Magnetic stirrer detection method and device and detection model training method and device

Abstract

The invention discloses a magnetic stirrer detection method and device and a detection model training method and device, and relates to the technical field of stirring. The magnetic stirrer detection method comprises the steps that target operation data of a to-be-detected stirring device is acquired, and the to-be-detected stirring device comprises a to-be-detected magnetic stirrer; the target operation data comprises N target motor torques, or comprises N target motor rotating speeds and N target motor torques, and N is a positive integer; extracting the target operation data to obtain target features; a target detection model is adopted to detect the target features, the target operation state of the magnetic stirrer to be detected is obtained, and the target detection model is obtained through training of the historical features and the corresponding historical operation states. According to the embodiment of the invention, the method can improve the detection accuracy of the operation state of the magnetic stirrer.

Description

Technical Field

[0001] The present application belongs to the field of stirring technology, and specifically relates to a magnetic stirring bar detection method and device, and a detection model training method and device. Background Art

[0002] A stirring device is a device that forces convection and uniform mixing of liquid or gaseous media. It is commonly used in experiments in various fields, including biology, chemistry, materials, and substance analysis. Common stirring devices include mechanical connecting rod stirrers and magnetic stirrers. To ensure the smooth and reliable conduct of experimental results, the magnetic stirrer in the magnetic stirrer must be regularly inspected to detect any abnormalities.

[0003] At present, for magnetic stirrers, Hall sensors are mainly used to detect the magnetic field signals of the magnetic stirrer and the permanent magnetic turntable, and by calculating the angular difference between the magnetic field intensity of the turntable and the magnetic field intensity of the magnetic stirrer, the operating status of the magnetic stirrer in the magnetic stirrer, such as loss of step, is detected. However, in the nuclear industry hot chamber environment, the additional Hall sensor is affected by gamma rays and cannot work effectively. In addition, the signal transmission link of the additional Hall sensor in the conventional environment is susceptible to electromagnetic interference. The noise of the collected signal affects the calculation result of the magnetic field angle difference, which is easy to cause false alarms of the operating status of the magnetic stirrer, resulting in errors in the detection result of the operating status of the magnetic stirrer. In summary, the accuracy of the detection of the operating status of the magnetic stirrer in the magnetic stirrer in the prior art is not enough. Summary of the Invention

[0004] The technical problem to be solved by the present application is to provide a magnetic stirrer detection method and device, and a detection model training method and device in response to the above-mentioned deficiencies in the prior art. By using the magnetic stirrer detection method, there is no need to additionally add a Hall sensor, and the problem of insufficient accuracy in detecting the operating status of the magnetic stirrer in the magnetic stirrer due to inaccurate data collected by the additional Hall sensor can be improved or solved. That is, the accuracy of detecting the operating status of the magnetic stirrer in the magnetic stirrer can be improved.

[0005] In a first aspect, an embodiment of the present application provides a magnetic stirring bar detection method, comprising:

[0006] Obtain target operating data of the stirring device to be detected, wherein the stirring device to be detected includes a magnetic stirring bar to be detected; the target operating data includes N target motor torques, or includes N target motor speeds and N target motor torques, where N is a positive integer;

[0007] Extract target operation data to obtain target features;

[0008] The target features are detected using a target detection model to obtain the target operating state of the magnetic stirrer to be detected, wherein the target detection model is trained by historical features and their corresponding historical operating states.

[0009] Based on the same inventive concept, in a second aspect, an embodiment of the present application further provides a detection model training method, which is used to train and obtain the target detection model of any one of the first aspects, and the method includes:

[0010] Acquire historical operating data of a stirring device, wherein the stirring device includes a magnetic stirring bar; the historical operating data includes Q historical motor torques, or includes Q historical motor speeds and Q historical motor torques, where Q is a positive integer;

[0011] Extract historical operation data to obtain historical features;

[0012] The preset model is trained using historical features and their corresponding historical operating states to obtain a target detection model.

[0013] Based on the same inventive concept, in a third aspect, an embodiment of the present application provides a magnetic stirring bar detection device, comprising:

[0014] a first acquisition module, configured to acquire target operating data of the stirring device to be detected, wherein the stirring device to be detected includes a magnetic stirrer to be detected; the target operating data includes N target motor torques, or includes N target motor speeds and N target motor torques, where N is a positive integer;

[0015] A first extraction module, connected to the first acquisition module, is used to extract the target operation data to obtain target features;

[0016] The detection module is connected to the first extraction module and is used to detect the target features using a target detection model to obtain the target operating state of the magnetic stirrer to be detected, wherein the target detection model is trained by historical features and their corresponding historical operating states.

[0017] Based on the same inventive concept, an embodiment of the present application further provides a detection model training device, which is used to train and obtain the target detection model as described in any one of the first aspects, and the device includes:

[0018] a second acquisition module, configured to acquire historical operating data of a stirring device, wherein the stirring device includes a magnetic stirring bar; the historical operating data includes Q historical motor torques, or Q historical motor speeds and Q historical motor torques, where Q is a positive integer;

[0019] A second extraction module, connected to the second acquisition module, is used to extract historical operation data to obtain historical features;

[0020] The training module is connected to the second extraction module and is used to train the preset model using historical features and their corresponding historical operating states to obtain a target detection model.

[0021] According to the magnetic stirrer detection method and device, detection model training method and device provided in the embodiment of the present application, by extracting the N target motor torques of the stirring device to be detected itself, or, extracting the N target motor speeds and N target motor torques of the stirring device to be detected itself, obtaining a target feature, and then using the target detection model to detect the target feature, obtaining the target operating state of the magnetic stirrer to be detected. That is to say, in the embodiment of the present application, by the N target motor torques of the stirring device to be detected itself, or, the N target motor speeds and N target motor torques of the stirring device to be detected itself, determining the target operating state of the magnetic stirrer to be detected, without the need to additionally set up a Hall sensor, can improve or solve the problem of insufficient accuracy of magnetic stirrer operating state detection in a magnetic stirrer due to inaccurate data collected by an additional Hall sensor, that is, can improve the accuracy of magnetic stirrer operating state detection in a magnetic stirrer. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 A schematic flow chart of a magnetic stirring bar detection method provided in an embodiment of the present application is shown;

[0023] Figure 2 A schematic structural diagram of a stirring device provided in an embodiment of the present application is shown;

[0024] Figure 3 A diagram showing an application environment of the magnetic stir bar detection method provided in an embodiment of the present application;

[0025] Figure 4 Another schematic flow chart of the magnetic stirring bar detection method provided in an embodiment of the present application is shown;

[0026] Figure 5 Another schematic flow chart of the magnetic stirring bar detection method provided in the embodiment of the present application is shown;

[0027] Figure 6 Another schematic flow chart of the magnetic stirring bar detection method provided in the embodiment of the present application is shown;

[0028] Figure 7 Another schematic flow chart of the magnetic stirring bar detection method provided in the embodiment of the present application is shown;

[0029] Figure 8 A schematic structural diagram of a magnetic stirring bar detection device provided in an embodiment of the present application is shown;

[0030] Figure 9 A schematic structural diagram of a computer device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0031] In order to enable those skilled in the art to better understand the technical solution of the present application, the present application is further described in detail below with reference to the accompanying drawings and embodiments.

[0032] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only configured to explain the present application and are not configured to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is merely to provide a better understanding of the present application by illustrating the examples of the present application.

[0033] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, the elements defined by the phrase "comprising..." do not exclude the presence of other identical elements in the process, method, article, or device comprising the elements.

[0034] It should be understood that the term "and / or" as used herein is merely a description of the relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the character " / " in this document generally indicates that the associated objects are in an "or" relationship.

[0035] Example 1

[0036] An embodiment of the present application provides a magnetic stirrer detection method, which can be applied to the detection process of magnetic stirrers in nuclear industry hot chamber environments or conventional environments.

[0037] It should be noted that the magnetic stir bar detection method provided in the embodiments of the present application can be performed by a magnetic stir bar detection device and an electronic device, etc. The following description will be made using the example of the magnetic stir bar detection method being performed by an electronic device.

[0038] like Figure 1 As shown, an embodiment of the present application provides a magnetic stirring bar detection method, which includes steps S110 to S130.

[0039] S110. Obtain target operating data of the stirring device to be detected, wherein the stirring device to be detected includes a magnetic stirrer to be detected; the target operating data includes N target motor torques, or includes N target motor speeds and N target motor torques, where N is a positive integer.

[0040] S120: Extract target operation data to obtain target features.

[0041] S130 , detecting target features using a target detection model to obtain a target operating state of the magnetic stirrer to be detected, wherein the target detection model is trained by historical features and their corresponding historical operating states.

[0042] According to the magnetic stir bar detection method provided in the embodiment of the present application, by extracting the N target motor torques of the stirring device to be detected itself, or, extracting the N target motor speeds and N target motor torques of the stirring device to be detected itself, a target feature is obtained, and then the target feature is detected using a target detection model to obtain the target operating state of the magnetic stir bar to be detected. That is to say, in the embodiment of the present application, by the N target motor torques of the stirring device to be detected itself, or, the N target motor speeds and N target motor torques of the stirring device to be detected itself, the target operating state of the magnetic stir bar to be detected is determined, without the need to additionally set up a Hall sensor, the problem of insufficient accuracy of the detection of the operating state of the magnetic stir bar in the magnetic stirrer can be improved or solved due to the inaccurate data collected by the additional Hall sensor, that is, the accuracy of the detection of the operating state of the magnetic stir bar in the magnetic stirrer can be improved.

[0043] The specific implementation methods of the above steps are introduced below.

[0044] In step S110, the stirring device to be detected can be any stirring device that needs to detect the operating state of the magnetic stirring bar. Figure 2 As shown, the stirring device to be tested may include a servo motor 1, a coupling 2, a permanent magnetic turntable 3, a container 4, and a magnetic stirrer 5. The servo motor 1 drives the permanent magnetic turntable 3, and the magnetic stirrer 5 rotates at the bottom of the container 4 under the magnetic force of the permanent magnetic turntable 3, thereby stirring the liquid in the container 4. It should be noted that Figure 2 N stands for north, S stands for south, and the direction indicated by the arrow is the direction of rotation.

[0045] For example, the target motor torque may be the current value of the output torque of the stirring device to be detected; and the target motor speed may be the current value of the output speed of the stirring device to be detected.

[0046] As an example, the target operating data includes N target motor torques.

[0047] As another example, the target operating data includes N target motor speeds and N target motor torques.

[0048] For example, upon detecting that the stirring device to be detected has been activated, the target operating data of the stirring device to be detected can be collected via a motor driver in the stirring device to be detected. Thus, because the control signal of the motor driver has anti-interference performance, collecting the target operating data of the stirring device to be detected via the motor driver can improve the quality of the target operating data, thereby improving the accuracy of detecting the operating status of the magnetic stirrer in the magnetic stirrer. Specifically, the motor driver can continuously collect the target operating data of the stirring device to be detected in real time, so as to promptly determine the operating status of the magnetic stirrer in the magnetic stirrer.

[0049] For example, the collection frequency used when collecting target operation data may be greater than or equal to 200 Hz. When it is detected that the stirring device to be detected stops running, the collection of target operation data is stopped synchronously, thereby improving or solving the problem of collecting invalid target operation data.

[0050] In some embodiments, obtaining target operating data of the stirring device to be detected specifically includes:

[0051] Obtaining a target sampling frequency and first initial operating data of the stirring device to be tested, the first initial operating data including P first initial motor torques, or P first initial motor speeds and P first initial motor torques; wherein the first initial motor speeds and the first initial motor torques correspond one to one, P is a positive integer, and P is greater than or equal to N;

[0052] Grouping the first initial operating data according to the target sampling frequency to obtain P / N groups of first intermediate operating data, where the first intermediate operating data includes N first initial motor torques, or includes N first initial motor speeds and N first initial motor torques;

[0053] Any one of the P / N groups of first intermediate operating data is determined as target operating data of the stirring device to be detected.

[0054] For example, the target sampling frequency may be a collection frequency used when collecting target operating data.

[0055] Exemplarily, the value of N is equal to the target sampling frequency. For example, if the target sampling frequency is 250 Hz, the value of N is 250.

[0056] Exemplarily, the N target motor speeds are the N first initial motor speeds in any set of first intermediate operating data; and the N target motor torques are the N first initial motor torques in any set of first intermediate operating data.

[0057] For example, the value of P is 750, the value of N is 250, and the first initial operating data includes 750 first initial motor speeds and 750 first initial motor torques. The first to 250th first initial motor speeds collected are determined as the 250 first initial motor speeds included in the first group of intermediate operating data; the 251st to 500th first initial motor speeds collected are determined as the 250 first initial motor speeds included in the second group of intermediate operating data; and the 501st to 750th first initial motor speeds collected are determined as the 250 first initial motor speeds included in the third group of intermediate operating data. The grouping of the first initial motor torques is similar and will not be repeated here.

[0058] It should be noted that the values ​​of N and P can be set according to actual conditions and are not limited here.

[0059] In step S120 , after acquiring the target operation data of the stirring device to be detected, the electronic device may further extract the target operation data to obtain target features.

[0060] As an example, the target feature includes a target torque time domain feature.

[0061] As another example, the target feature includes a target order spectrum energy feature.

[0062] As yet another example, the target features include target torque time domain features and target order spectrum energy features.

[0063] In some embodiments, when the target operating data includes N target motor torques,

[0064] The target feature includes a target torque time domain feature, wherein the target torque time domain feature includes at least one of a target mean, a target effective value, a target peak factor, a target standard deviation, a target signal peak, a target kurtosis, and a target disturbance factor.

[0065] In this embodiment, the target torque time domain characteristics include at least one of a target mean, a target effective value, a target peak factor, a target standard deviation, a target signal peak, a target kurtosis, and a target disturbance factor, which can improve the integrity and accuracy of the target torque time domain characteristics.

[0066] For example, the target mean may be the average value of N target motor torques; the target effective value may be the effective value of N target motor torques; the target peak factor may be the peak factor of N target motor matrices; the target standard deviation may be the standard deviation of N target motor matrices; the target signal peak may be the signal peak of N target motor matrices; the target kurtosis may be the kurtosis of N target motor torques; and the target disturbance factor may be the disturbance factor of N target motor torques.

[0067] It should be noted that the target effective value can reflect the changing trend of the target motor torque during the target operation data acquisition process; the target peak factor can reflect the stability of the target motor torque; the target signal peak can indicate the strength of the target motor torque; the target kurtosis can reflect the impact characteristics of the target motor torque; and the target disturbance factor can reflect the fluctuation characteristics of the target motor torque.

[0068] As an example, the target torque time-domain characteristic includes a target mean value.

[0069] As another example, the target torque time-domain characteristics include a target kurtosis and a target disturbance factor.

[0070] As yet another example, the target torque time-domain characteristics include a target mean value, a target effective value, a target peak factor, a target standard deviation, a target signal peak value, a target kurtosis, and a target disturbance factor.

[0071] For example, the target mean value may be determined according to formula (1).

[0072]

[0073] in, is the target mean, x n is the nth target motor torque, and 1≤n≤N, where n is a positive integer.

[0074] Exemplarily, the target effective value may be determined according to formula (2).

[0075] Formula (2) includes:

[0076]

[0077] Among them, x rms is the target effective value.

[0078] Exemplarily, the target signal peak value may be determined according to formula (3).

[0079] Formula (3) includes:

[0080] x peak =max(x n ) (3)

[0081] Among them, x peak is the target signal peak value, and max is the maximum value.

[0082] Exemplarily, the target peak factor may be determined according to formula (4).

[0083] Formula (4) includes:

[0084]

[0085] Where CF represents the target crest factor.

[0086] For example, the target standard deviation may be determined according to formula (5).

[0087] Formula (5) includes:

[0088]

[0089] Among them, σ x is the target standard deviation.

[0090] Exemplarily, the target disturbance factor may be determined according to formula (6).

[0091] Formula (6) includes:

[0092]

[0093] Where T is the target disturbance factor.

[0094] For example, the target kurtosis may be determined according to formula (7).

[0095] Formula (7) includes:

[0096]

[0097] Where K is the target kurtosis.

[0098] In other embodiments, when the target operating data includes N target motor speeds and N target motor torques, the target motor speeds and the target motor torques correspond one to one, and the target feature includes a target order spectrum energy feature;

[0099] Extract the target operation data to obtain target features, including:

[0100] Determine N first motor rotation angles according to N target motor speeds and their corresponding N target acquisition timestamps, where the target motor speeds correspond one-to-one to the target acquisition timestamps and the first motor rotation angles respectively;

[0101] Determining a target torque order spectrum according to the N first motor rotation angles;

[0102] According to the target torque order spectrum, the target order spectrum energy characteristics are determined.

[0103] In this embodiment, N first motor angles are first determined based on N target motor speeds and their corresponding N target acquisition timestamps, and then the target torque order spectrum is determined based on the N first motor angles. Finally, the target order spectrum energy characteristics are determined based on the target torque order spectrum, which can improve the reliability of the target order spectrum energy characteristics.

[0104] Exemplarily, the target motor speed and its corresponding target motor torque have the same target acquisition timestamp.

[0105] For example, the target order spectrum energy characteristic may be the amplitude of the target order spectrum corresponding to the stirring device to be tested, or may be the largest L order signals in the target torque order spectrum, where L is an integer greater than or equal to 1, and the specific value may be set according to actual needs. For example, the value of L may be 8.

[0106] In some examples, determining a target torque order spectrum based on the N first motor rotation angles specifically includes:

[0107] Determine M identical first motor rotation angles among the N first motor rotation angles as M target motor rotation angles, where M is less than or equal to N and is a positive integer;

[0108] Determine a target torque order signal according to the M target motor torques corresponding to the M target motor rotation angles;

[0109] Perform Fourier transform on the target torque order signal to obtain the target torque order spectrum.

[0110] In this embodiment, by determining M identical first motor angles among N first motor angles as M target motor angles, and then determining the target torque order signal based on the M target motor torques corresponding one-to-one to the M target motor angles, and then performing Fourier transform on the target torque order signal to obtain the target torque order spectrum, the reliability of the target torque order spectrum can be improved, and thus the reliability of the target order spectrum energy characteristics can be improved.

[0111] It should be noted that the target motor torque corresponds to the target motor speed, the target motor speed corresponds to the first motor angle, and the first motor angle corresponds to the target motor angle. Therefore, the target motor angle corresponds to the target motor torque.

[0112] For example, the target torque order spectrum may be determined according to a target torque order signal corresponding to the target motor torque, and the target torque order signal may be used to describe the vibration frequency of the mechanical equipment.

[0113] It should be noted that order spectrum is an analytical method for rotating machinery. It decomposes mechanical vibration signals into components of different orders and calculates the magnitude of vibration energy at each order. The order spectrum accurately reflects the vibration condition of the machinery and provides an effective means for fault diagnosis. The amplitude of the order spectrum refers to the maximum value of the calculated vibration energy.

[0114] In some examples, determining a target torque order signal based on M target motor torques corresponding to M target motor angles may include:

[0115] The M target motor torques corresponding to the M target motor angles are sorted according to the target acquisition timestamps to obtain a target sequence;

[0116] The target sequence is interpolated to obtain the target torque order signal.

[0117] In this embodiment, by sorting the M target motor torques corresponding to the M target motor angles one by one according to the target acquisition timestamp to obtain a target sequence, and then interpolating the target sequence to obtain a target torque order signal, the reliability of the target torque order signal can be improved, and thus the reliability of the target torque order spectrum can be improved.

[0118] Exemplarily, the target acquisition timestamps may be sorted from large to small, or the target acquisition timestamps may be sorted from small to large, which is not limited here.

[0119] Exemplarily, the target sequence is interpolated based on a linear interpolation method to obtain the target torque order signal. In other words, the target sequence is resampled to obtain the target torque order signal.

[0120] It should be noted that the value of M can be set according to actual conditions and is not limited here.

[0121] In step S130, after extracting the target operation data and obtaining the target features, the electronic device may further use a target detection model to detect the target features to obtain the target operation state of the magnetic stirrer to be detected.

[0122] For example, the target operating state may include a normal state, a step-out state, a jumping state, a worn state, and a weak magnetic state. Among them, the step-out state may be a state in which the magnetic stirrer to be detected cannot rotate synchronously with the magnetic field, which is manifested as a state in which the rotation speed is not synchronized with the magnetic field; the jumping state may be a state in which the magnetic stirrer to be detected is separated from the center position of the bottom of the container, and irregularly jumps or hits the container wall; the worn state may be a state in which the surface of the magnetic stirrer to be detected is physically damaged or magnetically attenuated due to long-term friction or chemical corrosion; the weak magnetic state may be a state in which the magnetic stirrer to be detected cannot rotate effectively due to insufficient magnetic field driving force due to demagnetization.

[0123] As an example, the target detection model is used to detect the time domain characteristics of the target torque to obtain the target operating state of the magnetic stirrer to be detected.

[0124] As another example, the target detection model is used to detect the target order spectrum energy characteristics to obtain the target operating state of the magnetic stirrer to be detected.

[0125] As another example, the target detection model is used to detect the target torque time domain characteristics and the target order spectrum energy characteristics to obtain the target operating state of the magnetic stirrer to be detected.

[0126] Exemplarily, the target detection model can determine the target operating state of the magnetic stirrer to be detected based on the target torque time domain characteristics and its corresponding data range, and / or the target order spectrum energy characteristics and its corresponding data range.

[0127] Example 2

[0128] The present embodiment provides a detection model training method for training the target detection model of embodiment 1. The target detection model trained by the detection model training method can be applied to the detection process of magnetic stirrers in nuclear industry hot chamber environments or conventional environments.

[0129] The detection model training method provided in the embodiment of the present application can be executed by a detection model training device and an electronic device, etc. The following description will be made by taking the detection model training method executed by an electronic device as an example.

[0130] The detection model training method provided in the embodiment of the present application may include steps S210 to S230.

[0131] S210. Acquire historical operating data of the stirring device, wherein the stirring device includes a magnetic stirring bar; the historical operating data includes Q historical motor torques, or Q historical motor speeds and Q historical motor torques, where Q is a positive integer.

[0132] S220: Extract historical operation data to obtain historical features.

[0133] S230: Use historical features and their corresponding historical operating states to train a preset model to obtain a target detection model.

[0134] According to the detection model training method provided in the embodiment of the present application, the historical features are determined by the Q historical motor torques of the stirring device itself, or the Q historical motor speeds and Q historical motor torques of the stirring device itself, and the preset model is trained using the historical features and their corresponding historical operating states to obtain a target detection model. Without the need for additional Hall sensors, the problem of insufficient accuracy in detecting the operating state of the magnetic stirrer in the magnetic stirrer due to inaccurate data collected by the additional Hall sensors can be improved or solved, that is, the accuracy of detecting the operating state of the magnetic stirrer in the magnetic stirrer can be improved. In addition, the target detection model can be given the ability to predict the torque characteristic data of the magnetic stirrer, thereby improving the efficiency of determining the operating state of the magnetic stirrer.

[0135] The specific implementation methods of the above steps are introduced below.

[0136] In step S210 , the historical motor torque may be a historical value of the output torque of the stirring device; and the historical motor speed may be a historical value of the output speed of the stirring device.

[0137] As an example, the historical operating data includes Q historical motor torques.

[0138] As another example, the historical operating data includes Q historical motor torques and Q historical motor speeds.

[0139] The specific implementation of step S210 is similar to that of step S110 and will not be repeated here.

[0140] It is understandable that there are multiple historical operation data.

[0141] It should be noted that the value of Q may be equal to or different from the value of N, and this is not limited here.

[0142] In step S220 , as an example, the historical features include historical torque time domain features.

[0143] As another example, the historical features include historical order spectrum energy features.

[0144] As yet another example, the historical features include historical torque time-domain features and historical order spectrum energy features.

[0145] In some embodiments, when the historical operating data includes Q historical motor torques,

[0146] The historical features include historical torque time domain features, wherein the historical torque time domain features include at least one of a historical mean, a historical effective value, a historical peak factor, a historical standard deviation, a historical signal peak, a historical kurtosis, and a historical disturbance factor.

[0147] In other embodiments, when the historical operating data includes Q historical motor speeds and Q historical motor torques, the historical motor speeds and the historical motor torques correspond one to one, and the historical features include historical order spectrum energy features;

[0148] Extract historical operation data to obtain historical features, including:

[0149] Determine Q second motor rotation angles based on Q historical motor speeds and their corresponding Q historical acquisition timestamps, where the historical motor speeds correspond one-to-one to the historical acquisition timestamps and the second motor rotation angles respectively;

[0150] Determine the historical torque order spectrum based on Q historical motor rotation angles;

[0151] According to the historical torque order spectrum, the energy characteristics of the historical order spectrum are determined.

[0152] In some examples, determining a historical torque order spectrum based on Q historical motor rotation angles includes:

[0153] Determine I identical second motor rotation angle among the Q second motor rotation angles as I historical motor rotation angle, where I is less than or equal to Q, and I is a positive integer;

[0154] Determine a historical torque order signal according to I historical motor torques corresponding one to one to I historical motor rotation angles;

[0155] Perform Fourier transform on the historical torque order signal to obtain the historical torque order spectrum.

[0156] In some examples, determining a historical torque order signal based on a one-to-one correspondence between one historical motor rotation angle and one historical motor torque specifically includes:

[0157] The historical motor torques corresponding to the historical motor angles are sorted according to the historical acquisition timestamps to obtain a historical sequence;

[0158] Interpolate the historical sequence to obtain the historical torque order signal.

[0159] In some examples, obtaining historical operating data of the stirring device includes:

[0160] Obtaining a historical sampling frequency and second initial operating data of the stirring device, where the second initial operating data includes J second initial motor torques, or J second initial motor speeds and J second initial motor torques; wherein the second initial motor speeds correspond to the second initial motor torques one-to-one, J is a positive integer, and J is greater than or equal to Q;

[0161] Grouping the second initial operating data according to the historical sampling frequency to obtain J / Q groups of second intermediate operating data, where the second intermediate operating data includes Q initial motor torques, or Q initial motor speeds and Q initial motor torques;

[0162] Any one of the J / Q groups of second intermediate operating data is determined as the historical operating data of the stirring device.

[0163] The specific implementation method of step S210 is similar to step S210 and will not be repeated here.

[0164] In step S230 , the historical operating status may include a historical normal state, a historical out-of-step state, a historical jump state, a historical wear state, and a historical magnetic weakening state.

[0165] Exemplarily, the preset model may be at least one of the algorithm models such as decision tree, logistic regression, Bayesian, support vector machine or random forest.

[0166] As an example, historical features are used as training samples, and historical operating states corresponding to the historical features are used as labels corresponding to the training samples. The preset model is trained to obtain a target detection model.

[0167] As another example, a portion of historical features is used as training samples, and the historical operating states corresponding to these historical features are used as labels for the training samples to train a preset model, thereby obtaining an intermediate model. Another portion of historical features is used as test samples, and the historical operating states corresponding to these historical features are used as labels for the test samples to test the intermediate model. The model loss function value of the intermediate model is determined, and if the model loss function value is less than or equal to a preset value, the intermediate model is determined as the target model. The preset value can be set based on actual conditions and is not limited here.

[0168] Specifically, 80% of the historical features and their corresponding historical operating states can be used as model training data, and the other 20% of the historical features and their corresponding historical operating states can be used as model testing data. The preset model is trained using the model training data, and the trained preset model is used as the intermediate model. The historical features in the model test data are input into the intermediate model, and the output data of the intermediate model is used as the predicted label data. The model loss function value of the intermediate model is determined based on the predicted label data and the historical operating states in the model test data. If the model loss function value is less than or equal to the preset value, the intermediate model is determined to be a target detection model. If the model loss function value is greater than the preset loss function value, the intermediate model continues to be trained until the model loss function value is less than or equal to the preset value, or the preset number of training times is reached. The preset number of training times can be set according to actual conditions and is not limited here.

[0169] The above scheme trains the preset model according to the model training data, determines the intermediate model, tests the intermediate model through the model testing data, determines the model loss function value of the intermediate model, and repeatedly trains the intermediate model according to the model loss function value, which can improve the prediction accuracy of the magnetic stirrer detection model.

[0170] Example 3

[0171] The magnetic stirring bar detection method provided in the embodiment of the present application can be applied to Figure 3 The application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. The server 104 obtains the target operation data of the stirring device to be detected, extracts the target operation data, obtains the target features, uses the target detection model to detect the target features, obtains the target operation state of the magnetic stirrer to be detected, and sends the target operation state of the magnetic stirrer to be detected to the terminal 102 through the communication network. Among them, the terminal 102 can be but is not limited to various personal computers, laptops, smart phones, tablets, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart car-mounted devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The server 104 can be implemented with an independent server or a server cluster consisting of multiple servers.

[0172] In one embodiment, Figure 4 As shown, a magnetic stir bar detection method is provided. This embodiment uses the method applied to a terminal as an example for illustration. It is understandable that the method can also be applied to a server, and can also be applied to a system including a terminal and a server, and implemented through the interaction between the terminal and the server. The magnetic stir bar detection method provided in the embodiment of the present application may include steps S410 to S440.

[0173] S410 , collecting sample operation data (ie, historical operation data) of the sample stirring device (ie, stirring device) through a motor driver.

[0174] The sample operation data includes sample motor torque (ie, historical motor torque) and sample motor speed (ie, historical motor speed).

[0175] The sample motor torque is the output torque of the sample stirring device. Figure 2As shown, the stirring device mainly consists of a servo motor 1, a coupling 2, a permanent magnetic turntable 3, a container 4 and a magnetic stirring bar 5. The servo motor 1 drives the permanent magnetic turntable 3, and the magnetic stirring bar 5 rotates at the bottom of the container 4 under the magnetic drive of the permanent magnetic turntable, thereby stirring the liquid in the container 4.

[0176] Specifically, when the sample stirring device is detected to be activated, the motor driver continuously collects the sample motor torque and sample motor speed of the sample stirring device in real time, and the collected sample motor torque and sample motor speed are used as sample operation data of the sample stirring device. Optionally, the sampling frequency (i.e., the historical sampling frequency) used when collecting the sample operation data is greater than or equal to 200Hz. When the sample stirring device is detected to be stopped, the collection of sample operation data is synchronously stopped to avoid collecting invalid sample operation data.

[0177] S420 , extracting features from the sample operation data to determine the sample torque time domain features (ie, historical torque time domain features) and the sample order spectrum energy features (historical order spectrum energy features) of the sample stirring device.

[0178] Among them, the time domain characteristics of the sample torque include the sample mean (i.e., historical mean), sample effective value (i.e., historical effective value), sample peak factor (i.e., historical peak factor), sample standard deviation (i.e., historical standard deviation), sample signal peak (i.e., historical signal peak), sample kurtosis (i.e., historical kurtosis) and sample disturbance factor (historical disturbance factor) corresponding to the sample motor torque. The sample effective value can reflect the changing trend of the sample motor torque during the sample operation data acquisition process, the sample peak factor can reflect the stability of the sample motor torque, the sample signal peak can represent the intensity of the sample motor torque, the sample kurtosis can reflect the impact characteristics of the sample motor torque, and the sample disturbance factor can reflect the fluctuation characteristics of the sample motor torque. The sample order spectrum energy feature can be the amplitude of the sample order spectrum corresponding to the sample stirring device, or it can be the largest L order signals in the sample order spectrum, where L is an integer greater than or equal to 1, and can be specifically set according to actual needs. The sample order spectrum is determined based on the order signal (i.e., historical torque order signal) corresponding to the sample motor torque, and the order signal can be used to describe the vibration frequency of the mechanical equipment. It should be noted that order spectrum is an analytical method for rotating machinery. It decomposes mechanical vibration signals into components of different orders and calculates the magnitude of vibration energy at each order. The order spectrum accurately reflects the vibration condition of the machinery and provides an effective means for fault diagnosis. The amplitude of the order spectrum refers to the maximum value of the calculated vibration energy.

[0179] Specifically, feature extraction is performed on the sample motor torque, the time domain characteristics of the sample torque of the sample stirring device are determined, the order analysis of the sample motor torque is performed based on the sample motor speed, the order signal of the sample motor torque (i.e., the historical torque order signal) is determined, the sample order spectrum of the sample motor torque (i.e., the historical torque order spectrum) is determined based on the order signal of the sample motor torque, and the sample order spectrum energy characteristics are determined based on the sample order spectrum.

[0180] S430. Train the machine learning model (i.e., preset model) through the sample torque time domain characteristics, the sample order spectrum energy characteristics, and the sample state label (i.e., historical operating state) of the sample magnetic stirrer in the sample stirring device to determine the magnetic stirrer detection model (i.e., target model).

[0181] The sample state label of the sample magnetic stirrer may include abnormal phenomena such as desynchronization (i.e., historical desynchronization state), jumping (i.e., historical jumping state), wear (i.e., historical wear state), and / or weak magnetism (i.e., historical weak magnetism state). The machine learning model may be an algorithm model such as a decision tree, logistic regression, Bayesian, support vector machine, or random forest.

[0182] Specifically, the sample state label of the magnetic stirrer corresponding to the sample torque time domain characteristics and the sample order spectrum energy characteristics is obtained, and the sample state label is used as the label data for model training of the machine learning model. The machine learning model is trained through the sample torque time domain characteristics, the sample order spectrum energy characteristics and the sample state label to determine the magnetic stirrer detection model.

[0183] S440, obtaining target operating data of the stirring device to be detected, and determining the operating state (i.e., target operating state) of the magnetic stirring bar to be detected in the stirring device to be detected based on the magnetic stirring bar detection model (i.e., target detection model) and the target operating data.

[0184] The target operation data includes the target motor torque and target motor speed of the stirring device to be detected within a certain period of time. The target motor torque refers to the output torque of the stirring device to be detected.

[0185] Specifically, the target motor torque and target motor speed of the stirring device to be detected within a certain period of time are obtained, and the target torque time domain characteristics and target order spectrum energy characteristics of the stirring device to be detected are determined according to the target motor torque and the target motor speed. The target torque time domain characteristics include the target mean, target effective value, target peak factor, target standard deviation, target signal peak, target kurtosis and target disturbance factor corresponding to the target motor torque. The target order spectrum energy characteristics can be the amplitude of the target order spectrum corresponding to the target stirring device, or it can be the largest M order signals in the target order spectrum. The target torque time domain characteristics and target order spectrum energy characteristics are used as input data of the magnetic stirring bar detection model, and the sample state label of the magnetic stirring bar to be detected in the stirring device to be detected is determined according to the output data of the magnetic stirring bar detection model, and the operating state of the stirring bar to be detected is determined to be abnormal according to the sample state label of the magnetic stirring bar to be detected.

[0186] In the above-mentioned magnetic stirrer detection method, sample operation data of the sample stirring device is collected through a motor driver; feature extraction is performed on the sample operation data to determine the sample torque time domain characteristics and sample order spectrum energy characteristics of the sample stirring device; a machine learning model is trained through the sample torque time domain characteristics, sample order spectrum energy characteristics and sample state labels of the sample magnetic stirrer in the sample stirring device to determine a magnetic stirrer detection model; target operation data of the stirring device to be detected is obtained, and the operation state of the magnetic stirrer to be detected in the stirring device to be detected is determined based on the magnetic stirrer detection model and the target operation data. The above-mentioned solution solves the problem that when the stirring device is operating in some special environments, due to electromagnetic interference, the traditional magnetic stirrer detection method has inaccurate detection results of the magnetic stirrer's operation state, which is prone to false alarms of the magnetic stirrer state. The sample motor torque and sample motor speed of the sample stirring device over a period of time are used to determine the sample torque time domain characteristics and sample order spectrum energy characteristics. The machine learning model is trained using the sample torque time domain characteristics, sample order spectrum energy characteristics and sample state labels of the sample magnetic stirrer to determine the magnetic stirrer detection model. The magnetic stirrer detection model is used to predict the operating state of the magnetic stirrer to be detected. The operating state of the magnetic stirrer is detected using the motor torque and motor speed of the stirring device itself, which can avoid the need for additional sensors for the stirring device in the nuclear industry hot chamber environment. At the same time, the control signal of the motor equipment has anti-interference performance, which can ensure the quality of the collected data and avoid false alarms of the magnetic stirrer state caused by errors in the detection data. The operating state of the stirrer is correlated by extracting the torque time domain statistical characteristics and the torque order spectrum energy characteristics. The magnetic stirrer state detection is realized by combining the intelligent decision-making model, which can improve the efficiency of the magnetic stirrer operation state detection.

[0187] In one embodiment, Figure 5As shown, feature extraction is performed on the sample operation data to determine the sample torque time domain feature and sample order spectrum energy feature of the sample stirring device, including:

[0188] S510: Determine the data collection timestamp (ie, historical collection timestamp) and sampling frequency (ie, historical sampling frequency) corresponding to the sample operation data, determine the target data length according to the sampling frequency, and determine the statistical calculation unit according to the target data length.

[0189] It should be noted that, considering that the data collection process of the sample operation data is a continuous collection process, the length of data collected per second can be determined according to the sampling frequency, and the length of data collected per second can be used as the target data length. The statistical calculation unit can be determined according to the target data length.

[0190] For example, if the sampling frequency corresponding to the sample operation data is 250 Hz, the target data length is 250, that is, 250 sample operation data are collected per second, and 250 can be used as a statistical calculation unit.

[0191] S520 : Extract features of the sample motor torque based on the statistical calculation unit to determine the time domain features of the sample torque of the sample stirring device.

[0192] Specifically, the sample operation data can be grouped according to the statistical calculation unit, and the sample operation data in a statistical calculation unit is regarded as a group of data. The sample motor torque in the grouped sample operation data is feature extracted to determine the sample torque time domain characteristics of the sample stirring device.

[0193] S530 : Determine a sample order spectrum energy characteristic of the sample stirring device based on the statistical calculation unit, the data acquisition timestamp, and the sample operation data.

[0194] Specifically, the sample operation data is grouped based on the statistical calculation unit to determine the sample group data, and the sample motor torque in the sample group data is resampled based on the data acquisition timestamp and sample motor speed corresponding to the sample group data to determine the torque order signal, and the torque order spectrum is determined according to the torque order signal, and the sample order spectrum energy characteristics of the sample stirring device are determined according to the torque order spectrum.

[0195] In this embodiment, the target data length of the sample operation data is determined according to the sampling frequency of the sample operation data, the statistical calculation unit is determined according to the target data length, the collected sample operation data is grouped according to the statistical calculation unit, and the sample torque time domain characteristics and sample order spectrum energy characteristics are determined according to the grouped sample operation data, which can improve the reliability of the sample torque time domain characteristics and sample order spectrum energy characteristics.

[0196] In one embodiment, Figure 6As shown, the feature extraction of the sample motor torque is performed based on the statistical calculation unit to determine the time domain feature of the sample torque of the sample stirring device, including:

[0197] S610 : Grouping the sample motor torques based on the statistical calculation unit to determine torque grouping data, and determining the sample effective value and the sample signal peak value according to the torque grouping data.

[0198] For example, if the sampling frequency corresponding to the sample operation data is 250Hz, the statistical calculation unit is 250, and each group of torque grouping data contains 250 sample motor torques. The grouping can be started from the first sample motor torque collected, that is, the first sample motor torque collected to the 250th sample motor torque collected is regarded as a group of torque grouping data, and the 251st sample motor torque collected to the 500th sample motor torque is regarded as a group of torque grouping data, and so on to determine each torque grouping data.

[0199] S620: Determine, based on each set of torque grouped data, a sample effective value and a sample signal peak value corresponding to each set of torque grouped data;

[0200] The calculation method of the sample effective value is shown in formula (8):

[0201]

[0202] Where x′ rms is the effective value of the sample, Q is the number of sample motor torques in the torque grouping data, x′ n is the nth sample motor torque in the torque grouped data, and 1≤n≤Q, where n and Q are both integers.

[0203] Sample signal peak x′ peak The calculation formula is shown in formula (9):

[0204] x′ peak =max(x′ n ) (9)

[0205] S630 : Determine the sample peak factor corresponding to each set of torque grouped data according to each set of torque grouped data and the corresponding sample effective value.

[0206] For example, the calculation formula of the sample peak factor is shown in formula (10):

[0207]

[0208] Where CF′ is the sample peak factor.

[0209] S640 : Based on each set of torque grouping data, determine a sample torque mean corresponding to each set of torque grouping data.

[0210] For example, the calculation formula of the sample torque mean is shown in formula (11):

[0211]

[0212] in, is the sample torque mean.

[0213] S650 : Determine the sample standard deviation corresponding to each set of torque grouping data based on the sample torque mean and the torque grouping data corresponding to each set of torque grouping data.

[0214] The calculation formula for the sample standard deviation is shown in formula (12):

[0215]

[0216] Among them, σ′ x is the sample standard deviation.

[0217] S660 : Determine a sample disturbance factor corresponding to each set of torque grouped data according to the sample standard deviation and the sample torque mean corresponding to each set of torque grouped data.

[0218] For example, the calculation formula of the sample disturbance factor is shown in formula (13):

[0219]

[0220] Where T′ is the sample perturbation factor.

[0221] S670 : Determine the sample kurtosis corresponding to each set of torque grouped data according to each set of torque grouped data, the sample standard deviation, and the sample torque mean.

[0222] For example, the calculation formula of sample kurtosis is shown in formula (14):

[0223]

[0224] Where K′ is the sample kurtosis.

[0225] S680. Use the sample torque mean, sample effective value, sample peak factor, sample standard deviation, sample signal peak, sample kurtosis and sample disturbance factor corresponding to each set of torque grouping data as the sample torque time domain characteristics of the sample stirring device.

[0226] The above scheme provides a calculation method for the sample mean, sample effective value, sample peak factor, sample standard deviation, sample signal peak, sample kurtosis and sample disturbance factor. Using the sample mean, sample effective value, sample peak factor, sample standard deviation, sample signal peak, sample kurtosis and sample disturbance factor as the time domain characteristics of the sample torque can improve the integrity and accuracy of the time domain characteristics of the sample torque.

[0227] In one embodiment, determining a sample order spectrum energy characteristic of the sample stirring device based on the statistical calculation unit, the data acquisition timestamp, and the sample operation data includes:

[0228] The sample operation data are grouped based on the statistical calculation unit to determine the sample group data; the torque order signal corresponding to the sample group data (i.e., the historical torque order signal) is determined based on the sample group data and the data acquisition timestamp corresponding to the sample group data; the torque order signal is Fourier transformed to determine the torque order spectrum (i.e., the historical torque order spectrum), and the sample order spectrum energy characteristics of the sample stirring device are determined based on the torque order spectrum.

[0229] Specifically, the sample operation data is grouped according to the statistical calculation unit to determine the grouped sample operation data, and the sample operation data in one statistical calculation unit is regarded as a group of data. The data acquisition timestamps are sorted to determine the timestamp sequence information, and the sample motor speeds in the sample operation data are extracted according to the timestamp sequence information to extract the sample motor speeds at equal time intervals as the target speed information, and the motor angle corresponding to the target speed information is determined according to the target speed information and the data acquisition timestamp corresponding to the target speed information, and the sample motor torque corresponding to the motor angle is determined as the target torque signal, and the torque order signal is determined according to the interpolation of the target torque signal corresponding to the same motor angle, and the torque order signal is Fourier transformed to determine the torque order spectrum, and the sample order spectrum energy characteristics of the sample stirring device are determined according to the torque order spectrum. For example, the first eight orders of energy in the torque order spectrum can be used as the sample order spectrum energy characteristics of the sample stirring device. It should be noted that the sample order spectrum energy characteristics of each group of sample operation data need to be determined.

[0230] The above scheme groups the sample operation data according to the statistical calculation unit, determines the sample group data, determines the torque order signal corresponding to each sample group data, and determines the sample order spectrum energy characteristics corresponding to each sample group data according to the torque order signal, thereby improving the reliability of the sample order spectrum energy characteristics.

[0231] In one embodiment, a machine learning model is trained using sample torque time domain features, sample order spectrum energy features, and sample state labels of sample magnetic stirrers in a sample stirring device to determine a magnetic stirrer detection model, including:

[0232] The sample torque time domain characteristics and sample order spectrum energy characteristics are used as sample training data, and the sample state label of the sample magnetic stirrer in the sample stirring device is used as sample supervision data; the machine learning model is trained based on the sample training data and sample supervision data to determine the magnetic stirrer detection model.

[0233] The above scheme provides a method for training a machine learning model to determine a magnetic stirrer detection model, which enables the magnetic stirrer detection model to have the ability to predict the torque characteristic data of the magnetic stirrer, thereby improving the efficiency of determining the operating status of the magnetic stirrer.

[0234] In one embodiment, a machine learning model is trained based on sample training data and sample supervision data to determine a magnetic stir bar detection model, including:

[0235] Determine model training data and model testing data based on sample training data and sample supervision data; use model training data to train the machine learning model to determine a candidate detection model; perform model testing on the candidate detection model using model testing data to determine the model loss function of the candidate detection model. If the model loss function meets the preset loss function condition, the candidate detection model is determined to be a magnetic stirrer detection model.

[0236] Specifically, the target training data is determined based on the sample training data and the sample supervision data, and the target training data is divided into model training data and model test data. For example, 80% of the target training data can be used as model training data, and 20% of the target training data can be used as model test data. The machine learning model is trained using the model training data, and the trained machine learning model is used as a candidate detection model. The sample training data in the model test data is input into the candidate detection model, and the output data of the candidate detection model is used as the predicted label data. The model loss function of the candidate detection model is determined based on the predicted label data and the sample supervision data in the model test data. If the model loss function meets the preset loss function conditions, the candidate detection model is determined to be a magnetic stirrer detection model. If the model loss function does not meet the preset loss function conditions, the model training of the candidate detection model continues.

[0237] The above scheme trains the machine learning model according to the model training data, determines the candidate detection model, performs model testing on the candidate detection model through the model testing data, determines the model loss function of the candidate detection model, and determines whether the machine learning model training is completed according to the model loss function, thereby improving the prediction accuracy of the magnetic stirrer detection model.

[0238] In one embodiment, Figure 7As shown, the target operation data of the stirring device to be detected is obtained, and the operation state of the magnetic stirring bar to be detected in the stirring device to be detected is determined according to the magnetic stirring bar detection model and the target operation data, including:

[0239] like Figure 7 As shown, the magnetic stirring bar detection method provided in the embodiment of the present application includes steps S710 to S730.

[0240] S710: Obtain target operating data of the stirring device to be detected.

[0241] The target operating data includes a target motor torque and a target motor speed.

[0242] S720 : Determine a target torque time domain characteristic of the stirring device to be detected according to the target motor torque, and determine a target order spectrum energy characteristic of the stirring device to be detected according to the target operation data.

[0243] Among them, the target torque time domain characteristics include the target mean, target effective value, target peak factor, target standard deviation, target signal peak, target kurtosis and target disturbance factor corresponding to the target motor torque.

[0244] Specifically, feature extraction is performed on the target motor torque to determine the target torque time domain characteristics of the target stirring device, order analysis is performed on the target motor torque based on the target operation data to determine the order signal of the target motor torque, the target order spectrum of the target motor torque is determined based on the order signal of the target motor torque, and the target order spectrum energy characteristics are determined based on the target order spectrum.

[0245] S730. Input the target torque time domain characteristics and the target order spectrum energy characteristics into the magnetic stirrer detection model (i.e., the target detection model), determine the target state label (i.e., the target motion state) of the magnetic stirrer to be detected in the stirring device to be detected based on the output data of the magnetic stirrer detection model, and determine the operating state (i.e., the target motion state) of the magnetic stirrer to be detected based on the target state label.

[0246] Exemplarily, the data range corresponding to the torque characteristic data of the magnetic stirrer when the magnetic stirrer has abnormal phenomena such as loss of step, jumping, wear or weak magnetism can be pre-set. The target torque time domain characteristics and the target order spectrum energy characteristics are input into the magnetic stirrer detection model, and the target state label of the magnetic stirrer to be detected in the stirring device to be detected is determined according to the output data of the magnetic stirrer detection model. The target state label is used to characterize the operating state of the magnetic stirrer to be detected. Exemplarily, the magnetic stirrer detection model can determine the target state label of the magnetic stirrer to be detected based on the target torque time domain characteristics and its corresponding data range, as well as the target order spectrum energy characteristics and its corresponding data range, and can determine the abnormal cause of the magnetic stirrer according to the target state label.

[0247] The above scheme determines the target torque time domain characteristics and target order spectrum energy characteristics of the stirring device to be detected based on the target operation data of the stirring device to be detected, determines the target state label of the magnetic stirring bar to be detected based on the target torque time domain characteristics and target order spectrum energy characteristics through the magnetic stirring bar detection model, and determines the operating state of the magnetic stirring bar to be detected based on the target state label, which can improve the accuracy of the determined operating state of the magnetic stirring bar to be detected.

[0248] Exemplarily, based on the above embodiment, the magnetic stirring bar detection method includes:

[0249] When the sample stirring device is detected to be activated, the motor driver continuously collects the sample motor torque and sample motor speed of the sample stirring device in real time, and the collected sample motor torque and sample motor speed are used as sample operation data of the sample stirring device. Preferably, the sampling frequency used when collecting the sample operation data is greater than or equal to 200 Hz. When the sample stirring device is detected to be stopped, the collection of sample operation data is simultaneously stopped to avoid collecting invalid sample operation data.

[0250] Example 4

[0251] like Figure 8 As shown, the magnetic stirring bar detection device provided in the embodiment of the present application includes:

[0252] A first acquisition module 810 is configured to acquire target operating data of a stirring device to be tested, wherein the stirring device to be tested includes a magnetic stirrer to be tested; the target operating data includes N target motor torques, or N target motor speeds and N target motor torques, where N is a positive integer;

[0253] A first extraction module 820, connected to the first acquisition module, is used to extract the target operation data to obtain target features;

[0254] The detection module 830 is connected to the first extraction module 820 and is used to detect the target features using a target detection model to obtain the target operating state of the magnetic stirrer to be detected, wherein the target detection model is trained by historical features and their corresponding historical operating states.

[0255] In some embodiments, when the target operating data includes N target motor torques,

[0256] The target feature includes a target torque time domain feature, wherein the target torque time domain feature includes at least one of a target mean, a target effective value, a target peak factor, a target standard deviation, a target signal peak, a target kurtosis, and a target disturbance factor.

[0257] In some embodiments, when the target operating data includes N target motor speeds and N target motor torques, the target motor speeds and the target motor torques correspond one to one, and the target feature includes a target order spectrum energy feature;

[0258] The first extraction module 820 is specifically configured to:

[0259] Determine N first motor rotation angles according to the N target motor speeds and their corresponding N target acquisition timestamps, wherein the target motor speeds correspond one-to-one to the target acquisition timestamps and the first motor rotation angles respectively;

[0260] Determining a target torque order spectrum according to the N first motor rotation angles;

[0261] According to the target torque order spectrum, the target order spectrum energy characteristics are determined.

[0262] In some implementations, the first extraction module 820 is specifically configured to:

[0263] Determine M identical first motor rotation angles among the N first motor rotation angles as M target motor rotation angles, where M is less than or equal to N and is a positive integer;

[0264] Determine a target torque order signal according to the M target motor torques corresponding to the M target motor rotation angles;

[0265] Perform Fourier transform on the target torque order signal to obtain the target torque order spectrum.

[0266] In some embodiments,

[0267] The first extraction module 820 is specifically configured to:

[0268] According to the M target motor torques corresponding to the M target motor rotation angles, the target torque order signal is determined, specifically including:

[0269] The M target motor torques corresponding to the M target motor angles are sorted according to the target acquisition timestamps to obtain a target sequence;

[0270] The target sequence is interpolated to obtain the target torque order signal.

[0271] In some implementations, the first acquisition module 810 is specifically configured to:

[0272] Obtaining a target sampling frequency and first initial operating data of the stirring device to be tested, the first initial operating data including P first initial motor torques, or P first initial motor speeds and P first initial motor torques; wherein the first initial motor speeds and the first initial motor torques correspond one to one, P is a positive integer, and P is greater than or equal to N;

[0273] Grouping the first initial operating data according to a target sampling frequency to obtain P / N groups of intermediate operating data, where the intermediate operating data includes N first initial motor torques, or includes N first initial motor speeds and N first initial motor torques;

[0274] Any one group of intermediate operating data among the P / N groups of intermediate operating data is determined as target operating data of the stirring device to be detected.

[0275] The magnetic stirrer detection device provided in the embodiment of the present application can execute the magnetic stirrer detection method in the embodiment of the present application, that is, it has the beneficial effects and implementation methods of the magnetic stirrer detection method provided in Example 1 of the present application. For details, please refer to the specific description of the magnetic stirrer detection method in the above Example 1, which will not be repeated in this embodiment.

[0276] Example 5

[0277] The detection model training device provided in the embodiment of the present application is used to train the target detection model of embodiment 1, and the device includes:

[0278] a second acquisition module, configured to acquire historical operating data of a stirring device, wherein the stirring device includes a magnetic stirring bar; the historical operating data includes Q historical motor torques, or Q historical motor speeds and Q historical motor torques, where Q is a positive integer;

[0279] A second extraction module, connected to the second acquisition module, is used to extract historical operation data to obtain historical features;

[0280] The training module is connected to the second extraction module and is used to train the preset model using historical features and their corresponding historical operating states to obtain a target detection model.

[0281] In some embodiments, when the historical operating data includes Q historical motor torques,

[0282] The historical features include historical torque time domain features, wherein the historical torque time domain features include at least one of a historical mean, a historical effective value, a historical peak factor, a historical standard deviation, a historical signal peak, a historical kurtosis, and a historical disturbance factor.

[0283] In some embodiments, when the historical operating data includes Q historical motor speeds and Q historical motor torques, the historical motor speeds and the historical motor torques correspond one to one, and the historical features include historical order spectrum energy features;

[0284] The second extraction module is specifically used to:

[0285] Determine Q second motor rotation angles based on Q historical motor speeds and their corresponding Q historical acquisition timestamps, where the historical motor speeds correspond one-to-one to the historical acquisition timestamps and the second motor rotation angles respectively;

[0286] Determine the historical torque order spectrum based on Q historical motor rotation angles;

[0287] According to the historical torque order spectrum, the energy characteristics of the historical order spectrum are determined.

[0288] In some examples, the second extraction module is specifically configured to:

[0289] Determine I identical second motor rotation angle among the Q second motor rotation angles as I historical motor rotation angle, where I is less than or equal to Q, and I is a positive integer;

[0290] Determine a historical torque order signal according to I historical motor torques corresponding one to one to I historical motor rotation angles;

[0291] Perform Fourier transform on the historical torque order signal to obtain the historical torque order spectrum.

[0292] In some examples, the second extraction module is specifically configured to:

[0293] The historical motor torques corresponding to the historical motor angles are sorted according to the historical acquisition timestamps to obtain a historical sequence;

[0294] Interpolate the historical sequence to obtain the historical torque order signal.

[0295] In some examples, the second acquisition module is specifically configured to:

[0296] Obtaining a historical sampling frequency and second initial operating data of the stirring device, where the second initial operating data includes J second initial motor torques, or J second initial motor speeds and J second initial motor torques; wherein the second initial motor speeds correspond to the second initial motor torques one-to-one, J is a positive integer, and J is greater than or equal to Q;

[0297] Grouping the second initial operating data according to the historical sampling frequency to obtain J / Q groups of second intermediate operating data, where the second intermediate operating data includes Q initial motor torques, or Q initial motor speeds and Q initial motor torques;

[0298] Any one of the J / Q groups of second intermediate operating data is determined as the historical operating data of the stirring device.

[0299] The detection model training device provided in the embodiment of the present application can execute the detection model training method in the embodiment of the present application, and has the beneficial effects and implementation methods of the detection model training method provided in Example 2 of the present application. For details, please refer to the specific description of the detection model training method in the above Example 2, and this embodiment will not be repeated here.

[0300] Example 6

[0301] The embodiment of the present application provides a computer device, which may be a terminal, and its internal structure diagram may be as follows: Figure 9 As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface, the display unit and the input device are connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a magnetic stirrer detection method is implemented. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device casing, or an external keyboard, touchpad or mouse.

[0302] Those skilled in the art will understand that Figure 9 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0303] Example 7

[0304] An embodiment of the present application provides a computer device, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, it implements the magnetic stirrer detection method in Example 1 and / or Example 3, and / or implements the detection model training method in Example 2.

[0305] Example 8

[0306] An embodiment of the present application provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, it implements the magnetic stirrer detection method in Example 1 and / or Example 3, and / or implements the detection model training method in Example 2.

[0307] Example 9

[0308] An embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the magnetic stirrer detection method in Example 1 and / or Example 3, and / or implements the detection model training method in Example 2.

[0309] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions.

[0310] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processor involved in the various embodiments provided herein may be, but are not limited to, a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, and the like.

[0311] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0312] It is understood that the above embodiments are merely exemplary embodiments for illustrating the principles of the present application, and the present application is not limited thereto. Those skilled in the art may make various modifications and improvements without departing from the spirit and substance of the present application, and such modifications and improvements are also considered to be within the scope of protection of the present application.

Claims

1. A magnetic stirring bar detection method, characterized in that, include: Obtain target operating data of the stirring device to be detected, wherein the stirring device to be detected includes a magnetic stirrer to be detected; the target operating data includes N target motor torques, or includes N target motor speeds and N target motor torques, where N is a positive integer; Extracting the target operation data to obtain target features; The target features are detected using a target detection model to obtain the target operating state of the magnetic stirrer to be detected, wherein the target detection model is trained by historical features and their corresponding historical operating states.

2. The method according to claim 1, characterized in that In the case where the target operation data includes N target motor torques, The target feature includes a target torque time domain feature, wherein the target torque time domain feature includes at least one of a target mean, a target effective value, a target peak factor, a target standard deviation, a target signal peak, a target kurtosis, and a target disturbance factor.

3. The method according to claim 1 or 2, characterized in that In a case where the target operating data includes N target motor speeds and N target motor torques, the target motor speeds and the target motor torques correspond one to one, and the target feature includes a target order spectrum energy feature; Extracting the target operation data to obtain target features specifically includes: Determine N first motor rotation angles according to N target motor speeds and their corresponding N target acquisition timestamps, wherein the target motor speeds correspond one-to-one to the target acquisition timestamps and the first motor rotation angles respectively; Determining a target torque order spectrum according to the N first motor rotation angles; The target order spectrum energy characteristics are determined according to the target torque order spectrum.

4. The method according to claim 3, characterized in that Determine the target torque order spectrum based on the N first motor rotation angles, specifically including: Determine M identical first motor rotation angles among the N first motor rotation angles as M target motor rotation angles, where M is less than or equal to N and is a positive integer; Determine a target torque order signal according to the M target motor torques corresponding to the M target motor rotation angles; Performing Fourier transform on the target torque order signal to obtain a target torque order spectrum.

5. The method according to claim 4, characterized in that According to the M target motor torques corresponding to the M target motor rotation angles, the target torque order signal is determined, specifically including: The M target motor torques corresponding to the M target motor angles are sorted according to the target acquisition timestamps to obtain a target sequence; The target sequence is interpolated to obtain a target torque order signal.

6. The method according to claim 1, wherein Obtain target operating data of the stirring device to be tested, including: Obtaining a target sampling frequency and first initial operating data of the stirring device to be tested, where the first initial operating data includes P first initial motor torques, or P first initial motor speeds and P first initial motor torques; wherein the first initial motor speeds and the first initial motor torques correspond one to one, P is a positive integer, and P is greater than or equal to N; Grouping the first initial operating data according to the target sampling frequency to obtain P / N groups of first intermediate operating data, where the first intermediate operating data includes N first initial motor torques, or includes N first initial motor speeds and N first initial motor torques; Any one of the P / N groups of first intermediate operating data is determined as target operating data of the stirring device to be detected.

7. A detection model training method, characterized in that: The method is used to train and obtain the target detection model according to any one of claims 1 to 6, and the method comprises: Acquire historical operating data of a stirring device, wherein the stirring device includes a magnetic stirring bar; the historical operating data includes Q historical motor torques, or includes Q historical motor speeds and Q historical motor torques, where Q is a positive integer; Extracting the historical operation data to obtain historical features; The preset model is trained using the historical features and their corresponding historical operating states to obtain the target detection model.

8. The method according to claim 7, characterized in that In the case where the historical operation data includes Q historical motor torques, The historical features include historical torque time domain features, wherein the historical torque time domain features include at least one of a historical mean, a historical effective value, a historical peak factor, a historical standard deviation, a historical signal peak, a historical kurtosis, and a historical disturbance factor.

9. The method according to claim 7 or 8, characterized in that In a case where the historical operating data includes Q historical motor speeds and Q historical motor torques, the historical motor speeds and the historical motor torques correspond one to one, and the historical features include historical order spectrum energy features; The historical operation data is extracted to obtain historical features, specifically including: Determine Q second motor rotation angles according to Q historical motor speeds and their corresponding Q historical acquisition timestamps, wherein the historical motor speeds correspond one-to-one to the historical acquisition timestamps and the second motor rotation angles respectively; Determine the historical torque order spectrum based on Q historical motor rotation angles; The energy characteristics of the historical order spectrum are determined according to the historical torque order spectrum.

10. A magnetic stirring bar detection device, characterized in that: include: A first acquisition module is configured to acquire target operating data of a stirring device to be detected, wherein the stirring device to be detected includes a magnetic stirrer to be detected; the target operating data includes N target motor torques, or includes N target motor speeds and N target motor torques, where N is a positive integer; a first extraction module, connected to the first acquisition module, configured to extract the target operation data to obtain target features; A detection module is connected to the first extraction module and is used to detect the target features using a target detection model to obtain the target operating state of the magnetic stirrer to be detected, wherein the target detection model is trained by historical features and their corresponding historical operating states.

11. The device according to claim 10, characterized in that In the case where the target operation data includes N target motor torques, The target feature includes a target torque time domain feature, wherein the target torque time domain feature includes at least one of a target mean, a target effective value, a target peak factor, a target standard deviation, a target signal peak, a target kurtosis, and a target disturbance factor; and / or, In a case where the target operating data includes N target motor speeds and N target motor torques, the target motor speeds and the target motor torques correspond one to one, and the target feature includes a target order spectrum energy feature; The first extraction module is specifically configured to: Determine N first motor rotation angles according to N target motor speeds and their corresponding N target acquisition timestamps, wherein the target motor speeds correspond one-to-one to the target acquisition timestamps and the first motor rotation angles respectively; Determining a target torque order spectrum according to the N first motor rotation angles; The target order spectrum energy characteristics are determined according to the target torque order spectrum.

12. A detection model training device, characterized in that: The device is used to train and obtain the target detection model according to any one of claims 1 to 6, and the device comprises: A second acquisition module is configured to acquire historical operating data of a stirring device, wherein the stirring device includes a magnetic stirring bar; the historical operating data includes Q historical motor torques, or includes Q historical motor speeds and Q historical motor torques, where Q is a positive integer; a second extraction module, connected to the second acquisition module, configured to extract the historical operation data to obtain historical features; A training module, connected to the second extraction module, is used to train a preset model using the historical features and their corresponding historical operating states to obtain the target detection model.

Images