Method, device and computer equipment for determining electromagnetic bearing clearance detection results

Abstract

The present disclosure proposes a method, device and computer equipment for determining the gap detection result of an electromagnetic bearing, which relates to the field of computer technology. The method includes: obtaining a relationship curve between the current difference and the displacement corresponding to the electromagnetic bearing during a gap detection process; processing the relationship curve to obtain a first eigenvector; inputting the first eigenvector into a trained gap detection classification model to determine a first classification result corresponding to the first eigenvector; and determining whether the gap detection corresponding to the relationship curve is valid based on the first classification result. Thus, by processing the relationship curve between the current difference and the displacement during the gap detection process to obtain the first eigenvector, and then using the trained gap detection classification model to obtain the corresponding first classification result, the effectiveness of the gap detection can be determined. This process does not require manual operation, saves time and improves efficiency.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to a method and device for determining an electromagnetic bearing clearance detection result, and a computer device. Background Art

[0002] Bearings are essential basic components of the machinery industry, especially rotary machinery. The development of the modern machinery industry has put forward many newer and higher requirements for bearings under many working conditions and special occasions. Traditional bearings are difficult or unable to meet these requirements. This has promoted the research of many new slewing bearings, and electromagnetic bearings are one of the more successful ones.

[0003] Electromagnetic bearings are a new type of high-performance support component or bearing that uses magnetic field force, that is, electromagnetic force, to stably suspend the rotor in space without mechanical contact, and the axis position can be controlled by a control system. Electromagnetic bearings have many advantages that traditional bearings cannot match, such as: no contact, no friction, no wear, no need for lubrication, high precision, long life, etc., which makes the application range of electromagnetic bearings more and more extensive. For example, it can be used in magnetic bearing-supported equipment such as the main helium blower of high-temperature gas-cooled reactors and helium compressors.

[0004] Usually, in the process of electromagnetic bearing clearance detection, manual detection is usually required, which may take a lot of time and is not efficient. Therefore, how to improve the efficiency of electromagnetic bearing clearance detection is very important. Summary of the invention

[0005] The present disclosure aims to solve one of the technical problems in the related art at least to some extent.

[0006] The first embodiment of the present disclosure provides a method for determining an electromagnetic bearing clearance detection result, comprising:

[0007] Obtain a relationship curve between the current difference and the displacement corresponding to the electromagnetic bearing during a gap detection process;

[0008] Processing the relationship curve to obtain a first eigenvector;

[0009] Inputting the first feature vector into a trained gap detection classification model to determine a first classification result corresponding to the first feature vector;

[0010] It is determined whether the gap detection corresponding to the relationship curve is valid according to the first classification result.

[0011] Optionally, processing the relationship curve to obtain a first eigenvector includes:

[0012] Dividing the relationship curve in the coordinate region to obtain N*N squares, where N is any integer greater than 1;

[0013] Determine the first value as the value corresponding to the square through which the relationship curve passes, and determine the second value as the value corresponding to the square through which the relationship curve does not pass;

[0014] Connect each of the squares in order;

[0015] The numerical values ​​corresponding to each of the spliced ​​squares are merged to obtain the corresponding first eigenvector.

[0016] Optionally, determining whether the gap detection corresponding to the relationship curve is valid according to the first classification result includes:

[0017] When the first classification result is normal, determining that the gap detection corresponding to the relationship curve is valid;

[0018] When the first classification result is abnormal, it is determined that the gap detection result corresponding to the relationship curve is invalid.

[0019] Optionally, after determining that the gap detection result corresponding to the relationship curve is invalid, the method further includes:

[0020] Performing M clearance detections on the electromagnetic bearing to determine M second classification results corresponding to the M clearance detections, wherein M is any integer greater than or equal to 1;

[0021] When all M second classification results are abnormal, an abnormal prompt is given.

[0022] Optionally, performing M clearance detections on the electromagnetic bearing to determine M second classification results corresponding to the M clearance detections includes:

[0023] Based on at least one current value, performing M clearance detections on the electromagnetic bearing to obtain M second classification results; or,

[0024] Based on at least one channel, M clearance detections are performed on the electromagnetic bearing to obtain M second classification results.

[0025] Optionally, before inputting the first feature vector into the trained gap detection classification model to determine a first classification result corresponding to the first feature vector, the method further includes:

[0026] Obtaining a historical relationship curve set between current difference and displacement corresponding to at least one electromagnetic bearing of the same type, wherein the historical relationship curve set includes a plurality of historical relationship curves and corresponding annotation labels;

[0027] Processing each of the historical relationship curves to obtain a second eigenvector corresponding to each of the historical relationship curves;

[0028] Input each of the second feature vectors into an initial model to determine a predicted label corresponding to each of the second feature vectors;

[0029] Determine a loss value based on a difference between a predicted label and an annotated label corresponding to each of the second feature vectors;

[0030] Based on the loss value, the initial model is modified to obtain a trained gap detection classification model.

[0031] Optionally, the step of obtaining a set of historical relationship curves between current difference and displacement corresponding to at least one electromagnetic bearing of the same type includes:

[0032] When the number of first historical relationship curves labeled as abnormal types is less than a first threshold, the second historical relationship curve labeled as normal types is modified to generate a new third historical relationship curve, wherein the labeling labels of the first historical relationship curve and the third relationship curve are both abnormal types.

[0033] The second aspect of the present disclosure provides a device for determining a clearance detection result of an electromagnetic bearing, comprising:

[0034] An acquisition module is used to obtain a relationship curve between a current difference and a displacement corresponding to the electromagnetic bearing during a gap detection process;

[0035] A processing module, used for processing the relationship curve to obtain a first eigenvector;

[0036] A first determination module, used for inputting the first feature vector into a trained gap detection classification model to determine a first classification result corresponding to the first feature vector;

[0037] The second determination module is used to determine whether the gap detection corresponding to the relationship curve is valid according to the first classification result.

[0038] Optionally, the processing module is specifically used to:

[0039] Dividing the relationship curve in the coordinate region to obtain N*N squares, where N is any integer greater than 1;

[0040] Determine the first value as the value corresponding to the square through which the relationship curve passes, and determine the second value as the value corresponding to the square through which the relationship curve does not pass;

[0041] Connect each of the squares in order;

[0042] The numerical values ​​corresponding to each of the spliced ​​squares are merged to obtain the corresponding first eigenvector.

[0043] Optionally, the second determining module is specifically configured to:

[0044] When the first classification result is normal, determining that the gap detection corresponding to the relationship curve is valid;

[0045] When the first classification result is abnormal, it is determined that the gap detection result corresponding to the relationship curve is invalid.

[0046] Optionally, the second determining module includes:

[0047] A detection unit, configured to perform M clearance detections on the electromagnetic bearing to determine M second classification results corresponding to the M clearance detections, wherein M is any integer greater than or equal to 1;

[0048] The prompting unit is used to give an abnormal prompt when all the M second classification results are abnormal.

[0049] Optionally, the detection unit is specifically used to:

[0050] Based on at least one current value, performing M clearance detections on the electromagnetic bearing to obtain M second classification results; or,

[0051] Based on at least one channel, M clearance detections are performed on the electromagnetic bearing to obtain M second classification results.

[0052] Optionally, the first determining module includes:

[0053] An acquisition unit, used to acquire a historical relationship curve set between a current difference and a displacement corresponding to at least one electromagnetic bearing of the same type, wherein the historical relationship curve set includes a plurality of historical relationship curves and corresponding annotation labels;

[0054] A processing unit, used for processing each of the historical relationship curves to obtain a second eigenvector corresponding to each of the historical relationship curves;

[0055] A first determining unit, configured to input each of the second feature vectors into an initial model to determine a prediction label corresponding to each of the second feature vectors;

[0056] A second determining unit, configured to determine a loss value based on a difference between a predicted label and an annotated label corresponding to each of the second feature vectors;

[0057] A correction unit is used to correct the initial model based on the loss value to obtain a trained gap detection classification model.

[0058] Optionally, the acquisition unit is specifically used to:

[0059] When the number of first historical relationship curves labeled as abnormal types is less than a first threshold, the second historical relationship curve labeled as normal types is modified to generate a new third historical relationship curve, wherein the labeling labels of the first historical relationship curve and the third relationship curve are both abnormal types.

[0060] The third aspect embodiment of the present disclosure proposes a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the method for determining the electromagnetic bearing clearance detection result proposed in the first aspect embodiment of the present disclosure is implemented.

[0061] The fourth aspect embodiment of the present disclosure proposes a non-temporary computer-readable storage medium storing a computer program, which, when executed by a processor, implements the method for determining the electromagnetic bearing clearance detection result as proposed in the first aspect embodiment of the present disclosure.

[0062] The fifth aspect of the present disclosure provides a computer program product. When an instruction processor in the computer program product is executed, the method for determining the electromagnetic bearing gap detection result provided in the first aspect of the present disclosure is executed.

[0063] The method, device, computer equipment and storage medium for determining the gap detection result of the electromagnetic bearing provided by the present disclosure can first obtain the relationship curve between the current difference and the displacement corresponding to the electromagnetic bearing in a gap detection process, and then process the relationship curve to obtain a first eigenvector, and then input the first eigenvector into the trained gap detection classification model to determine the first classification result corresponding to the first eigenvector, and then determine whether the gap detection corresponding to the relationship curve is effective based on the first classification result. Thus, by processing the relationship curve between the current difference and the displacement in the gap detection process, the first eigenvector is obtained, and then the trained gap detection classification model is used to obtain the corresponding first classification result, and then the effectiveness of the gap detection can be determined. This process does not require manual operation, saves time and improves efficiency. Additional aspects and advantages of the present disclosure will be partially given in the following description, and part will become obvious from the following description, or will be understood through the practice of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] The above and / or additional aspects and advantages of the present disclosure will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0065] Figure 1 A schematic flow chart of a method for determining an electromagnetic bearing clearance detection result provided in an embodiment of the present disclosure;

[0066] Figure 1A A schematic diagram of a curve showing the relationship between the current difference ΔI and the displacement x of the electromagnetic bearing gap detection provided by an embodiment of the present disclosure;

[0067] Figure 1B A schematic diagram of a relationship curve after being divided into squares according to an embodiment of the present disclosure;

[0068] Figure 1C A schematic diagram showing the numerical value corresponding to each square provided in an embodiment of the present disclosure;

[0069] Figure 2 A schematic flow chart of a method for determining an electromagnetic bearing clearance detection result provided by another embodiment of the present disclosure;

[0070] Figure 3 A schematic flow chart of a method for determining an electromagnetic bearing clearance detection result provided by another embodiment of the present disclosure;

[0071] Figure 3A A schematic diagram of a process for determining an electromagnetic bearing clearance detection result provided by another embodiment of the present disclosure;

[0072] Figure 4 A schematic diagram of the structure of a device for determining an electromagnetic bearing clearance detection result provided by an embodiment of the present disclosure;

[0073] Figure 5 A block diagram of an exemplary computer device suitable for implementing embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0074] Embodiments of the present disclosure are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present disclosure, and should not be construed as limiting the present disclosure.

[0075] The following describes a method, apparatus, computer device, and storage medium for determining an electromagnetic bearing clearance detection result according to an embodiment of the present disclosure with reference to the accompanying drawings.

[0076] The embodiment of the present disclosure takes the method for determining the electromagnetic bearing gap detection result as an example, in which the method is configured in a device for determining the electromagnetic bearing gap detection result. The device for determining the electromagnetic bearing gap detection result can be applied to any computer device so that the computer device can perform the function of determining the electromagnetic bearing gap detection result.

[0077] Among them, the computer device can be a personal computer (PC), a cloud device, a mobile device, etc. The mobile device can be, for example, a mobile phone, a tablet computer, a personal digital assistant, a wearable device, a car device, etc., which are hardware devices with various operating systems, touch screens and / or display screens.

[0078] Figure 1 A schematic flow chart of a method for determining an electromagnetic bearing clearance detection result provided in an embodiment of the present disclosure.

[0079] like Figure 1 As shown, the method for determining the electromagnetic bearing clearance detection result may include the following steps:

[0080] Step 101, obtaining a relationship curve between a current difference and a displacement corresponding to an electromagnetic bearing in a gap detection process.

[0081] Among them, a displacement sensor can be set on the electromagnetic bearing, and a current value I is applied to the electromagnetic bearing to make the rotor position move continuously, so that the corresponding relationship between the position x between the rotor and the first contact point of the auxiliary bearing in the electromagnetic bearing and the current difference ΔI during the movement of the rotor can be obtained, that is, the relationship curve between the current difference and the displacement, etc., which is not limited in this disclosure.

[0082] The current difference ΔI may be understood as the difference between the current value I and the current real-time current value when the rotor is at different positions.

[0083] Step 102: Process the relationship curve to obtain a first eigenvector.

[0084] Optionally, the relationship curve between the current difference and the displacement can be divided in the coordinate area to obtain N*N squares, and then the first value can be determined as the value corresponding to the squares passed by the relationship curve, and the second value can be determined as the value corresponding to the squares not passed by the relationship curve, and each square can be spliced ​​in order, and then the values ​​corresponding to each spliced ​​square are fused to obtain the corresponding first eigenvector.

[0085] Among them, N can be any integer greater than 1; it can be a pre-set value, such as 6, 10, 20, etc., or it can be adjusted according to needs, etc.; the present disclosure does not limit this.

[0086] In addition, there are many ways to merge the values ​​corresponding to each square, such as splicing the values ​​corresponding to each square by row, or splicing by column, or any other desirable way to merge, etc., and the present disclosure does not limit this.

[0087] For example, if the relationship curve between the current difference ΔI and the displacement x of a certain electromagnetic bearing gap detection is as follows: Figure 1A As shown, when the value of N is 21, the relationship curve can be divided into squares in the coordinate area to obtain Figure 1B The 21*21 squares shown. Then the value corresponding to the square through which the relationship curve passes can be determined as 1, for example Figure 1C The black squares in the relationship curve are set to 0. Figure 1C Then, each square can be expanded according to its position. For example, all the squares can be spliced ​​in rows, and the values ​​corresponding to each square can be spliced ​​in order, which is the first eigenvector.

[0088] Optionally, the relationship curve between the current difference and the displacement can be analyzed to determine the minimum current difference and the maximum current difference. Then, the relationship curve can be divided into three sub-relationship curves according to the minimum current difference and the maximum current difference. Then, the corresponding proportion of each sub-relationship curve in the relationship curve can be determined according to the length of each sub-relationship curve, and then the various proportion values ​​can be spliced ​​to obtain a first eigenvector, etc. The present disclosure does not limit this.

[0089] Step 103: input the first feature vector into the trained gap detection classification model to determine a first classification result corresponding to the first feature vector.

[0090] Among them, the gap detection classification model can be a model that has been trained in advance. For example, any initial model can be trained to obtain a trained gap detection classification model, etc., and the present disclosure does not limit this.

[0091] In addition, there may be multiple first classification results, such as normal or abnormal, etc., and the present disclosure does not limit this.

[0092] It can be understood that in the embodiment of the present disclosure, the first feature vector can be input into a trained gap detection classification model, and after being processed by the gap detection classification model, a first classification result corresponding to the first feature vector can be determined.

[0093] Step 104: Determine whether the gap detection corresponding to the relationship curve is valid according to the first classification result.

[0094] It is understandable that, since there are multiple first classification results, when the first classification results are different, the gap detection corresponding to the relationship curve may also be different, and the present disclosure does not limit this.

[0095] Optionally, when the first classification result is normal, it can be determined that the gap detection corresponding to the relationship curve is valid; when the first classification result is abnormal, it can be determined that the gap detection result corresponding to the relationship curve is invalid.

[0096] Therefore, in the embodiment of the present disclosure, based on the first eigenvector corresponding to the relationship curve between the current difference and the displacement, combined with the trained gap detection classification model, the corresponding first classification result can be determined more accurately, and then based on the first classification result, it can be determined whether the gap detection is effective. This process does not require manual operation, saves time and improves efficiency.

[0097] In the disclosed embodiment, the relationship curve between the current difference and the displacement corresponding to the electromagnetic bearing in a gap detection process can be first obtained, and then the relationship curve can be processed to obtain a first eigenvector, and then the first eigenvector can be input into the trained gap detection classification model to determine the first classification result corresponding to the first eigenvector, and then according to the first classification result, it can be determined whether the gap detection corresponding to the relationship curve is effective. Thus, by processing the relationship curve between the current difference and the displacement in the gap detection process to obtain the first eigenvector, and then using the trained gap detection classification model, the corresponding first classification result can be obtained, and then the effectiveness of the gap detection can be determined. This process does not require manual operation, saves time, and improves efficiency.

[0098] Figure 2 A schematic flow chart of a method for determining an electromagnetic bearing clearance detection result provided in an embodiment of the present disclosure.

[0099] like Figure 2 As shown, the method for determining the electromagnetic bearing clearance detection result may include the following steps:

[0100] Step 201, obtaining a relationship curve between a current difference and a displacement corresponding to an electromagnetic bearing in a gap detection process.

[0101] Step 202: Process the relationship curve to obtain a first eigenvector.

[0102] Step 203: input the first feature vector into the trained gap detection classification model to determine a first classification result corresponding to the first feature vector.

[0103] Step 204 , when the first classification result is normal, determine that the gap detection corresponding to the relationship curve is valid.

[0104] Step 205 , when the first classification result is abnormal, determining that the gap detection result corresponding to the relationship curve is invalid.

[0105] It should be noted that the specific content and implementation of steps 201 to 205 can refer to the description of other embodiments of the present disclosure and will not be repeated here.

[0106] Step 206 , when it is determined that the gap detection result corresponding to the relationship curve is invalid, perform M gap detections on the electromagnetic bearing to determine M second classification results corresponding to the M gap detections, where M is any integer greater than or equal to 1.

[0107] Here, M can be any value set in advance, such as 3, 5, 10, etc., and the present disclosure does not limit this.

[0108] For example, when the value of M is 3, if the gap detection result corresponding to the determined relationship curve is invalid, then the gap detection of the electromagnetic bearing can be repeated three times to obtain the second classification results corresponding to the three gap detections, that is, to obtain three second classification results.

[0109] For example, for gap detection 1, the relationship curve between the corresponding current difference and displacement can be obtained first, and then the relationship curve can be processed to obtain the corresponding first eigenvector, and then the first eigenvector is input into the trained gap detection classification model to determine the corresponding second classification result 1, and then determine the effectiveness of the gap detection corresponding to the relationship curve. The process of obtaining the second classification result 2 and the second classification result 3 is similar to the process of obtaining the second classification result 1, and will not be repeated here.

[0110] It should be noted that the above examples are merely illustrative and cannot be used as limitations on the value of M, the method of determining the second classification result, etc. in the embodiment of the present disclosure.

[0111] Optionally, based on at least one current value, M clearance detections may be performed on the electromagnetic bearing to obtain M second classification results.

[0112] Among them, the same current value can be used to repeatedly perform gap detection on the electromagnetic bearing M times to obtain M second classification results; or different current values ​​can be used to repeatedly perform gap detection on the electromagnetic bearing M times to obtain M second classification results, and so on. The present disclosure does not limit this.

[0113] Optionally, based on at least one channel, M clearance detections may be performed on the electromagnetic bearing to obtain M second classification results.

[0114] It is understandable that the electromagnetic bearing generally includes a plurality of stator coils, each of which may correspond to a respective channel, and the electromagnetic bearing may be subjected to M gap detections based on the same channel to obtain M second classification results. Alternatively, different channels may be used to perform M gap detections on the electromagnetic bearing to obtain M second classification results, and the present disclosure does not limit this.

[0115] Therefore, in the embodiment of the present disclosure, when it is determined that the gap detection result corresponding to the relationship curve is invalid, the electromagnetic bearing can be subjected to M gap detections to determine M second classification results corresponding to the M gap detections, thereby avoiding the need for manual review when an abnormality occurs in the electromagnetic bearing gap detection, reducing manual operations, saving time, and providing conditions for realizing the automation of electromagnetic bearing gap detection.

[0116] Step 207: When all the M second classification results are abnormal, an abnormal prompt is given.

[0117] It is understandable that if all M second classification results are abnormal, it can be indicated that the electromagnetic bearing may have a fault, such as a mechanical fault somewhere inside it, etc. At this time, an abnormal prompt can be given to inform the user that the electromagnetic bearing may need to be replaced or repaired, etc. If the electromagnetic bearing is a component of the main helium blower of the high temperature gas-cooled reactor, then the abnormal prompt provides conditions for ensuring the safety and reliability of the main helium blower of the high temperature gas-cooled reactor.

[0118] In addition, there are many ways to provide abnormal prompts, such as displaying them on the display interface of the associated terminal device; or sending them to the associated terminal device in the form of email or notification; or making voice broadcasts through speakers, etc., which are not limited in this disclosure.

[0119] Optionally, when at least one second classification result among the M second classification results is normal, it can be determined that the gap detection corresponding to the electromagnetic bearing is valid.

[0120] For example, if all three second classification results are normal, then it can be determined that the gap detection corresponding to the electromagnetic bearing is valid; or, if one of the three second classification results is normal, then it can be determined that the gap detection corresponding to the electromagnetic bearing is valid; or, if two of the three second classification results are normal, then it can be determined that the gap detection corresponding to the electromagnetic bearing is valid, and so on. The present disclosure does not limit this.

[0121] In the disclosed embodiment, the relationship curve between the current difference and the displacement corresponding to the electromagnetic bearing in a gap detection process can be first obtained, and then the relationship curve can be processed to obtain a first eigenvector, and then the first eigenvector can be input into the trained gap detection classification model to determine the first classification result corresponding to the first eigenvector, and then according to the first classification result, it can be determined whether the gap detection corresponding to the relationship curve is valid. In the case where the gap detection result corresponding to the relationship curve is determined to be invalid, the electromagnetic bearing can be subjected to M gap detections to determine the M second classification results corresponding to the M gap detections. In the case where the M second classification results are all abnormal, an abnormal prompt is given. Thus, based on the first eigenvector corresponding to the relationship curve between the current difference and the displacement, combined with the trained gap detection classification model, the corresponding first classification result can be determined more accurately, and then according to the first classification result, it can be determined whether the gap detection is valid. In the case where the gap detection is invalid, multiple detections can be repeated to determine whether the electromagnetic bearing is faulty. This process does not require manual operation, saves time, improves efficiency, and also provides conditions for the automation of electromagnetic bearing gap detection.

[0122] It is understandable that the initial model can be trained in advance to obtain a trained gap detection classification model, so that in the electromagnetic bearing gap detection process, the trained gap detection classification model can be directly used. Figure 3 The training process of the gap detection classification model is explained.

[0123] Figure 3 A schematic flow chart of a method for determining an electromagnetic bearing clearance detection result provided in an embodiment of the present disclosure.

[0124] like Figure 3 As shown, the method for determining the electromagnetic bearing clearance detection result may include the following steps:

[0125] Step 301 : obtaining a historical relationship curve set between current difference and displacement corresponding to at least one electromagnetic bearing of the same type, wherein the historical relationship curve set includes a plurality of historical relationship curves and corresponding annotation labels.

[0126] Among them, due to the different sizes and weights of electromagnetic bearings, the types of electromagnetic bearings may also be different, and thus the corresponding current values ​​may also be different. Therefore, in the embodiment of the present disclosure, a historical relationship curve set between the current difference and the displacement corresponding to the same type of electromagnetic bearings can be obtained.

[0127] For example, if there are multiple electromagnetic bearings corresponding to type 1, namely electromagnetic bearing 1 and electromagnetic bearing 2, then one or more historical relationship curves and corresponding annotation labels corresponding to electromagnetic bearing 1 can be obtained, and one or more historical relationship curves and corresponding annotation labels corresponding to electromagnetic bearing 2 can be obtained. Alternatively, if there is only one electromagnetic bearing corresponding to type 2, namely electromagnetic bearing 3, then multiple historical relationship curves and corresponding annotation labels corresponding to electromagnetic bearing 3 can be obtained.

[0128] It should be noted that the above examples are merely illustrative and cannot be used as limitations on the types, quantities, etc. of electromagnetic bearings in the embodiments of the present disclosure.

[0129] It is understandable that the historical relationship curve may include a first historical relationship curve labeled as an abnormal type, or may also include a second historical relationship curve labeled as a normal type, and the present disclosure does not limit this.

[0130] Optionally, when the number of first historical relationship curves labeled as abnormal type is less than a first threshold, the second historical relationship curve labeled as normal type is modified to generate a new third historical relationship curve, wherein the labeling labels of the first historical relationship curve and the third relationship curve are both abnormal type.

[0131] The first threshold may be a value set in advance, such as 10, 100, etc., which is not limited in the present disclosure.

[0132] For example, when the first threshold is 50, if there are only 20 first historical relationship curves, which is less than the first threshold 50, then the second historical relationship curve can be modified, such as changing the minimum current difference value in a second historical relationship curve to a smaller value, and using the modified curve as a new third historical relationship curve. Since the third historical relationship curve and the first historical relationship curve are both relationship curves corresponding to abnormal types, the number of historical relationship curves marked with abnormal types can be increased, so that the historical relationship curves in the historical relationship curve set can be made more comprehensive and complete, etc. The present disclosure does not limit this.

[0133] Step 302: Process each historical relationship curve to obtain a second eigenvector corresponding to each historical relationship curve.

[0134] Among them, the historical relationship curve can be divided in the coordinate area to obtain N*N squares, and then the values ​​corresponding to the squares passed by the historical relationship curve are determined as "1", and the values ​​corresponding to the squares not passed by the historical relationship curve are determined as "0". Then, each square can be spliced ​​in order, and the values ​​corresponding to each spliced ​​square are merged to obtain the corresponding second eigenvector. The specific content and implementation process can refer to the description of obtaining the first eigenvector in other embodiments of the present disclosure, and will not be repeated here.

[0135] Wherein, N may be any integer greater than 1, such as 10, 20, etc. It is understandable that during the generation and use of the gap detection classification model, the value of N needs to be kept the same, and the present disclosure does not limit this.

[0136] Step 303: input each second eigenvector into the initial model to determine the prediction label corresponding to each second eigenvector.

[0137] Among them, the initial model can be any model that can be classified. By inputting the second eigenvector into the initial model and processing it by the initial model, the prediction label corresponding to the second eigenvector can be determined, and the present disclosure does not limit this.

[0138] In addition, there may be multiple prediction labels, such as "normal" or "abnormal", etc., which is not limited in the present disclosure.

[0139] Step 304: Determine a loss value based on the difference between the predicted label and the labeled label corresponding to each second eigenvector.

[0140] Among them, for the same second eigenvector, the difference between the predicted label and the labeled label corresponding to the second eigenvector can be used, for example, the loss function value between the predicted label and the labeled label can be determined through a loss function, and it can be used as the loss value, etc. The present disclosure does not limit this.

[0141] For example, the cross entropy loss function can be used to determine the loss value between the predicted label and the labeled label; or the loss function corresponding to the support vector machine can be used to determine the loss value between the predicted label and the labeled label, and the present disclosure does not limit this.

[0142] Step 305: based on the loss value, the initial model is modified to obtain a trained gap detection classification model.

[0143] It is understandable that after determining the loss value, the initial model can be modified based on the loss value to improve the learning ability and performance of the initial model, thereby obtaining a trained gap detection classification model. For example, the training of the gap detection classification model can be determined to be completed when a preset number of training steps is reached; or the training of the gap detection classification model can be determined to be completed when a preset training cycle is reached, etc., and the present disclosure does not limit this.

[0144] It is understandable that after obtaining the trained gap detection classification model, if there is a need to perform electromagnetic bearing gap detection, the trained gap detection classification model can be directly used, thereby simplifying the electromagnetic bearing gap detection and saving time.

[0145] It should be noted that the method for determining the electromagnetic bearing gap detection result provided in the present disclosure can be applied to any electromagnetic bearing scenario, and the present disclosure does not limit this.

[0146] Combine the following Figure 3A The process of determining the electromagnetic bearing clearance detection result provided by the present disclosure is described.

[0147] First, the gap detection classification model can be trained offline. In the offline training, curve samples can be collected first, that is, the historical relationship curve corresponding to the electromagnetic bearing gap detection can be obtained first, and then abnormal samples can be added, that is, the historical relationship curve with abnormal labels can be added, and then features can be extracted to obtain a second feature vector, and then the second feature vector can be used to train the support vector machine to generate a trained gap detection classification model.

[0148] After that, the trained detection classification model can be used for online prediction. For example, a gap detection can be performed on a certain electromagnetic bearing to obtain the corresponding relationship curve between the current difference and the displacement, and then the features of the relationship curve can be extracted to obtain the first feature vector. After that, the first feature vector can be input into the trained gap detection classification model to determine whether the first classification result corresponding to the first feature vector is normal. If it is normal, it can be determined that the gap detection is over; if it is abnormal, the gap detection of the electromagnetic bearing can continue.

[0149] It should be noted that the above examples are merely illustrative and cannot be used as a limitation on the process of determining the electromagnetic bearing clearance detection result in the embodiment of the present disclosure.

[0150] In the disclosed embodiment, a historical relationship curve set between the current difference and the displacement corresponding to at least one electromagnetic bearing of the same type can be first obtained, wherein the historical relationship curve set includes multiple historical relationship curves and corresponding annotation labels, and then each historical relationship curve can be processed to obtain the second eigenvector corresponding to each historical relationship curve, and then each second eigenvector can be input into the initial model to determine the predicted label corresponding to each second eigenvector, and then the loss value is determined based on the difference between the predicted label and the annotation label corresponding to each second eigenvector, and then the initial model is corrected based on the loss value to obtain a trained gap detection classification model. Thus, the initial model can be trained by using the historical relationship curve set between the current difference and the displacement corresponding to the electromagnetic bearing, and a trained gap detection classification model can be obtained, and then the gap detection classification model can be used to automatically determine the gap detection result of the electromagnetic bearing, and the process does not require manual operation, which saves time, improves efficiency, and provides conditions for the automation of electromagnetic bearing gap detection.

[0151] In order to implement the above embodiment, the present disclosure also proposes a device for determining the electromagnetic bearing gap detection result.

[0152] Figure 4 A schematic diagram of the structure of a device for determining an electromagnetic bearing clearance detection result provided in an embodiment of the present disclosure.

[0153] like Figure 4 As shown, the device 100 for determining the electromagnetic bearing clearance detection result may include: an acquisition module 110 , a processing module 120 , a first determination module 130 and a second determination module 140 .

[0154] The acquisition module 110 is used to obtain a relationship curve between the current difference and the displacement corresponding to the electromagnetic bearing during a gap detection process.

[0155] The processing module 120 is used to process the relationship curve to obtain a first eigenvector.

[0156] The first determination module 130 is used to input the first feature vector into the trained gap detection classification model to determine a first classification result corresponding to the first feature vector.

[0157] The second determination module 140 is used to determine whether the gap detection corresponding to the relationship curve is valid according to the first classification result.

[0158] Optionally, the processing module 120 is specifically configured to:

[0159] Dividing the relationship curve in the coordinate region to obtain N*N squares, where N is any integer greater than 1;

[0160] Determine the first value as the value corresponding to the square through which the relationship curve passes, and determine the second value as the value corresponding to the square through which the relationship curve does not pass;

[0161] Connect each of the squares in order;

[0162] The numerical values ​​corresponding to each of the spliced ​​squares are merged to obtain the corresponding first eigenvector.

[0163] Optionally, the second determining module 140 is specifically configured to:

[0164] When the first classification result is normal, determining that the gap detection corresponding to the relationship curve is valid;

[0165] When the first classification result is abnormal, it is determined that the gap detection result corresponding to the relationship curve is invalid.

[0166] Optionally, the second determining module 140 includes:

[0167] A detection unit, configured to perform M clearance detections on the electromagnetic bearing to determine M second classification results corresponding to the M clearance detections, wherein M is any integer greater than or equal to 1;

[0168] The prompting unit is used to give an abnormal prompt when all the M second classification results are abnormal.

[0169] Optionally, the detection unit is specifically used to:

[0170] Based on at least one current value, performing M clearance detections on the electromagnetic bearing to obtain M second classification results; or,

[0171] Based on at least one channel, M clearance detections are performed on the electromagnetic bearing to obtain M second classification results.

[0172] Optionally, the first determining module 120 includes:

[0173] An acquisition unit, used to acquire a historical relationship curve set between a current difference and a displacement corresponding to at least one electromagnetic bearing of the same type, wherein the historical relationship curve set includes a plurality of historical relationship curves and corresponding annotation labels;

[0174] A processing unit, used for processing each of the historical relationship curves to obtain a second eigenvector corresponding to each of the historical relationship curves;

[0175] A first determining unit, configured to input each of the second feature vectors into an initial model to determine a prediction label corresponding to each of the second feature vectors;

[0176] A second determining unit, configured to determine a loss value based on a difference between a predicted label and an annotated label corresponding to each of the second feature vectors;

[0177] A correction unit is used to correct the initial model based on the loss value to obtain a trained gap detection classification model.

[0178] Optionally, the acquisition unit is specifically used to:

[0179] When the number of first historical relationship curves labeled as abnormal types is less than a first threshold, the second historical relationship curve labeled as normal types is modified to generate a new third historical relationship curve, wherein the labeling labels of the first historical relationship curve and the third relationship curve are both abnormal types.

[0180] The functions and specific implementation principles of the above modules in the embodiments of the present disclosure can be referred to the above method embodiments, and will not be repeated here.

[0181] The device for determining the gap detection result of the electromagnetic bearing of the disclosed embodiment can first obtain the relationship curve between the current difference and the displacement corresponding to the electromagnetic bearing in a gap detection process, and then process the relationship curve to obtain a first eigenvector, and then input the first eigenvector into the trained gap detection classification model to determine the first classification result corresponding to the first eigenvector, and then determine whether the gap detection corresponding to the relationship curve is effective based on the first classification result. Thus, by processing the relationship curve between the current difference and the displacement in the gap detection process to obtain the first eigenvector, and then using the trained gap detection classification model, the corresponding first classification result can be obtained, and then the effectiveness of the gap detection can be determined. This process does not require manual operation, saves time, and improves efficiency.

[0182] In order to implement the above embodiments, the present disclosure also proposes a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the method for determining the electromagnetic bearing clearance detection result proposed in the above embodiments of the present disclosure is implemented.

[0183] In order to implement the above embodiments, the present disclosure further proposes a non-temporary computer-readable storage medium storing a computer program, which, when executed by a processor, implements the method for determining the electromagnetic bearing gap detection result as proposed in the above embodiments of the present disclosure.

[0184] In order to implement the above embodiments, the present disclosure further proposes a computer program product. When the instruction processor in the computer program product is executed, the method for determining the electromagnetic bearing gap detection result proposed in the above embodiments of the present disclosure is executed.

[0185] Figure 5 A block diagram of an exemplary computer device suitable for implementing embodiments of the present disclosure is shown. Figure 5 The computer device 12 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0186] like Figure 5 As shown, the computer device 12 is in the form of a general-purpose computing device. The components of the computer device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that connects various system components (including the system memory 28 and the processing unit 16).

[0187] The bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor or a local bus using any of a variety of bus structures. For example, these architectures include but are not limited to Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus and Peripheral Component Interconnection (PCI) bus.

[0188] The computer device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the computer device 12, including volatile and non-volatile media, removable and non-removable media.

[0189] The memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. The computer device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 may be used to read and write non-removable, non-volatile magnetic media ( Figure 5not shown, usually called a "hard drive"). Although Figure 5 Not shown in the figure, a disk drive for reading and writing a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing a removable non-volatile optical disk (e.g., a compact disc read only memory (CD-ROM), a digital versatile disc read only memory (DVD-ROM), or other optical media) may be provided. In these cases, each drive may be connected to the bus 18 via one or more data medium interfaces. The memory 28 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the various embodiments of the present disclosure.

[0190] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in the memory 28, such program modules 42 including but not limited to an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. The program modules 42 generally perform the functions and / or methods of the embodiments described in the present disclosure.

[0191] The computer device 12 may also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), one or more devices that enable a user to interact with the computer device 12, and / or any device that enables the computer device 12 to communicate with one or more other computing devices (e.g., network card, modem, etc.). Such communication may be performed via an input / output (I / O) interface 22. In addition, the computer device 12 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 20. As shown, the network adapter 20 communicates with other modules of the computer device 12 via a bus 18. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the computer device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0192] The processing unit 16 executes various functional applications and data processing by running programs stored in the system memory 28, such as implementing the methods mentioned in the above embodiments.

[0193] The technical solution disclosed in the present invention can first obtain the relationship curve between the current difference and the displacement corresponding to the electromagnetic bearing in a gap detection process, and then process the relationship curve to obtain a first eigenvector, and then input the first eigenvector into the trained gap detection classification model to determine the first classification result corresponding to the first eigenvector, and then determine whether the gap detection corresponding to the relationship curve is effective based on the first classification result. Thus, by processing the relationship curve between the current difference and the displacement in the gap detection process to obtain the first eigenvector, and then using the trained gap detection classification model, the corresponding first classification result can be obtained, and then the effectiveness of the gap detection can be determined. This process does not require manual operation, saves time, and improves efficiency.

[0194] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present disclosure. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0195] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of the present disclosure, "plurality" means at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0196] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present disclosure includes additional implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present disclosure belong.

[0197] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute the instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0198] It should be understood that the various parts of the present disclosure can be implemented in hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used to implement: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0199] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0200] In addition, each functional unit in each embodiment of the present disclosure may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0201] The storage medium mentioned above may be a read-only memory, a disk or an optical disk, etc. Although the embodiments of the present disclosure have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations of the present disclosure. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present disclosure.

Claims

1. A method for determining the result of electromagnetic bearing clearance detection, characterized in that: include: Obtain a relationship curve between the current difference and the displacement corresponding to the electromagnetic bearing during a gap detection process; Processing the relationship curve to obtain a first eigenvector; Inputting the first feature vector into a trained gap detection classification model to determine a first classification result corresponding to the first feature vector; Determining whether the gap detection corresponding to the relationship curve is valid according to the first classification result; The processing of the relationship curve to obtain a first eigenvector includes: Dividing the relationship curve in the coordinate region to obtain N*N squares, where N is any integer greater than 1; Determine the first value as the value corresponding to the square through which the relationship curve passes, and determine the second value as the value corresponding to the square through which the relationship curve does not pass; Connect each of the squares in order; The numerical values ​​corresponding to each of the spliced ​​squares are merged to obtain the corresponding first eigenvector.

2. The method according to claim 1, characterized in that The determining, according to the first classification result, whether the gap detection corresponding to the relationship curve is valid includes: When the first classification result is normal, determining that the gap detection corresponding to the relationship curve is valid; When the first classification result is abnormal, it is determined that the gap detection result corresponding to the relationship curve is invalid.

3. The method according to claim 2, characterized in that After determining that the gap detection result corresponding to the relationship curve is invalid, the method further includes: Performing M clearance detections on the electromagnetic bearing to determine M second classification results corresponding to the M clearance detections, wherein M is any integer greater than or equal to 1; When all M second classification results are abnormal, an abnormal prompt is given.

4. The method according to claim 3, characterized in that The performing M times of gap detection on the electromagnetic bearing to determine M second classification results corresponding to the M times of gap detection includes: Based on at least one current value, performing M clearance detections on the electromagnetic bearing to obtain M second classification results; or, Based on at least one channel, M clearance detections are performed on the electromagnetic bearing to obtain M second classification results.

5. The method according to claim 1, characterized in that Before inputting the first feature vector into the trained gap detection classification model to determine a first classification result corresponding to the first feature vector, the method further includes: Obtaining a historical relationship curve set between current difference and displacement corresponding to at least one electromagnetic bearing of the same type, wherein the historical relationship curve set includes a plurality of historical relationship curves and corresponding annotation labels; Processing each of the historical relationship curves to obtain a second eigenvector corresponding to each of the historical relationship curves; Input each of the second feature vectors into an initial model to determine a predicted label corresponding to each of the second feature vectors; Determine a loss value based on a difference between a predicted label and an annotated label corresponding to each of the second feature vectors; Based on the loss value, the initial model is modified to obtain a trained gap detection classification model.

6. The method according to claim 5, characterized in that The step of obtaining a historical relationship curve set between the current difference and the displacement corresponding to at least one electromagnetic bearing of the same type comprises: When the number of first historical relationship curves labeled as abnormal types is less than a first threshold, the second historical relationship curve labeled as normal types is modified to generate a new third historical relationship curve, wherein the labeling labels of the first historical relationship curve and the third historical relationship curve are both abnormal types.

7. A device for determining the result of electromagnetic bearing clearance detection, characterized in that: include: An acquisition module is used to obtain a relationship curve between a current difference and a displacement corresponding to the electromagnetic bearing during a gap detection process; A processing module, used for processing the relationship curve to obtain a first eigenvector; A first determination module, used for inputting the first feature vector into a trained gap detection classification model to determine a first classification result corresponding to the first feature vector; A second determination module, configured to determine whether the gap detection corresponding to the relationship curve is valid according to the first classification result; The processing module is further used to divide the relationship curve in the coordinate area to obtain N*N squares, where N is any integer greater than 1; Determine the first value as the value corresponding to the square through which the relationship curve passes, and determine the second value as the value corresponding to the square through which the relationship curve does not pass; Connect each of the squares in order; The numerical values ​​corresponding to each of the spliced ​​squares are merged to obtain the corresponding first eigenvector.

8. A computer device, characterized in that: The invention comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the program, the method for determining the electromagnetic bearing clearance detection result as described in any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for determining the electromagnetic bearing clearance detection result as described in any one of claims 1 to 6 is implemented.

Images