CN115164702A

CN115164702A - Method and device for determining electromagnetic bearing gap detection result and computer equipment

Info

Publication number: CN115164702A
Application number: CN202210698416.XA
Authority: CN
Inventors: 闫循石; 时振刚; 莫逆; 孙喆
Original assignee: Huaneng Nuclear Energy Technology Research Institute Co Ltd
Current assignee: Tsinghua University; Huaneng Group Technology Innovation Center Co Ltd; Huaneng Nuclear Energy Technology Research Institute Co Ltd
Priority date: 2022-06-20
Filing date: 2022-06-20
Publication date: 2022-10-11

Abstract

The disclosure provides a method and a device for determining a detection result of an electromagnetic bearing gap and computer equipment, and relates to the technical field of computers. The method comprises the following steps: acquiring a corresponding relation curve between a current difference value and displacement of the electromagnetic bearing in a primary gap detection process; processing the relation curve to obtain a first feature vector; inputting the first feature vector into a trained gap detection classification model to determine a first classification result corresponding to the first feature vector; and determining whether the gap detection corresponding to the relation curve is effective or not according to the first classification result. Therefore, the relation curve between the current difference value and the displacement in the gap detection process is processed to obtain the first characteristic vector, then the trained gap detection classification model is utilized, the corresponding first classification result can be obtained, and whether the gap detection is effective or not can be determined.

Description

Method and device for determining electromagnetic bearing gap detection result and computer equipment

Technical Field

The present disclosure relates to the field of computer technologies, and in particular, to a method and an apparatus for determining a gap detection result of an electromagnetic bearing, and a computer device.

Background

Bearings are essential parts essential for the mechanical industry, in particular for rotary machines. The development of the modern mechanical industry has put many newer, higher demands on bearings under many operating conditions and in special situations, which conventional bearings have been difficult or impossible to meet. This has prompted the study of many new types of slewing bearings, of which electromagnetic bearings are the more successful ones.

The electromagnetic bearing is a novel and high-performance supporting part or bearing which utilizes magnetic field force, namely electromagnetic force to stably suspend a rotor in space without mechanical contact and the position of an axis can be controlled by a control system. The electromagnetic bearing has many incomparable advantages compared with the traditional bearing, such as no contact, no friction, no abrasion, no lubrication, high precision, long service life and the like, so that the application range of the electromagnetic bearing is wider and wider, for example, the electromagnetic bearing can be used in equipment supported by the magnetic bearing, such as a high-temperature gas-cooled reactor helium circulator, a helium compressor and the like.

Generally, in the process of detecting the gap of the electromagnetic bearing, manual detection is usually required, a lot of time may be required, and the efficiency is not high. Therefore, how to improve the gap detection efficiency of the electromagnetic bearing is very important.

Disclosure of Invention

The present disclosure is directed to solving, at least to some extent, one of the technical problems in the related art.

An embodiment of a first aspect of the present disclosure provides a method for determining a gap detection result of an electromagnetic bearing, including:

acquiring a corresponding relation curve between a current difference value and displacement of the electromagnetic bearing in a primary gap detection process;

processing the relation curve to obtain a first feature vector;

inputting the first feature vector into a trained gap detection classification model to determine a first classification result corresponding to the first feature vector;

and determining whether the gap detection corresponding to the relation curve is effective or not according to the first classification result.

Optionally, the processing the relationship curve to obtain a first feature vector includes:

dividing the relation curve in a coordinate region to obtain N × N grids, wherein N is any integer greater than 1;

determining a first numerical value as a numerical value corresponding to a square grid passed by the relation curve and determining a second numerical value as a numerical value corresponding to a square grid not passed by the relation curve;

splicing each square grid in sequence;

and fusing the numerical values corresponding to each spliced square to obtain a corresponding first feature vector.

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

determining that the gap detection corresponding to the relation curve is effective under the condition that the first classification result is normal;

and under the condition that the first classification result is abnormal, determining that the gap detection result corresponding to the relation curve is invalid.

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

performing gap detection on the electromagnetic bearing for M times to determine M second classification results corresponding to the gap detection for M times, wherein M is any integer greater than or equal to 1;

and when all the M second classification results are abnormal, performing abnormity prompting.

Optionally, 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:

performing gap detection on the electromagnetic bearing for M times based on at least one current value to obtain M second classification results; alternatively, the first and second liquid crystal display panels may be,

and performing gap detection on the electromagnetic bearing for M times based on at least one channel to obtain M second classification results.

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

obtaining a historical relationship curve set between a current difference value and displacement corresponding to at least one electromagnetic bearing of the same type, wherein the historical relationship curve set comprises a plurality of historical relationship curves and corresponding label labels;

processing each historical relationship curve to obtain a second feature vector corresponding to each historical relationship curve;

inputting each second feature vector into an initial model to determine a prediction label corresponding to each second feature vector;

determining a loss value based on the difference between the prediction label and the labeling label corresponding to each second feature vector;

and correcting the initial model based on the loss value to obtain a trained gap detection classification model.

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

and under the condition that the number of the first historical relationship curves marked with abnormal types is smaller than a first threshold value, modifying the second historical relationship curve marked with normal types to generate a new third historical relationship curve, wherein the marking labels of the first historical relationship curve and the third relationship curve are abnormal types.

An embodiment of a second aspect of the present disclosure provides an apparatus for determining a gap detection result of an electromagnetic bearing, including:

the acquisition module is used for acquiring a corresponding relation curve between a current difference value and displacement of the electromagnetic bearing in the primary gap detection process;

the processing module is used for processing the relation curve to obtain a first feature vector;

the first determining module is used for inputting the first feature vector into a trained gap detection classification model so as to determine a first classification result corresponding to the first feature vector;

and the second determining module is used for determining whether the gap detection corresponding to the relation curve is effective or not according to the first classification result.

Optionally, the processing module is specifically configured to:

dividing the relation curve in a coordinate area to obtain N × N grids, wherein N is any integer larger than 1;

splicing each square grid in sequence;

Optionally, the second determining module is specifically configured to:

Optionally, the second determining module includes:

the detection unit is used for carrying out gap detection on the electromagnetic bearing for M times so as to determine M second classification results corresponding to the gap detection for M times, wherein M is any integer greater than or equal to 1;

and the prompting unit is used for performing exception prompting under the condition that all the M second classification results are abnormal.

Optionally, the detection unit is specifically configured to:

Optionally, the first determining module includes:

the device comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring a historical relationship curve set between a current difference value and displacement corresponding to at least one electromagnetic bearing of the same type, and the historical relationship curve set comprises a plurality of historical relationship curves and corresponding label labels;

the processing unit is used for processing each historical relationship curve to obtain a second feature vector corresponding to each historical relationship curve;

a first determining unit, configured to input each second feature vector into an initial model to determine a prediction tag corresponding to each second feature vector;

a second determining unit, configured to determine a loss value based on a difference between the prediction tag and the annotation tag corresponding to each second feature vector;

and the correcting unit is used for correcting the initial model based on the loss value so as to obtain a trained gap detection classification model.

Optionally, the obtaining unit is specifically configured to:

An embodiment of a third aspect of the present disclosure provides a computer device, including: the present disclosure relates to a device for determining a clearance detection result of an electromagnetic bearing, and more particularly, to a device for determining a clearance detection result of an electromagnetic bearing, which is configured to detect a clearance of an electromagnetic bearing, and a method for determining a clearance detection result of an electromagnetic bearing.

A fourth aspect of the present disclosure provides a non-transitory computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the computer program implements the method for determining the electromagnetic bearing gap detection result as set forth in the first aspect of the present disclosure.

A fifth aspect of the present disclosure provides a computer program product, which when executed by an instruction processor performs the method for determining the electromagnetic bearing gap detection result provided in the first aspect of the present disclosure.

According to the method, the device, the computer equipment and the storage medium for determining the electromagnetic bearing gap detection result, a relation curve between a current difference value and displacement corresponding to an electromagnetic bearing in a gap detection process can be obtained first, then the relation curve can be processed to obtain a first feature vector, then the first feature vector can be input into a gap detection classification model after training is completed to determine a first classification result corresponding to the first feature vector, and then whether gap detection corresponding to the relation curve is effective or not can be determined according to the first classification result. Therefore, the relation curve between the current difference value and the displacement in the gap detection process is processed to obtain the first characteristic vector, then the trained gap detection classification model is utilized, the corresponding first classification result can be obtained, and whether the gap detection is effective or not can be determined. Additional aspects and advantages of the disclosure will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the disclosure.

Drawings

The above and/or additional aspects and advantages of the present disclosure will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:

fig. 1 is a schematic flowchart illustrating a method for determining a clearance detection result of an electromagnetic bearing according to an embodiment of the present disclosure;

fig. 1A is a schematic diagram illustrating a relationship curve between a current difference Δ I and a displacement x for gap detection of an electromagnetic bearing according to an embodiment of the present disclosure;

fig. 1B is a schematic diagram of a relationship curve subjected to a grid division process according to an embodiment of the disclosure;

fig. 1C is a schematic diagram of a numerical representation corresponding to each square provided in an embodiment of the present disclosure;

fig. 2 is a schematic flowchart of a method for determining a clearance detection result of an electromagnetic bearing according to another embodiment of the present disclosure;

fig. 3 is a schematic flowchart of a method for determining a clearance detection result of an electromagnetic bearing according to another embodiment of the present disclosure;

FIG. 3A is a schematic diagram of a process for determining a clearance measurement of an electromagnetic bearing according to another embodiment of the present disclosure;

fig. 4 is a schematic structural diagram of an apparatus for determining an electromagnetic bearing gap detection result according to an embodiment of the present disclosure;

FIG. 5 illustrates a block diagram of an exemplary computer device suitable for use to implement embodiments of the present disclosure.

Detailed Description

Reference will now be made in detail to the embodiments of the present disclosure, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the drawings are exemplary and intended to be illustrative of the present disclosure, and should not be construed as limiting the present disclosure.

A method, an apparatus, a computer device, and a storage medium for determining an electromagnetic bearing gap detection result according to embodiments of the present disclosure are described below with reference to the accompanying drawings.

The embodiments of the present disclosure exemplify that the method for determining the electromagnetic bearing gap detection result is configured in the apparatus for determining the electromagnetic bearing gap detection result, and the apparatus for determining the electromagnetic bearing gap detection result may be applied to any computer device, so that the computer device may perform the function of determining the electromagnetic bearing gap detection result.

The Computer device may be a Personal Computer (PC), a cloud device, a mobile device, and the like, and the mobile device may be a hardware device having various operating systems, touch screens, and/or display screens, such as a mobile phone, a tablet Computer, a Personal digital assistant, a wearable device, and an in-vehicle device.

Fig. 1 is a schematic flowchart of a method for determining a clearance detection result of an electromagnetic bearing according to an embodiment of the present disclosure.

As shown in fig. 1, the method for determining the electromagnetic bearing gap detection result may include the following steps:

step 101, obtaining a relation curve between a current difference value and displacement corresponding to the electromagnetic bearing in a primary gap detection process.

The electromagnetic bearing may be provided with a displacement sensor, and the rotor position is constantly moved by applying a current value I to the electromagnetic bearing, so that a corresponding relationship between a position x between the rotor and a 1 st contact point of the auxiliary bearing in the electromagnetic bearing and a current difference Δ I, that is, a relationship curve between the current difference and the displacement, and the like, may be obtained in the moving process of the rotor, which is not limited in the present disclosure.

The current difference Δ I may be understood as a difference between the current value I and the current real-time current value when the rotor is at different positions.

And 102, processing the relation curve to obtain a first feature vector.

Optionally, the relationship curve between the current difference and the displacement may be divided in the coordinate region to obtain N × N squares, then a first value may be determined as a value corresponding to a square through which the relationship curve passes, a second value may be determined as a value corresponding to a square through which the relationship curve does not pass, and each square is spliced in sequence, and then the values corresponding to each spliced square are fused to obtain a corresponding first feature vector.

Wherein, N can be any integer greater than 1; it may be a preset value, such as 6, 10, 20, etc., or may be adjusted according to the requirement, etc.; the present disclosure is not limited thereto.

In addition, there may be a plurality of ways to fuse the values corresponding to each square, for example, the values corresponding to each square may be spliced in rows, or may also be spliced in columns, or may also be fused in any other desirable way, and the like, which is not limited in this disclosure.

For example, if a relationship curve between the current difference Δ I and the displacement x detected in a certain time of the electromagnetic bearing gap is as shown in fig. 1A, when the value of N is 21, the relationship curve may be divided into squares in a coordinate region to obtain 21 × 21 squares as shown in fig. 1B. Then, the value corresponding to the square grid through which the relationship curve passes can be determined as 1, such as the black square grid in fig. 1C; the value corresponding to the square not passed by the relation curve is determined as 0, such as the white square in fig. 1C. Then, each square grid may be expanded according to the position of the square grid, for example, all the square grids may be spliced according to rows, and the numerical values corresponding to each square grid are spliced in sequence, that is, the first feature vector is obtained.

Optionally, a relationship curve between the current difference and the displacement may be analyzed to determine a minimum current difference and a maximum current difference, then the relationship curve may be divided into three sub-relationship curves according to the minimum current difference and the maximum current difference, then a corresponding proportion value of each sub-relationship curve in the relationship curve may be determined according to a length of each sub-relationship curve, and then each proportion value may be spliced to obtain the first feature vector, and the like, which is not limited by the present disclosure.

Step 103, 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 gap detection classification model may be a model trained in advance, for example, the trained gap detection classification model may be obtained by training any initial model, and the disclosure does not limit this.

In addition, the first classification result may be various, such as may be normal, or may also be abnormal, etc., and this disclosure does not limit this.

It can be understood that, in the embodiment of the present disclosure, the first feature vector may be input into the trained gap detection classification model, and through the processing of the gap detection classification model, the first classification result corresponding to the first feature vector may be determined.

And step 104, determining whether the gap detection corresponding to the relation curve is effective or not according to the first classification result.

It is understood that, since the first classification result is various, when the first classification result is different, the gap detection corresponding to the general relationship curve may also be different, and the disclosure does not limit this.

Optionally, when the first classification result is normal, it may be determined that the gap detection corresponding to the relationship curve is valid; and under the condition that the first classification result is abnormal, determining that the gap detection result corresponding to the relation curve is invalid.

Therefore, in the embodiment of the disclosure, based on the first feature vector corresponding to the relation curve between the current difference value and the displacement, the corresponding first classification result can be determined more accurately by combining the gap detection classification model completed by training, and then whether the gap detection is effective or not can be determined according to the first classification result.

According to the embodiment of the disclosure, a relationship curve between a current difference value and a displacement corresponding to an electromagnetic bearing in a gap detection process can be obtained first, then the relationship curve can be processed to obtain a first feature vector, then the first feature vector can be input into a trained gap detection classification model to determine a first classification result corresponding to the first feature vector, and then whether gap detection corresponding to the relationship curve is effective or not can be determined according to the first classification result. Therefore, the relation curve between the current difference value and the displacement in the gap detection process is processed to obtain the first characteristic vector, then the trained gap detection classification model is utilized, the corresponding first classification result can be obtained, and whether the gap detection validity is valid or not can be determined.

Fig. 2 is a schematic flowchart of a method for determining a clearance detection result of an electromagnetic bearing according to an embodiment of the present disclosure.

As shown in fig. 2, the method for determining the electromagnetic bearing gap detection result may include the following steps:

step 201, obtaining a corresponding current difference value and displacement relation curve of the electromagnetic bearing in a primary gap detection process.

Step 202, the relationship curve is processed to obtain a first feature vector.

Step 203, inputting the first feature vector into the trained gap detection classification model to determine a first classification result corresponding to the first feature vector.

And 204, determining that the gap detection corresponding to the relation curve is effective under the condition that the first classification result is normal.

In step 205, when the first classification result is abnormal, it is determined that the gap detection result corresponding to the relationship curve is invalid.

It should be noted that specific contents and implementation manners of step 201 to step 205 may refer to descriptions of other embodiments of the disclosure, and are not described herein again.

And step 206, under the condition that the gap detection result corresponding to the relation curve is determined to be invalid, performing gap detection on the electromagnetic bearing for M times to determine M second classification results corresponding to the gap detection for M times, wherein M is any integer greater than or equal to 1.

Where M may be any value set in advance, for example, it may be 3, 5, 10, etc., which is not limited in this disclosure.

For example, if it is determined that the gap detection result corresponding to the relationship curve is invalid when the value of M is 3, gap detection may be continuously and repeatedly performed on the electromagnetic bearing for 3 times at this time to obtain second classification results respectively corresponding to the 3 times of gap detection, that is, 3 second classification results.

For example, for the gap detection 1, a relationship curve between the corresponding current difference and the displacement may be obtained first, then the relationship curve is processed to obtain a corresponding first feature vector, and then the first feature vector is input into the trained gap detection classification model to determine a corresponding second classification result 1, thereby determining whether the gap detection corresponding to the relationship curve is valid or not. 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 is not described herein again.

It should be noted that the above examples are only illustrative, and cannot be taken as limitations on the values, the manner of determining the second classification result, and the like of the embodiment M of the present disclosure.

Optionally, gap detection may be performed on the electromagnetic bearing M times based on the at least one current value to obtain M second classification results.

The electromagnetic bearing can be subjected to gap detection for M times repeatedly by adopting the same current value so as to obtain M second classification results; or, the gap detection may be repeated M times for the electromagnetic bearing by using different current values, so as to obtain M second classification results, and the like, which is not limited by the present disclosure.

Optionally, gap detection may be performed on the electromagnetic bearing for M times based on the at least one channel, so as to obtain M second classification results.

It is understood that, in general, a plurality of stator coils are included in the electromagnetic bearing, each stator coil may correspond to a respective channel, and gap detection may be performed on the electromagnetic bearing M times based on the same channel to obtain M second classification results. Alternatively, different channels may be used instead, and the gap detection may be performed M times on the electromagnetic bearing to obtain M second classification results, and the like, which is not limited in this disclosure.

Therefore, in the embodiment of the present disclosure, under the condition that the gap detection result corresponding to the relationship curve is determined to be invalid, M times of gap detection may be performed on the electromagnetic bearing to determine M second classification results corresponding to the M times of gap detection, thereby avoiding manual rechecking operation upon occurrence of an abnormality in gap detection of the electromagnetic bearing, reducing manual operation, saving time, and providing conditions for automation of gap detection of the electromagnetic bearing.

And step 207, performing exception prompting when all the M second classification results are abnormal.

It can be understood that, if all the M second classification results are abnormal, it may indicate that there may be a fault in the electromagnetic bearing, for example, there may be a mechanical fault in the electromagnetic bearing, and at this time, an abnormal prompt may be performed to notify a user that the electromagnetic bearing may need to be replaced or repaired. If the electromagnetic bearing is a certain component in the high-temperature gas-cooled reactor main helium fan, conditions are provided for ensuring the safety and the reliability of the high-temperature gas-cooled reactor main helium fan by carrying out exception prompting.

In addition, there are various abnormal prompting modes, such as displaying on a display interface of the associated terminal device; or the information can be sent to the associated terminal equipment in the forms of mails and notifications; or voice broadcast and the like can also be performed through a loudspeaker, which is not limited by the disclosure.

Optionally, when at least one of the M second classification results is normal, it may be determined that the gap detection corresponding to the electromagnetic bearing is valid.

For example, if all the 3 second classification results are normal, it may be determined that the gap detection corresponding to the electromagnetic bearing is valid; or if one of the 3 second classification results is normal, determining that the gap detection corresponding to the electromagnetic bearing is effective; or 2 of the 3 second classification results are normal, it may be determined that the gap detection corresponding to the electromagnetic bearing is valid, and the like, which is not limited by the present disclosure.

According to the embodiment of the disclosure, a relation curve between a current difference value and a displacement corresponding to an electromagnetic bearing in a gap detection process can be obtained first, then the relation curve can be processed to obtain a first feature vector, then the first feature vector can be input into a trained gap detection classification model to determine a first classification result corresponding to the first feature vector, then according to the first classification result, whether gap detection corresponding to the relation curve is valid or not can be determined, under the condition that the gap detection result corresponding to the relation curve is determined to be invalid, gap detection can be performed on the electromagnetic bearing for M times to determine M second classification results corresponding to the M times of gap detection, and under the condition that the M second classification results are all abnormal, an abnormal prompt is performed. From this, based on the first eigenvector that the relation curve between current difference and displacement corresponds, combine the clearance detection classification model that the training was accomplished, can comparatively accurate confirm the first classification result that corresponds, and then according to this first classification result, can confirm whether effective that the clearance detects, under the invalid condition of clearance detection, can repeat many times and detect to confirm whether this electromagnetic bearing breaks down, this process need not manual operation, the time is saved, the efficiency is improved, the automation that also provides the condition for electromagnetic bearing clearance detection.

It can be understood that the initial model may be trained in advance to obtain a trained gap detection classification model, so that the trained gap detection classification model may be directly used in the gap detection process of the electromagnetic bearing, and the training process of the gap detection classification model is described below with reference to fig. 3.

Fig. 3 is a schematic flowchart of a method for determining a gap detection result of an electromagnetic bearing according to an embodiment of the disclosure.

As shown in fig. 3, the method for determining the electromagnetic bearing gap detection result may include the following steps:

step 301, obtaining a historical relationship curve set between a current difference value and a displacement corresponding to at least one electromagnetic bearing of the same type, wherein the historical relationship curve set comprises a plurality of historical relationship curves and corresponding label labels.

Since the electromagnetic bearings are different in size, weight, and the like, the types of the electromagnetic bearings may also be different, and thus the corresponding current values may also be different. Therefore, in the embodiment of the disclosure, a historical relationship curve set between the current difference and the displacement corresponding to the electromagnetic bearings of the same type can be obtained.

For example, there are a plurality of electromagnetic bearings corresponding to the type 1, which are the electromagnetic bearing 1 and the electromagnetic bearing 2, so that one or more historical relationship curves and corresponding labels corresponding to the electromagnetic bearing 1 and one or more historical relationship curves and corresponding labels corresponding to the electromagnetic bearing 2 can be obtained. Or, if the type 2 corresponds to only one electromagnetic bearing: the electromagnetic bearing 3 can then obtain a plurality of historical relationship curves and corresponding labels corresponding to the electromagnetic bearing 3.

It should be noted that the above examples are only illustrative and should not be taken as limiting the type, number, etc. of the electromagnetic bearings in the embodiments of the present disclosure.

It is understood 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 so on, which is not limited in this disclosure.

Optionally, when the number of the first historical relationship curves labeled as abnormal types is smaller than a first threshold, the second historical relationship curve labeled as normal types is modified to generate a new third historical relationship curve, where the labeling labels of the first historical relationship curve and the third relationship curve are both abnormal types.

The first threshold may be a preset value, such as 10, 100, and the like, which is not limited in this disclosure.

For example, in a case that the first threshold is 50, if only 20 first historical relationship curves are smaller than the first threshold 50, the second historical relationship curve may be modified, for example, the minimum current difference value in a certain second historical relationship curve is changed to be smaller, the changed curve is used as a new third historical relationship curve, and since the third historical relationship curve and the first historical relationship curve are both relationship curves corresponding to abnormal types, the number of the historical relationship curves labeled as abnormal types may be increased, so that the historical relationship curves in the historical relationship curve set may be more comprehensive and complete, and the like, which is not limited by the present disclosure.

Step 302, processing each historical relationship curve to obtain a second feature vector corresponding to each historical relationship curve.

The history relation curve can be divided in the coordinate area to obtain N × N grids, then the numerical value corresponding to the grid through which the history relation curve passes is determined as "1", the numerical value corresponding to the grid through which the history relation curve does not pass is determined as "0", then each grid can be spliced in sequence, and the numerical value corresponding to each spliced grid is fused to obtain a corresponding second feature vector, specific contents and implementation processes thereof can refer to descriptions of the first feature vector obtained in other embodiments of the present disclosure, and details are not repeated here.

Wherein, N may be any integer greater than 1, such as 10, 20, and so on. It is understood that, during the generation and use of the gap detection classification model, the value of N needs to be kept the same, which is not limited in this disclosure.

Step 303, inputting each second feature vector into the initial model to determine a prediction label corresponding to each second feature vector.

The initial model may be any model that can be classified, and the second feature vector is input into the initial model, and through processing of the initial model, the prediction label and the like corresponding to the second feature vector may be determined, which is not limited in this disclosure.

In addition, the prediction tag may be various, such as "normal" or "abnormal", and the disclosure does not limit this.

Step 304, determining a loss value based on the difference between the prediction label and the labeling label corresponding to each second feature vector.

For the same second feature vector, a loss function value between the prediction tag and the label tag may be determined according to a difference between the prediction tag and the label tag corresponding to the second feature vector, for example, through a loss function, and is used as a loss value, and the like, which is not limited in this disclosure.

For example, a cross entropy loss function can be used to determine a loss value between a prediction tag and a label; or a loss function corresponding to the support vector machine may also be used to determine a loss value between the prediction tag and the label tag, and the like, which is not limited in this disclosure.

And 305, correcting the initial model based on the loss value to obtain a trained gap detection classification model.

It is understood that after determining the initial loss value, the initial model may be modified based on the loss value such that the learning ability and performance of the initial model are improved, thereby obtaining a trained gap detection classification model. For example, the completion of the training of the gap detection classification model can be determined under the condition that the preset training step number is reached; or it may be determined that the training of the gap detection classification model is completed when a preset training period is reached, and the like, which is not limited by the present disclosure.

It can be understood that after the trained gap detection classification model is obtained, if the gap detection of the electromagnetic bearing is needed, the trained gap detection classification model can be directly used, so that the gap detection of the electromagnetic bearing is simplified, and the time is saved.

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

The following describes a process for determining the electromagnetic bearing gap detection result provided by the present disclosure with reference to fig. 3A.

First, the gap detection classification model may be trained offline. The offline training can collect curve samples firstly, namely historical relation curves corresponding to electromagnetic bearing gap detection are obtained firstly, then abnormal samples can be supplemented, namely the historical relation curves with abnormal labels are supplemented, then features can be extracted to obtain second feature vectors, and then the second feature vectors can be used for training a support vector machine to generate a gap detection classification model after training is completed.

And then online prediction can be carried out by using the trained detection classification model. For example, gap detection may be performed on a certain electromagnetic bearing, a relationship curve between a corresponding current difference and displacement is obtained, and then features may be extracted from the relationship curve to obtain a first feature vector. Then, inputting the first feature vector into the trained gap detection classification model to determine whether a first classification result corresponding to the first feature vector is normal, and under the normal condition, determining that the gap detection is finished; if abnormal, the gap detection can be continued for the electromagnetic bearing.

It should be noted that the above examples are only illustrative and should not be taken as a limitation to the determination process of the electromagnetic bearing gap detection result in the embodiment of the present disclosure.

According to the embodiment of the disclosure, a historical relationship curve set between a current difference value and a displacement corresponding to at least one electromagnetic bearing of the same type may be obtained first, where the historical relationship curve set includes a plurality of historical relationship curves and corresponding label labels, then each historical relationship curve may be processed to obtain a second feature vector corresponding to each historical relationship curve, then each second feature vector may be input into an initial model to determine a prediction label corresponding to each second feature vector, then a loss value is determined based on a difference between the prediction label corresponding to each second feature vector and the label, and then the initial model is corrected based on the loss value to obtain a trained gap detection classification model. Therefore, the initial model can be trained by utilizing the historical relationship curve set between the current difference value and the displacement corresponding to the electromagnetic bearing, the gap detection classification model after training can be obtained, then the gap detection classification model is utilized, the gap detection result of the electromagnetic bearing can be automatically determined, manual operation is not needed in the process, the time is saved, the efficiency is improved, and conditions are provided for automation of gap detection of the electromagnetic bearing.

In order to implement the above embodiments, the present disclosure further provides an apparatus for determining a gap detection result of an electromagnetic bearing.

Fig. 4 is a schematic structural diagram of an apparatus for determining an electromagnetic bearing gap detection result according to an embodiment of the present disclosure.

As shown in fig. 4, the apparatus 100 for determining the electromagnetic bearing gap detection result may include: an acquisition module 110, a processing module 120, a first determination module 130, and a second determination module 140.

The obtaining module 110 is configured to obtain a relationship curve between a current difference and a displacement corresponding to the electromagnetic bearing in a gap detection process.

The processing module 120 is configured to process the relationship curve to obtain a first feature vector.

A first determining module 130, configured to input the first feature vector into a trained gap detection classification model, so as to determine a first classification result corresponding to the first feature vector.

A second determining module 140, configured to determine whether gap detection corresponding to the relationship curve is valid according to the first classification result.

Optionally, the processing module 120 is specifically configured to:

determining a first numerical value as a numerical value corresponding to a square lattice passed by the relation curve and determining a second numerical value as a numerical value corresponding to a square lattice not passed by the relation curve;

splicing each square grid in sequence;

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

Optionally, the second determining module 140 includes:

Optionally, the detection unit is specifically configured to:

performing gap detection on the electromagnetic bearing for M times based on at least one current value to obtain M second classification results; alternatively, the first and second electrodes may be,

and performing M times of gap detection on the electromagnetic bearing based on at least one channel to obtain M second classification results.

Optionally, the first determining module 120 includes:

the device comprises an acquisition unit, a processing unit and a control unit, wherein the acquisition unit is used for acquiring a historical relationship curve set between a current difference value and displacement corresponding to at least one electromagnetic bearing of the same type, and the historical relationship curve set comprises a plurality of historical relationship curves and corresponding label labels;

a first determining unit, configured to input each second feature vector into an initial model to determine a prediction label corresponding to each second feature vector;

Optionally, the obtaining unit is specifically configured to:

and under the condition that the number of the first historical relationship curves with the abnormal labels is smaller than a first threshold value, modifying the second historical relationship curve with the normal labels 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 of abnormal types.

The functions and specific implementation principles of the above modules in the embodiments of the present disclosure may refer to the above method embodiments, which are not described herein again.

The device for determining the electromagnetic bearing gap detection result according to the embodiment of the disclosure may obtain a relationship curve between a current difference value and a displacement corresponding to the electromagnetic bearing in a gap detection process, process the relationship curve to obtain a first feature vector, input the first feature vector into a trained gap detection classification model to determine a first classification result corresponding to the first feature vector, and determine whether the gap detection corresponding to the relationship curve is effective according to the first classification result. Therefore, the relation curve between the current difference value and the displacement in the gap detection process is processed to obtain the first characteristic vector, then the trained gap detection classification model is utilized, the corresponding first classification result can be obtained, and whether the gap detection is effective or not can be determined.

In order to implement the foregoing embodiments, the present disclosure also provides a computer device, including: the present disclosure relates to a magnetic bearing gap detection device, and more particularly, to a magnetic bearing gap detection device, a magnetic bearing gap detection method, and a magnetic bearing gap detection method.

In order to achieve the above embodiments, the present disclosure further proposes a non-transitory 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 by the foregoing embodiments of the present disclosure.

In order to achieve the above embodiments, the present disclosure further proposes a computer program product, which when executed by an instruction processor in the computer program product, executes the method for determining the electromagnetic bearing gap detection result as proposed by the foregoing embodiments of the present disclosure.

FIG. 5 illustrates a block diagram of an exemplary computer device suitable for use in implementing embodiments of the present disclosure. The computer device 12 shown in fig. 5 is only one example and should not impose any limitations on the functionality or scope of use of embodiments of the present disclosure.

As shown in FIG. 5, computer device 12 is in the form of a general purpose computing device. The components of 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 couples various system components including the system memory 28 and the processing unit 16.

Bus 18 represents one or more of any of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures. By way of example, such 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 Interconnect (PCI) bus.

Computer device 12 typically includes a variety of computer system readable media. Such media may be any available media that is accessible by computer device 12 and includes both volatile and nonvolatile media, removable and non-removable media.

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. Computer device 12 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 34 may be used to read from and write to non-removable, nonvolatile magnetic media (not shown in FIG. 5, and commonly referred to as a "hard drive"). Although not shown in FIG. 5, a disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a Compact disk Read Only Memory (CD-ROM), a Digital versatile disk Read Only Memory (DVD-ROM), or other optical media) may be provided. In these cases, each drive may be connected to bus 18 by one or more data media interfaces. Memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the disclosure.

A program/utility 40 having a set (at least one) of program modules 42 may be stored, for example, in 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 of which may comprise an implementation of a network environment. Program modules 42 generally perform the functions and/or methodologies of the embodiments described in this disclosure.

Computer device 12 may also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), with one or more devices that enable a user to interact with computer device 12, and/or with any devices (e.g., network card, modem, etc.) that enable computer device 12 to communicate with one or more other computing devices. Such communication may be through an input/output (I/O) interface 22. Moreover, 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 Network adapter 20. As shown, network adapter 20 communicates with the other modules of computer device 12 via bus 18. It should be understood that although not shown in the figures, other hardware and/or software modules may be used in conjunction with 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, among others.

The processing unit 16 executes various functional applications and data processing, for example, implementing the methods mentioned in the foregoing embodiments, by running a program stored in the system memory 28.

According to the technical scheme, a relation curve between a current difference value and displacement corresponding to the electromagnetic bearing in the primary gap detection process can be obtained firstly, then the relation curve can be processed to obtain a first feature vector, then the first feature vector can be input into a trained gap detection classification model to determine a first classification result corresponding to the first feature vector, and then whether the gap detection corresponding to the relation curve is effective or not can be determined according to the first classification result. Therefore, the relation curve between the current difference value and the displacement in the gap detection process is processed to obtain the first characteristic vector, then the trained gap detection classification model is utilized, the corresponding first classification result can be obtained, and whether the gap detection is effective or not can be determined.

In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present disclosure. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Moreover, various embodiments or examples and features of various embodiments or examples described in this specification can be combined and combined by one skilled in the art without being mutually inconsistent.

Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the feature. In the description of the present disclosure, "a plurality" means at least two, e.g., two, three, etc., unless explicitly specifically limited otherwise.

Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing steps of a custom logic function or process, and alternate implementations are included within the scope of the preferred embodiment of the present disclosure in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the embodiments of the present disclosure.

The logic and/or steps represented in the flowcharts or otherwise described herein, such as an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Further, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.

It should be understood that portions of the present disclosure may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.

It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.

In addition, functional units in the embodiments of the present disclosure may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium.

The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc. While embodiments of the present disclosure have been shown and described above, it will be understood that the above embodiments are exemplary and not to be construed as limiting the present disclosure, and that changes, modifications, substitutions and alterations may be made to the above embodiments by those of ordinary skill in the art within the scope of the present disclosure.

Claims

1. A method for determining a clearance detection result of an electromagnetic bearing is characterized by comprising the following steps:

processing the relation curve to obtain a first feature vector;

2. The method of claim 1, wherein processing the relationship curve to obtain a first feature vector comprises:

splicing each square grid in sequence;

3. The method of claim 1, wherein said determining whether gap detection corresponding to the relationship curve is valid according to the first classification result comprises:

4. The method of claim 3, wherein after said determining that the gap detection result for the relationship curve is invalid, further comprising:

5. The method of claim 4, wherein said performing M gap checks on the electromagnetic bearing to determine M second classification results corresponding to the M gap checks comprises:

6. The method of claim 1, wherein before the inputting the first feature vector into a trained gap detection classification model to determine a first classification result corresponding to the first feature vector, further comprising:

acquiring a historical relationship curve set between a current difference value and displacement corresponding to at least one electromagnetic bearing of the same type, wherein the historical relationship curve set comprises a plurality of historical relationship curves and corresponding label labels;

7. The method of claim 6, wherein obtaining a set of historical relationship curves between current difference values and displacements for at least one electromagnetic bearing of the same type comprises:

8. An apparatus for determining a clearance measurement result of an electromagnetic bearing, comprising:

9. A computer arrangement comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor when executing the program performing the method of determining a result of a gap detection for an electromagnetic bearing according to any of claims 1-7.

10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the method for determining an electromagnetic bearing gap detection result according to any one of claims 1 to 7.