speed;

[0127] 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.

[0128] In some embodiments, the system is configured to:

[0129] The controller obtains the weights of multiple sample parameters in the medical centrifuge within the first period;

[0130] The controller takes the first vibration frequency, the first rotation speed, 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 perform iterative calculations on the first vibration frequency, the first rotation speed, and the first actual rotation speed, and outputs the predicted actual rotation speed according to the input vibration frequency and the target rotation speed. It further includes:

[0131] The controller takes the first vibration frequency, the first rotation speed, the weights of multiple sample parameters, 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 perform iterative calculations on the first vibration frequency, the first rotation speed, the weights of multiple sample parameters, and the first actual rotation speed, and outputs the predicted actual rotation speed according to the input vibration frequency, the sample parameter weights, and the target rotation speed.

[0132] In some embodiments, the system is configured to:

[0133] The controller takes the first vibration frequency, the first rotation speed, the weights of multiple sample parameters, 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 perform iterative calculations on the first vibration frequency, the first rotation speed, the weight of one sample parameter, and the first actual rotation speed, and outputs the predicted actual rotation speed according to the input vibration frequency, the sample parameter weights, and the target rotation speed. It includes:

[0134] The controller performs data processing on the first vibration frequency, the first rotation speed, the weight of one sample parameter, and the first actual rotation speed. Among them, the first vibration frequency, the first rotation speed, and the weight of one sample parameter are used as three different dimensions, and the three dimensions form the feature vector of the actual rotation speed;

[0135] The controller controls the target neural network training model to perform iterative calculations based on the feature vector.

[0136] In some embodiments, the system is configured to:

[0137] The controller takes the first vibration frequency, the first rotation speed, the weights of multiple sample parameters, 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 perform iterative calculations on the first vibration frequency, the first rotation speed, the weight of one sample parameter, 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, including:

[0138] The controller obtains the predicted actual rotation speed and feeds it back to the target neural network training model, and determines the error value according to the feedback result;

[0139] If the error value is greater than the preset threshold, the target neural network training model continues to perform iterative calculations;

[0140] If the error value is less than or equal to the preset threshold, the target neural network training model stops iterative calculations and outputs the predicted actual rotation speed.

[0141] In some embodiments, the system is configured to:

[0142] The controller obtains the predicted actual rotation speed and feeds it back to the target neural network training model, and determines the error value according to the feedback result, including:

[0143] Compare the predicted actual rotation speed 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:

[0144] = ( - )

[0145] Wherein, is the error value, is the first actual rotation speed, is the predicted actual rotation speed.

[0146] Combined with the second aspect, in some embodiments, the system is configured to:

[0147] Compare the predicted actual rotation speed 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:

[0148] = ( - )

[0149] Wherein, is the error value, is the first actual rotation speed, is the predicted actual rotation speed.

[0150] A rotational speed calibration system for a medical centrifuge proposed in this application establishes a neural network training model by obtaining the first vibration frequency of the centrifuge, the first rotation control signal output by the drive chip, and the rotation speed directly measured within the first period. After obtaining the trained neural network training model through iterative training of multiple data, the vibration frequency and the rotation speed output by the control chip during actual use are imported 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 this speed, so that the speed displayed by the centrifuge is closer to the true rotation speed rather than the input rotation speed, improving the measurement accuracy.

[0151] Based on the same inventive concept, an embodiment of this application also proposes an electronic device, which includes:

[0152] 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 rotational speed calibration method of the medical centrifuge in the embodiment of this application.

[0153] In addition, to achieve the above object, an embodiment of this application also proposes a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, it implements the rotational speed calibration method of the medical centrifuge in the embodiment of this application.

[0154] The following specifically introduces each component of the electronic device:

[0155] Wherein, the processor is the control center of the electronic device, which can be a single processor or a collective term for multiple processing elements. For example, the processor is one or more central processing units (CPUs), or can be 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 digital signal processors (DSPs), or, one or more field programmable gate arrays (FPGAs).

[0156] Optionally, the processor can perform various functions of the electronic device by running or executing software programs stored in the memory and calling data stored in the memory.

[0157] The memory is used to store the software program for implementing the solution of the present invention and is controlled by the processor for execution. The specific implementation manner can refer to the above method embodiments and will not be elaborated here.

[0158] Optionally, the memory can 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 compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, 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 can be integrated with the processor or exist independently and is coupled to the processor through the interface circuit of the electronic device. The embodiments of the present invention do not make specific limitations in this regard.

[0159] The transceiver is used to communicate with a network device or with a terminal device.

[0160] Optionally, the transceiver can include a receiver and a transmitter. The receiver is used to implement the receiving function, and the transmitter is used to implement the transmitting function.

[0161] Optionally, the transceiver can be integrated with the processor or exist independently and is coupled to the processor through the interface circuit of the router. The embodiments of the present invention do not make specific limitations in this regard.

[0162] In addition, the technical effects of the electronic device can refer to the technical effects of the data transmission method in the above method embodiments and will not be elaborated here.

[0163] It should be understood that the processor in the embodiments of the present invention may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs) 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.

[0164] 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 ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (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 but not limitation, many forms of random access memory (RAM) are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced SDRAM (ESDRAM), synchlink DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0165] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware, or any combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. A computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions according to the embodiments of the present invention are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (such as infrared, wireless, microwave, etc.) means. 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 collections of available media. The available media can be magnetic media (such as floppy disks, hard disks, magnetic tapes), optical media (such as DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0166] It should be understood that the term "and / or" in this document is merely a description of the association relationship between associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. Here, A and B can be singular or plural. In addition, the character " / " in this document generally represents an "or" relationship between the associated objects before and after, but it may also represent an "and / or" relationship, which can be specifically understood with reference to the context.

[0167] In the present invention, "at least one" means one or more, and "a plurality" means two or more. "At least one of the following" or its similar expressions refer 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 represent: a, b, c, a - b, a - c, b - c, or a - b - c, where a, b, and c can be single or multiple.

[0168] It should be understood that in various embodiments of the present invention, the magnitudes of the serial numbers of the above processes do not mean the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0169] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. A professional technician can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

Claims

1. A method for calibrating the rotational speed of a medical centrifuge 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 the first vibration frequency of the medical centrifuge within the first period; The controller obtains the first rotation control signal output by the drive chip within the first period, and determines the first rotation speed based on the first rotation control signal; The controller obtains the first actual rotation speed according to the input measurement result; The controller takes 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 perform iterative calculations on the first vibration frequency, the first rotation speed, and the first actual rotation speed, and outputs the predicted actual rotation speed corresponding to the first period according to the input vibration frequency and 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 drive 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 corresponding to the target period; Calibrate the rotation speed displayed on the medical centrifuge based on the target actual rotation speed.

2. The method for calibrating the rotational speed of a medical centrifuge based on a base force sensor according to claim 1, wherein The method further includes: The controller obtains the weights of multiple sample parameters in the medical centrifuge within the first period; The controller takes 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 perform iterative calculations on the first vibration frequency, the first rotation speed, and the first actual rotation speed, and outputs the predicted actual rotation speed corresponding to the first period. It further includes: The controller takes the first vibration frequency, the first rotation speed, the weights of multiple sample parameters, 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 perform iterative calculations on the first vibration frequency, the first rotation speed, the weights of multiple sample parameters, and the first actual rotation speed, and outputs the predicted actual rotation speed according to the input vibration frequency, sample parameter weights, and target rotation speed.

3. A method for calibrating the rotational speed of a medical centrifuge based on a base force sensor according to claim 2, characterized in that, The controller takes the first vibration frequency, the first rotation speed, the weights of multiple sample parameters, 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 perform iterative calculations on the first vibration frequency, the first rotation speed, the weights of multiple sample parameters, and the first actual rotation speed, and outputs the predicted actual rotation speed according to the input vibration frequency, sample parameter weights, and target rotation speed, including: The controller processes data on the first vibration frequency, the first rotational speed, the weights of multiple sample parameters, and the first actual rotational speed. Among them, the first vibration frequency, the first rotational speed, and the weights of multiple sample parameters serve as three different dimensions, and the three dimensions form the feature vector of the actual rotational speed; The controller controls the target neural network model to perform iterative calculations based on the feature vector.

4. A method for calibrating the rotational speed of a medical centrifuge based on a base force sensor according to claim 3, characterized in that, The controller uses the first vibration frequency, the first rotational speed, the weights of multiple sample parameters, and the first actual rotational speed as a training set and imports it into the target neural network model. The target neural network model is used to perform iterative calculations on the first vibration frequency, the first rotational speed, the weights of multiple sample parameters, and the first actual rotational speed, and based on the input vibration frequency, sample parameter weights, and target rotational speed, outputs the predicted actual rotational speed, including: The controller obtains the predicted actual rotational speed and feeds it back to the target neural network 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 model continues to perform iterative calculations; If the error value is less than or equal to the preset threshold, the target neural network model stops iterative calculations and outputs the predicted actual rotational speed.

5. A method for calibrating the rotational speed of a medical centrifuge based on a base force sensor according to claim 4, wherein, The controller obtains the predicted actual rotational speed and feeds it back to the target neural network model, and determines the error value based on the feedback result, including: Comparing the predicted actual rotational speed with the first actual rotational speed. If the first actual rotational speed is greater than the predicted actual rotational speed, the error value, and the relationship between the first actual rotational speed and the predicted actual rotational speed satisfy: =（ - ） wherein, is the error value, is the first actual rotation speed, is the predicted actual rotation speed.

6. A method for calibrating the rotational speed of a medical centrifuge based on a base force sensor according to claim 5, characterized in that, Comparing the predicted actual rotational speed with the first actual rotational speed. If the first actual rotational speed is less than the predicted actual rotational speed, the error value, and the relationship between the first actual rotational speed and the predicted actual rotational speed satisfy: =（ - ） wherein, is the error value, is the first actual rotational speed, is the predicted actual rotational speed.

7. A medical centrifuge speed calibration system based on a base force sensor, characterized in that, The medical centrifuge includes a controller, and the system is configured to: The controller obtains the first vibration frequency of the medical centrifuge within the first period; The controller obtains the first rotation control signal output by the drive chip within the first period and determines the first rotational speed based on the first rotation control signal; The controller obtains the first actual rotational speed according to the input measurement result; The controller uses the first vibration frequency, the first rotational speed, and the first actual rotational speed as a training set and imports it into the target neural network model. The target neural network model is used to perform iterative calculations on the first vibration frequency, the first rotational speed, and the first actual rotational speed, and based on the input vibration frequency and target rotational speed, outputs the predicted actual rotational 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 drive 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 a predicted target actual rotation speed; Calibrate the rotation speed displayed on the medical centrifuge based on the target actual rotation speed.

8. An electronic device, characterized in that, Comprising: 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 according to any one of claims 1-6.

9. A computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the method according to any one of claims 1-6 is implemented.

Images