Motor Detection Data Acquisition Method and System Based on Simulation Environment

Abstract

The present invention relates to the field of data processing, and particularly to a method and system for collecting motor detection data based on a simulation environment. Motor detection data is collected at a preset collection frequency, and by preprocessing the collected motor detection data, the local reachability density of the motor detection data is obtained. Further, an adjustment factor for the data collection frequency is calculated according to the local reachability density of the motor detection data, and the collection frequency of the motor detection data is adjusted according to the adjustment factor to perform the next round of collection of the motor detection data, so as to realize the adaptive adjustment of the collection frequency of the motor detection data according to the degree of abnormality of the motor detection data.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and particularly to a method and system for collecting motor detection data based on a simulation environment. Background Art

[0002] In modern industry, motors, as key driving devices, are applied in various fields such as manufacturing, transportation, and energy. With the rapid development of industrial automation, the requirements for the reliability, efficiency, and fault diagnosis of motor performance are increasing day by day.

[0003] During the process of collecting motor detection data, higher attention is paid to the data that may be abnormal, and more detailed data collection is required. During the process of collecting motor detection data, the fixed data collection frequency often cannot meet the data collection requirements. Collecting detection data through a high collection frequency will consume a large amount of additional computing power when collecting relatively stable normal data, while a low collection frequency will result in the inability to fully obtain the change situation of the abnormal data that is the focus of attention, leading to deviations in the analysis of motor detection data.

[0004] For example, the Chinese patent application document with the publication number CN114966396A discloses a motor data collection device, which is connected to a motor through data collection modules such as a motor three-phase current collection module, a motor vibration data collection module, a motor temperature collection module, and a motor analog quantity collection module to collect motor data such as current data, vibration data, and temperature data. However, due to the lack of an efficient and reasonable data collection method, the collected data cannot effectively reflect the operating conditions of the motor, and it is difficult to timely detect abnormalities in the motor operation. Summary of the Invention

[0005] In view of the problem that the above-collected data cannot effectively reflect the operating conditions of the motor and it is difficult to timely detect abnormalities in the motor operation, in the first aspect, the present invention proposes a method for collecting motor detection data based on a simulation environment, including the following steps: collecting a number of motor detection data, and calculating the local reachability density of the collected motor detection data through the LOF algorithm; calculating an adjustment factor for the data collection frequency according to the local reachability density, and the specific calculation method of the adjustment factor is:

[0006] ;

[0007] wherein, A i represents the adjustment factor of the i-th data point, P i represents the density abnormality degree of the i-th data point, and the density abnormality degree is restricted by the local reachability density and distance of the i-th data point and its surrounding data points, F irepresents the local fluctuation degree of the i-th data point, and the local fluctuation degree is positively correlated with the change degree between the value of the i-th data point and the values of multiple surrounding data points, T P represents a preset density anomaly threshold, T F represents a preset local fluctuation degree threshold; adjust the acquisition frequency of the motor detection data according to the adjustment factor to perform the next round of acquisition of the motor detection data.

[0008] Calculate the local reachability density of the collected motor detection data through the LOF algorithm, and then the anomaly degree of each data point can be quantified according to the local reachability density, so as to adaptively adjust the acquisition frequency. This method has higher sensitivity to abnormal data, can adaptively increase the acquisition frequency of abnormal data, and reduce the acquisition frequency of normal data, thereby improving the acquisition efficiency.

[0009] Furthermore, collect a number of motor detection data, including: collect more than two of the following signals: rotational speed, temperature, current, voltage.

[0010] By collecting more than two signals, it is possible to prevent detection errors caused by collecting only one signal.

[0011] Furthermore, the specific calculation method of the density anomaly degree is as follows:

[0012] ;

[0013] where P i represents the density anomaly degree of the i-th data point, C i represents the number of all other data points within the local reachability distance of the i-th data point, exp( ) represents the natural exponential function, I k represents the gap in the data acquisition time sequence, ρ i,k represents the local reachability density of the k-th data point among multiple data points around the i-th data point, d(i,k) represents the distance between the k-th data point and the i-th data point, represents the average value of the local reachability densities of other data points within the local reachability distance of the i-th data point, represents the average value of the distances between the i-th data point and other data points within the local reachability distance.

[0014] By calculating data such as the local reachability density of the collected motor detection data and the distances between data points, the density anomaly degree can be quantified to calculate the adjustment factor. The exp(-I k ) term in the formula takes into account the gap in the data acquisition time sequence, which means that this method can consider the change trend of data points over time, so as to more accurately identify abnormal points.

[0015] Further, the distance metric between the data points is configured as one or more of the following: Euclidean distance, Manhattan distance, and Mahalanobis distance.

[0016] When the number of data items included in the data points is too large, it is difficult to directly measure the distance between data points with multiple items using conventional distance metrics. For example, when the data points include four items of data: rotational speed, temperature, current, and voltage, it is no longer possible to calculate the relative distance between the data points using conventional two-dimensional or three-dimensional distance metrics. By selecting a suitable distance metric (such as Euclidean distance), the relative distance between multi-dimensional data points can be calculated.

[0017] Further, the specific calculation method of the local fluctuation degree is as follows:

[0018] ;

[0019] where F i represents the local fluctuation degree of the i-th data point, N represents the number of data items included in each data point, K represents the number of other data points within the neighborhood of each data point, represents the difference in acquisition time between the i-th data point and the k-th data point among multiple surrounding data points, and D j (i, k) represents the j-th item of data of the k-th data point among multiple surrounding data points of the i-th data point, represents the average value of the j-th item of data of all data points among multiple surrounding data points of the i-th data point, represents the standard deviation of the j-th item of data of all data points among multiple surrounding data points of the i-th data point.

[0020] Further, adjusting the acquisition frequency of the motor detection data according to the adjustment factor includes: taking the average of several adjustment factors calculated from several motor detection data collected in this round, and multiplying the average value by the acquisition frequency of this round as the acquisition frequency of the motor detection data in the next round.

[0021] By taking the average of the adjustment factors of multiple data points, the change situation of the overall data can be comprehensively considered, avoiding errors in the calculated adjustment factors due to errors in individual data. By taking the average value, a more reasonable sampling frequency can be obtained.

[0022] Further, taking the average of several adjustment factors calculated from several motor detection data collected in this round includes: taking the average of several adjustment factors calculated from several motor detection data within a preset time period, or taking the average of several adjustment factors calculated from several motor detection data for a preset number of times.

[0023] Further, the calculation of the local reachability density includes setting a K value, where the K value represents the number of neighboring data points considered when calculating the local reachability density, and the K value is set to 10.

[0024] By setting a reasonable K value, the data calculation amount and calculation efficiency can be balanced, avoiding excessive calculation amount due to too large K value affecting the calculation efficiency, and avoiding unrepresentative calculation results due to too small K value. Setting a reasonable K value can efficiently and reasonably calculate the local reachability density of the motor detection data.

[0025] Further, the method for collecting motor detection data based on the simulation environment further includes filtering, amplifying, and analog-to-digital conversion operations on the collected motor detection data to convert the collected analog data signal into a digital signal suitable for analysis and processing.

[0026] In a second aspect, a system for collecting motor detection data based on the simulation environment is provided, including a collection device and a controller. The controller includes a processor and a memory, and the memory stores computer program instructions. When the computer program instructions are executed by the processor, the method for collecting motor detection data based on the simulation environment of the present invention is implemented.

[0027] The technical effects of the present invention are as follows:

[0028] The motor detection data is collected through a preset collection frequency, and the local reachability density of the motor detection data is obtained by preprocessing the collected motor detection data. Further, an adjustment factor for the data collection frequency is calculated based on the local reachability density of the motor detection data, and the collection frequency of the motor detection data is adjusted according to the adjustment factor to perform the next round of collection of the motor detection data, thereby realizing the adaptive adjustment of the collection frequency of the motor detection data according to the abnormality degree of the motor detection data. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features, and advantages of the exemplary embodiments of the present invention will become readily understood. In the drawings, several embodiments of the present invention are shown in an exemplary rather than restrictive manner, and the same or corresponding reference numerals represent the same or corresponding parts, where:

[0030] Figure 1 is a flowchart of the method for collecting motor detection data based on the simulation environment in an embodiment of the present invention shown schematically;

[0031] Figure 2 is a block diagram of the structure of the system for collecting motor detection data based on the simulation environment in an embodiment of the present invention shown schematically. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0032] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts shall fall within the protection scope of the present invention.

[0033] The specific embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings.

[0034] Embodiment of the motor detection data acquisition method:

[0035] As Figure 1 shown, the motor detection data acquisition method based on a simulation environment of the present invention includes:

[0036] S1. Collect motor detection data and preprocess the motor detection data to obtain the local reachability density of the motor detection data.

[0037] As an important power device in industrial production, the operating state of the motor is the key detection object in the production process. Usually, the performance of the motor is monitored, fault diagnosed, or predictive maintenance is performed by detecting the operating parameters of the motor. Among them, common parameters include speed, temperature, current, voltage, etc. Select corresponding sensors according to the parameters to be detected, such as temperature sensors, vibration sensors, current sensors, etc. During the operation of the motor, the initial acquisition frequency of the motor detection data can be preset. For example, the initial acquisition frequency is 1 time per hour, and a data acquisition system is used to collect sensor signals. In some cases, operations such as filtering, amplifying, and analog-to-digital conversion of the collected motor detection data (for example, the sensor outputs an analog signal) are also required to make it into a form suitable for analysis and processing.

[0038] Further, in order to obtain the local reachability density of the motor detection data, the collected motor detection data is preprocessed by the LOF (Local Outlier Factor) algorithm.

[0039] In the present invention, each piece of data collected each time is called a data point, and the set of data points collected in each round is called a data set. For example, in this embodiment, 24 data points are collected in each round, and the 24 data points form the data set collected in this round.

[0040] A K value for the local reachability density is preset for each data point. The K value refers to the number of neighbor points of the data point considered when calculating the local reachability density. The neighbor points refer to a set of points that are closest to a specific data point under a given distance metric. For example, if the K value is preset to 5, it means that under a given distance metric, the distances between a specific data point and other data points are calculated, and the 5 data points with the smallest distance values are selected. The K value can be preset to 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 or other values. Preferably, the K value is preset to 10.

[0041] Further, the local reachability density of each data point in the dataset is obtained. The local reachability density refers to the reciprocal of the average reachable distance from the data point to its neighbor points. In one embodiment, the K value is preset to 10, the first-round collection frequency is 1 time per hour, one data point is collected each time, and 24 times are collected in each round.

[0042] In this embodiment, after the collection of the 24 motor detection data points in the first round is completed, one of the data points is selected as a specific data point (for example, the first data point is selected), and the local reachability density of this data point is calculated, that is, the reciprocal of the average reachable distance between this data point and its 10 neighbor data points (the K value is preset to 10). In this embodiment, the Euclidean distance is selected as the distance metric. In other embodiments, other distance metrics such as the Manhattan distance and the Mahalanobis distance can also be selected. The present invention does not limit this. Similarly, the local reachability densities of the remaining 23 data points in the dataset can be calculated.

[0043] In the embodiment of the present invention, the collected data points include two or more signals of the motor rotation speed, temperature, current, and voltage. That is, one data point includes two or more items of data.

[0044] S2. Calculate an adjustment factor for the data collection frequency according to the local reachability density of the motor detection data.

[0045] In one embodiment, the calculation formula for the adjustment factor is:

[0046] ;

[0047] where, A i represents the adjustment factor of the i-th data point, P i represents the density abnormality degree of the i-th data point. The density abnormality degree is restricted by the local reachability density and distance of the i-th data point and its surrounding data points. F i represents the local fluctuation degree of the i-th data point. The local fluctuation degree is positively correlated with the change degree between the value of the i-th data point and the values of multiple surrounding data points. T P represents a preset density abnormality threshold, T FRepresents a preset local fluctuation degree threshold.

[0048] For any data point, obtain the density tendency degree of the data point according to its local reachability density and the local reachability densities of other surrounding data, and judge the outlier degree of the data point according to the density tendency degree of the data point.

[0049] The specific calculation process of the density anomaly degree is as follows: Obtain all other data points within the local reachability distance of the i-th data point. The local reachability distance represents the distance between the i-th data point and the K-th farthest data point from it (for example, when the value of K is 10, take the distance between the i-th data point in the data set and the 10th farthest data point from the i-th data point as the local reachability distance), and record the number of all other data points within the local reachability distance as C i (for example, when the value of K is 10, within the local reachability distance of the -th data point in the data set, there are at least 10 data points. If there is 1 more data point outside these 10 data points whose distance is exactly equal to the local reachability distance, then C i is equal to 11). Sort all the other data points according to the Euclidean distance from the i-th data point, and obtain the Euclidean distance between the k-th data point and the i-th data point and record it as d(i,k). The local reachability density of the k-th data point (for example, when the value of K is 10, k represents the serial number of these 10 data points, that is, the range of k is 1 to 10) is recorded as ρ i,k , and record the difference in the data collection time series between the k-th data point and the i-th data point as I k (for example, the collection time of the k-th data point is 09:00, the collection time of the i-th data point is 12:00, and the time series difference is 3, then I k is 3). The above data is used to reflect the distribution of the local reachability densities of the data points within the local reachability distance of the i-th data point, and then calculate the density anomaly degree P i of the i-th data point. In this embodiment, the density anomaly degree P i of the i-th data point is calculated by the following formula:

[0050] ;

[0051] Among them, C i represents the number of all other data points of the i-th data point within the local reachability distance, and exp( ) represents the natural exponential function. represents the -th average value of the local reachability densities of other data points within the local reachability distance of the data point, represents the -th average value of the Euclidean distances from other data points within the local reachability distance of the data point.

[0052] It should be noted that in the formula the part represents the ratio of the local reachability density of the data points within the local reachability distance range of the data points to their Euclidean distance. The greater the difference between this ratio and the ratio of the average values of the two items of data, the more likely it is that the data point is an abnormal data point. Then, through the exp(-I k ) part in the formula, the influence degree of the ratio difference of the data points with a relatively large difference in the acquisition time from the th data point is weakened.

[0053] The density abnormality degree of each data point in the dataset can be obtained through the above formula.

[0054] In this embodiment, in addition to the density abnormality degree, it is also necessary to obtain the fluctuation degree of the data that is relatively close to the acquisition time of the data point according to the acquisition time sequence of the data points to measure the data abnormality degree. The data points with a greater fluctuation degree may also be the data points that need to be focused on.

[0055] According to the K value of the local reachability density, the K nearest data points to each data point are obtained, and the jth data value of the kth (the range of k is from 1 to K) local range data point among the K data points is denoted as D j (i, k).

[0056] Specifically, the local fluctuation degree of the data point is obtained according to each item of data within the local range of the data point:

[0057] ;

[0058] where F i represents the local fluctuation degree of the ith data point, N represents the number of data items included in each data point, K represents the number of other data points in the neighborhood of each data point, represents the difference in acquisition time between the ith data point and the kth data point among the multiple data points around it, D j (i, k) represents the jth data of the kth data point among the multiple data points around the ith data point, represents the average value of the jth data of all the data points among the multiple data points around the ith data point, represents the standard deviation of the jth data of all the data points among the multiple data points around the ith data point. The local fluctuation degree of each data point in the dataset can be obtained through the above formula.

[0059] Furthermore, the adjustment factor of each data point in the current round of dataset can be obtained through the adjustment factor calculation formula .

[0060] Adjust the sampling frequency of the data according to the adjustment factor. The larger the adjustment factor of the data, the higher the sampling frequency required at that data point to ensure that the detailed changes in the data can be collected.

[0061] Through the above method, 24 adjustment factors (A1……A 24 ) corresponding to 24 data points in this round can be calculated.

[0062] S3. Adjust the acquisition frequency of the motor detection data according to the adjustment factor to perform the acquisition of the next motor detection data.

[0063] Specifically, take the average value of the 24 adjustment factors calculated from a number of motor detection data collected in this round, and multiply this average value by the acquisition frequency in this round as the acquisition frequency of the next round of motor detection data.

[0064] Among them, each acquisition round can be determined according to the time period (for example, taking 24 hours as an acquisition round, then the acquisition is carried out at the same acquisition frequency within 24 hours), or can be determined according to the number of acquisitions (for example, taking the acquisition of 24 data points as an acquisition round, then the acquisition frequencies used for the 24 data points in this round are the same).

[0065] Calculate the local reachability density of the collected motor detection data through the LOF algorithm, and then the abnormality degree of each data point can be quantified according to the local reachability density to adaptively adjust the acquisition frequency. This method has higher sensitivity to abnormal data, can adaptively increase the acquisition frequency of abnormal data, and reduce the acquisition frequency of normal data, thereby improving the acquisition efficiency.

[0066] Embodiment of a motor detection data acquisition system based on a simulation environment:

[0067] On the other hand, the present invention also provides a motor detection data acquisition system based on a simulation environment. As Figure 2 shown, the motor detection data acquisition system based on a simulation environment includes an acquisition device and a controller. The acquisition device includes a motor speed acquisition device (for example, a speed acquisition device of model DT2235B can be used), a temperature acquisition device (for example, a temperature acquisition device of model PX05006 can be used), a current acquisition device (for example, a current acquisition device of model INA282AQDRQ1 can be used), a voltage acquisition device (for example, a voltage acquisition device of model YK-DCD-D-S-16-DV-500 can be used). The controller includes a processor and a memory, and the memory stores computer program instructions. When the computer program instructions are executed by the processor, a motor detection data acquisition method according to the first aspect of the present invention is implemented.

[0068] The motor detection data acquisition system based on the simulation environment further includes other components well-known to those skilled in the art, such as communication interfaces. Their settings and functions are known in the art, so they will not be elaborated here.

[0069] In the present invention, the aforementioned memory can be any tangible medium that contains or stores a program, which can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, a computer-readable storage medium can be any suitable magnetic storage medium or magneto-optical storage medium, such as, resistive random access memory (RRAM), dynamic random access memory (DRAM), static random access memory (SRAM), enhanced dynamic random access memory (EDRAM), high-bandwidth memory (HBM), hybrid memory cube (HMC), etc., or any other medium that can be used to store the required information and can be accessed by an application, module, or both. Any such computer storage medium can be part of the device or accessible or connectable to the device. Any application or module described in the present invention can be implemented by computer-readable / executable instructions stored or otherwise held by such a computer-readable medium.

[0070] In the description of this specification, the meanings of "a plurality of" and "several" are at least two, such as two, three, or more, etc., unless otherwise specifically and clearly defined.

[0071] Although this specification has shown and described multiple embodiments of the present invention, it is obvious to those skilled in the art that such embodiments are provided only by way of example. Those skilled in the art will think of many changes, alterations, and alternative ways without departing from the spirit and idea of the present invention. It should be understood that various alternative solutions to the embodiments of the present invention described herein can be adopted in the process of practicing the present invention.

Claims

1. A motor detection data acquisition method based on a simulation environment, characterized in that: The method comprises: Collect some motor test data and pass The algorithm calculates the local reachability density of the collected motor detection data; The adjustment factor of the data acquisition frequency is calculated according to the local reachable density, and the calculation method of the adjustment factor is specifically as follows: ； in, Indicates The adjustment factor for each data point is Indicates The density anomaly of the data points is Indicates The local fluctuation degree of each data point, Indicates the preset density anomaly threshold, Indicates the preset local fluctuation degree threshold; The calculation method of density anomaly degree is: ; Indicates The number of all other data points within the local reachable distance of a data point, represents the natural exponential function, Indicates the gap in data collection timing, Indicated in Among the multiple data points around the data point, The local reachable density of data points is Indicates Data points and The distance between data points, Indicates The average value of the local reachability density of other data points within the local reachability distance of a data point, Indicates The average value of the distances of a data point to other data points within the local reachable distance; The calculation method of local fluctuation degree is: ; Indicates the number of data items contained in each data point, represents the number of other data points in the neighborhood of each data point, Indicates A data point and the number of data points around it The difference in acquisition time between data points, Indicates of the multiple data points surrounding the data point The data point Item data, Indicates of all data points in the multiple data points surrounding the data point The average value of the data items, Indicates of all data points in the multiple data points surrounding the data point The standard deviation of the data item; The collection frequency of the motor detection data is adjusted according to the adjustment factor, including: taking an average value of several adjustment factors calculated from several motor detection data collected in this round, multiplying the average value by the collection frequency of this round as the collection frequency of the next round of motor detection data; and collecting the next round of motor detection data.

2. The motor detection data acquisition method based on a simulation environment according to claim 1 is characterized in that: Collect a number of motor detection data, including: collect two or more of the following signals: speed, temperature, current, voltage.

3. The motor detection data acquisition method based on a simulation environment according to claim 1 is characterized in that: The distance measurement method between the data points is configured as one or more of the following: Euclidean distance, Manhattan distance, and Mahalanobis distance.

4. The motor detection data acquisition method based on a simulation environment according to claim 1 is characterized in that: The adjustment factors calculated from the motor detection data collected in this round are averaged, including: averaging the adjustment factors calculated from the motor detection data within a preset time period, or averaging the adjustment factors calculated from the motor detection data of a preset number of times.

5. The motor detection data acquisition method based on a simulation environment according to claim 1 is characterized in that: The calculation of the local reachable density includes The value setting is The value represents the number of neighboring data points considered when calculating the local reachable density. Set the value to 10.

6. The motor detection data acquisition method based on a simulation environment according to claim 1 is characterized in that: It also includes filtering, amplifying and analog-to-digital conversion operations on the collected motor detection data to convert the collected analog data signals into digital signals.

7. A motor detection data acquisition system based on a simulation environment, characterized in that: It comprises an acquisition device and a controller, the controller comprises a processor and a memory, the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the motor detection data acquisition method based on a simulation environment as described in any one of claims 1 to 6 is implemented.

Images