An oil film whirl monitoring method, system, storage medium and electronic device

Abstract

The application relates to the technical field of rotating machinery and sliding bearings, and discloses an oil film vortex monitoring method, system, storage medium and electronic equipment. The method comprises the following steps: acquiring first running data of a bearing in a normal state and second running data of the bearing in an oil film vortex fault state, and respectively pre-processing the first running data and the second running data to obtain pre-processed first running data and pre-processed second running data; determining a first alarm baseline according to a preset mechanical vibration standard; determining a second alarm baseline according to the pre-processed first running data and the pre-processed second running data; determining a target alarm baseline according to the first alarm baseline and the second alarm baseline; and monitoring the running state of a target bearing through the target alarm baseline. The method solves the defects that the setting of a fixed threshold value is extremely dependent on artificial experience and professional knowledge, improves accuracy and has better universality.

Description

Technical Field

[0001] This application relates to the field of rotating machinery and sliding bearing technology, and in particular to a method, system, storage medium, computer program product, and electronic device for monitoring oil film eddy current. Background Technology

[0002] The purpose of the background description provided herein is to give an overall background to this application. The statements in this section are merely to provide background information relevant to this application and do not necessarily constitute prior art.

[0003] Oil film whirl faults are generally a type of hydrodynamic instability that occurs in sliding bearings at speeds above the first critical speed. They are a subsynchronous oscillation phenomenon in which the center of the rotor rotates around the center of the sliding bearing.

[0004] As bearings are one of the key components of rotating machinery, their operational status directly affects the machining accuracy, operational reliability, and lifespan of the entire large-scale mechanical equipment. Conducting bearing condition monitoring is fundamental to ensuring the safe and stable operation of mechanical equipment.

[0005] Under current conditions, alarm values ​​are thresholds or prescribed vibration values ​​set based on existing experience. When these alarm values ​​are reached or significant changes occur, appropriate remedial measures need to be taken. Generally, if an alarm occurs, the machine can continue to operate for a period of time, while an investigation should be conducted to determine the cause of the vibration change and to develop corresponding remedial measures.

[0006] Current condition monitoring methods are based on rules of thumb using fixed thresholds (e.g., limit values ​​set according to existing experience or specified vibration values). These rules define the range of variation for the system's main parameters. Thresholds are typically set as warning and alarm values. When the monitored parameters exceed these ranges, the machine is considered to have malfunctioned. These methods are simple to operate, require minimal computation, and facilitate real-time monitoring of the machine's sensor signals by the program.

[0007] Under current conditions, due to various factors such as design, manufacturing, and use, sliding bearings frequently experience oil film whirl failures. These failures can range from minor equipment damage and reduced production efficiency to serious impacts on production safety and economy, and even lead to accidents and endanger lives. Therefore, real-time monitoring of the operating status of sliding bearings in large rotating machinery is crucial for understanding their current condition.

[0008] Under current conditions, when conducting condition monitoring, the setting of thresholds relies heavily on human experience and professional knowledge. In actual applications, factors such as complex machine operating conditions and environmental changes can cause errors in the set thresholds. In some cases, manual on-site adjustments are required multiple times, and once the thresholds are set, they are generally not updated. Summary of the Invention

[0009] To address the aforementioned problems, this application proposes a method, system, storage medium, computer program product, and electronic device for monitoring oil film eddy current. This overcomes the drawback of fixed threshold settings being highly dependent on human experience and expertise, improving accuracy and offering greater versatility.

[0010] A first aspect of this application provides a method for monitoring oil film eddy currents, the method comprising:

[0011] The first operating data of the bearing under normal conditions and the second operating data of the bearing under oil film whirl fault conditions are obtained, and the first operating data and the second operating data are preprocessed to obtain the preprocessed first operating data and the preprocessed second operating data, respectively.

[0012] The first alarm baseline is determined based on the preset mechanical vibration standard;

[0013] A second alarm baseline is determined based on the preprocessed first operating data and the preprocessed second operating data;

[0014] The target alarm baseline is determined based on the first alarm baseline and the second alarm baseline;

[0015] The operating status of the target bearing is monitored using the target alarm baseline.

[0016] Furthermore, the preprocessing of the first running data and the second running data respectively includes:

[0017] The first running data and the second running data are converted into root mean square data, respectively.

[0018] Furthermore, after monitoring the operating status of the target bearing through the target alarm baseline, the method further includes:

[0019] An alarm message is issued when the operating state meets preset conditions.

[0020] Furthermore, the second alarm baseline includes a second early warning baseline, and determining the second alarm baseline based on the preprocessed first operating data and the preprocessed second operating data includes:

[0021] Determine the current acquisition cycle value when an abnormal state occurs;

[0022] The ratio of the short-cycle root mean square value to the long-cycle root mean square value is determined based on the current acquisition cycle value, the preprocessed first operating data, and the preprocessed second operating data, and a second early warning baseline is determined based on the ratio of the short-cycle root mean square value to the long-cycle root mean square value.

[0023] Furthermore, the second alarm baseline includes a second alarm baseline, and determining the second alarm baseline based on the preprocessed first operating data and the preprocessed second operating data includes:

[0024] The alarm value is determined by a preset explicit regression model based on the preprocessed second operating data, and the second alarm baseline is determined based on the alarm value.

[0025] Furthermore, after monitoring the operating status of the target bearing through the target alarm baseline, the method further includes:

[0026] When the operating state meets preset conditions, fault data is determined;

[0027] The preset explicit regression model is trained based on the fault data, and the alarm value is redefined. The second alarm baseline is then updated based on the redefined alarm value.

[0028] A second aspect of this application provides an oil film eddy monitoring system, the system comprising:

[0029] The acquisition module is used to acquire the first operating data of the bearing under normal conditions and the second operating data of the bearing under the condition of oil film whirl fault, and to preprocess the first operating data and the second operating data respectively to obtain the preprocessed first operating data and the preprocessed second operating data.

[0030] The first determination module is used to determine the first alarm baseline according to a preset mechanical vibration standard;

[0031] The second determining module is used to determine a second alarm baseline based on the preprocessed first operating data and the preprocessed second operating data;

[0032] The third determining module is used to determine the target alarm baseline based on the first alarm baseline and the second alarm baseline;

[0033] The detection module is used to monitor the operating status of the target bearing through the target alarm baseline.

[0034] A third aspect of this application provides a computer program product comprising a computer program or instructions that, when executed by a processor, implement the steps of the method described above.

[0035] A fourth aspect of this application provides a computer-readable storage medium storing a computer program that can be executed by one or more processors to implement the steps of the method described above.

[0036] A fifth aspect of this application provides an electronic device including a memory and one or more processors, wherein a computer program is stored on the memory, and the memory and the one or more processors are communicatively connected to each other, wherein when the computer program is executed by the one or more processors, it implements the steps of the method described above.

[0037] Compared with the prior art, the technical solution of this application has the following advantages or beneficial effects:

[0038] (1) Compared with the fixed threshold method, this application can reduce the dependence of the fixed threshold setting on human experience and professional knowledge. The data with root mean square value greater than 4.5 are input into the preset linear regression model to continue training and obtain a better alarm baseline, thus realizing the adaptive update of the alarm baseline.

[0039] (2) The selected time-domain feature expression and condition expression are combined, and the early warning baseline is obtained by combining the ratio of the short-period average value to the long-period average value of the mechanical vibration national standard GB / T6075.1-2012 and the time-domain feature short-period average value, without setting an accurate early warning value. Compared with the fixed threshold method, the expression is clearer and has better accuracy.

[0040] (3) Compared with the fixed alarm threshold method, this application constructs a linear regression model, inputs oil film whirl fault data to obtain a fitting equation, obtains the initial alarm baseline y2 by the lowest point value of the fitting equation, and then combines y2 with the initial alarm baseline y1 set by the national standard to obtain the final alarm baseline, which can obtain a more accurate alarm threshold.

[0041] (4) Compared with the fixed threshold method, the designed conditional expression is subjected to logical operation, which has both accurate value warning and alarm baselines and statistical warning and alarm baselines. As long as one of the above conditions is met, alarm or warning processing can be performed, which has better versatility.

[0042] (5) Compared with the fixed threshold method, this application uses the warning and alarm baseline set in the national standard GB / T 6075.1-2012 for mechanical vibration as a safety net strategy, and uses the ratio k of the average value of the short-cycle root mean square value and the average value of the long-cycle root mean square value and the lowest point of the fitted equation as an advance strategy, which has better accuracy and safety. Attached Figure Description

[0043] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0044] It should also be noted that, for ease of description, only the parts relevant to this disclosure are shown in the accompanying drawings. The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions in this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0045] Figure 1 A flowchart illustrating an oil film eddy monitoring method provided in this application embodiment;

[0046] Figure 2 This is a schematic diagram of a national standard for the root mean square value of mechanical vibration velocity.

[0047] Figure 3 A schematic diagram of a root mean square value curve provided in an embodiment of this application;

[0048] Figure 4 A schematic diagram illustrating the ratio of a short-period root mean square value to a long-period root mean square value, provided as an embodiment of this application.

[0049] Figure 5 A scatter plot of a linear regression model provided in an embodiment of this application;

[0050] Figure 6 This is a connection block diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0051] The following detailed description of the embodiments of this application, in conjunction with the accompanying drawings, will provide a thorough understanding of how this application uses technical means to solve technical problems and achieve corresponding technical effects, enabling its implementation. The embodiments of this application and the various features within them can be combined with each other without conflict, and all resulting technical solutions are within the protection scope of this application.

[0052] It should be clearly stated that the embodiments described below are merely some embodiments of this application, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0053] Example 1

[0054] This embodiment provides a method for monitoring oil film eddy current. Figure 1 A flowchart of an oil film eddy monitoring method provided in this application embodiment is shown below. Figure 1 As shown, the method disclosed in this embodiment includes the following steps:

[0055] Step 110: Obtain the first operating data of the bearing under normal conditions and the second operating data of the bearing under oil film whirl fault conditions, and preprocess the first operating data and the second operating data respectively to obtain the preprocessed first operating data and the preprocessed second operating data.

[0056] Optionally, vibration sensors can be installed on the bearing to collect vibration data. The collected data should include data from normal operation and operation during oil film whirl faults. All data should be saved as dataset D. Normal data and oil film whirl fault data should be distinguished. The data structure can be JSON format.

[0057]

[0058]

[0059] In some embodiments, the preprocessing of the first running data and the second running data includes:

[0060] The first running data and the second running data are converted into root mean square data, respectively.

[0061] Optionally, the preset mechanical vibration standard includes the national standard for mechanical vibration, GB / T 6075.1-2012.

[0062] The use of root mean square (RMS) velocity measurement to characterize the vibration response characteristics of machines in the national standard GB / T 6075.1-2012 for mechanical vibration has been very successful. RMS values ​​can generally adequately describe the fault-free operating condition of rotating shaft assemblies. When abnormalities or faults occur, the vibration data is clearly represented graphically by the RMS values. Therefore, RMS values ​​are chosen as the feature expression of this invention, and the data in dataset D needs to be converted into an RMS value expression form.

[0063] An alternative expression for the root mean square value is as follows:

[0064]

[0065] Where X represents the root mean square value, N is a time series with N data points, and x(n) represents the nth data point.

[0066] Furthermore, based on the preprocessed first operating data and the preprocessed second operating data, a short-cycle root mean square value average curve with a first preset cycle value and a long-cycle root mean square value average curve with a second preset cycle value can be plotted in the same coordinate system, and a root mean square value graph can be plotted in another identical coordinate system; wherein, the horizontal axis of the coordinate system is the acquisition cycle value, and the vertical axis is the vibration amplitude.

[0067] It should be noted that the first preset cycle value can be set to 3, and the second preset cycle value can be set to 20.

[0068] For example, based on the transformed root mean square (RMS) value X from dataset D, a graph of the corresponding RMS value is plotted, and on the RMS value graph, curves with a period of 20 (long-period RMS value average curve 1) and a period of 3 (short-period RMS value average curve 2) are plotted. Then, on another graph, a graph showing the ratio of the short-period RMS value to the long-period RMS value is plotted.

[0069] For example, by choosing the root mean square (RMS) value as the feature, we can plot the short-period RMS value average curve 1 (period 3), the long-period RMS value average curve 2 (period 20), and the graph of the RMS value (see reference). Figure 4 , Figure 4 A schematic diagram showing the ratio of a short-period root mean square value to a long-period root mean square value provided in the embodiments of this application, and a graph showing the ratio of a short-period root mean square value to a long-period root mean square value (see reference). Figure 3 , Figure 3 (A schematic diagram of a root mean square curve provided in an embodiment of this application).

[0070] Step 120: Determine the first alarm baseline according to the preset mechanical vibration standard.

[0071] In some embodiments, the first alarm baseline includes a first warning baseline; wherein the first warning baseline includes:

[0072] y1 = (x ≥ k1)? 1:0

[0073] Where y1 represents whether to issue an early warning, k1 is a constant, and x is the root mean square value.

[0074] Optionally, the first warning baseline y1 can be obtained according to the national standard GB / T 6075.1-2012 for mechanical vibration, and the value of k1 can be set to 4.5.

[0075] For example, see reference. Figure 2 The national standard recommends that the warning value should be lower than the lower limit of region C. Therefore, the first warning baseline y1 can be obtained:

[0076] If X >= 4.5,

[0077] y = 1;

[0078] else y = 0.

[0079] Where X is the root mean square value, y=1 indicates that an early warning should be issued, and y=0 indicates that no early warning should be issued. Therefore, y1 means that if the root mean square value is greater than or equal to 4.5, the device should issue an early warning; otherwise, the machine will operate normally and no early warning is required.

[0080] In some embodiments, the first alarm baseline further includes a first alarm baseline; wherein the first alarm baseline includes:

[0081] b1 = (x ≥ k2)? 1:0

[0082] Where b1 indicates whether to trigger an alarm, k2 is a constant, and x is the root mean square value.

[0083] Optionally, the value of k1 can be set to 9.3.

[0084] For example, the national standard recommends that the alarm value should be higher than the baseline by a certain amount, equal to a certain proportion of the upper limit value of zone B in the national vibration standard GB / T 6075.1-2012. If the baseline is low, the alarm value may be lower than zone C. Different bearings on the machine may require different alarm value settings, reflecting differences in dynamic load and bearing support stiffness. Here, an initial alarm baseline b1 can be designed:

[0085] If X >= 9.3,

[0086] b = 1;

[0087] else b = 0.

[0088] Where X is the root mean square value, b=1 indicates an alarm, and y=0 indicates no alarm. Therefore, b1 means that if the root mean square value is greater than or equal to 9.3, the device should trigger an alarm; otherwise, no alarm should be triggered.

[0089] Step 130: Determine the second alarm baseline based on the preprocessed first running data and the preprocessed second running data.

[0090] In some embodiments, the second alarm baseline includes a second warning baseline, and determining the second alarm baseline based on the preprocessed first operating data and the preprocessed second operating data includes:

[0091] Determine the current acquisition cycle value when an abnormal state occurs;

[0092] The ratio of the short-cycle root mean square value to the long-cycle root mean square value is determined based on the current acquisition cycle value, the preprocessed first operating data, and the preprocessed second operating data, and a second early warning baseline is determined based on the ratio of the short-cycle root mean square value to the long-cycle root mean square value.

[0093] Optionally, based on the root mean square value graph and the ratio of short-term to long-term periods, the above graphs are analyzed and processed to extract information that can represent machine early warning. Conditional expressions are designed based on the extracted information to obtain the second early warning baseline y2.

[0094] For example, combined with Figure 3 and Figure 4 It can be seen that the sliding bearing operates normally from cycle 1 to cycle 531. After cycle 531, the sliding bearing exhibits an abnormal state or shows signs of oil film whirl fault. Therefore, we can express the design condition expression for the sliding bearing's early warning. At the current cycle of 531, the short-cycle RMS value d1 = 2.42, and the long-cycle RMS value d2 = 1.85. Therefore, the ratio of the current short-cycle RMS value to the long-cycle RMS value is k = 1.3. Thus, the second early warning baseline y2 can be obtained:

[0095] If k >= 1.3,

[0096] y = 1;

[0097] else y = 0.

[0098] Therefore, y2 means that if the ratio of the current short-period root mean square value to the long-period root mean square value is greater than or equal to 1.3, an early warning can be issued; otherwise, the machine will operate normally and no early warning is required.

[0099] In some embodiments, the second alarm baseline includes a second alarm baseline, and determining the second alarm baseline based on the preprocessed first operating data and the preprocessed second operating data includes:

[0100] The alarm value is determined by a preset explicit regression model based on the preprocessed second operating data, and the second alarm baseline is determined based on the alarm value.

[0101] In some embodiments, the preset explicit regression model includes:

[0102]

[0103] in, Let be the total number of scatter points, i be the i-th scatter point, and β be the scatter point. i Let δ be the fitting coefficient for the i-th scatter point. i Additional parameters, X, are added to the fitting of the i-th scatter point. iLet be the mean square value of the i-th scatter point.

[0104] Optionally, based on the data labeled as oil film whirl fault, the second alarm condition expression b2 is obtained. A pre-constructed linear regression model is expressed as follows:

[0105]

[0106] Where F represents the dependent variable and X represents the independent variable. Let denoted as the total number of scatter points, i be the i-th scatter point, β be the fitting coefficient, and δ be the total number of scatter points. i Additional parameters are added for fitting, with Xi representing the i-th data point. Data labeled as oil film whirl faults in the dataset are input into a pre-defined linear regression model. A fitting equation is obtained using the least squares method, and a scatter plot of the fitted data is plotted.

[0107] In some embodiments, the second alarm baseline includes:

[0108] b = (x > f) min )? 1:0

[0109] Where b indicates whether to issue an early warning, f min is the alarm value, and x is the root mean square value.

[0110] Furthermore, by setting the alarm value to the lowest point value of the fitted equation in the scatter plot, the second alarm baseline b2 can be obtained:

[0111] if X>=f min ,

[0112] b = 1;

[0113] else b = 0.

[0114] Among them, f min b2 represents the minimum value of the fitted equation. b2 means that if the root mean square value is greater than or equal to the minimum value of the fitted equation, an alarm can be triggered; otherwise, no alarm is required.

[0115] For example, to construct a linear regression model, the data marked with oil film whirl faults in the collected dataset are input into the preset linear regression model. The least squares method is used to obtain the fitting equation, and a scatter plot and fitting curve are plotted as follows. Figure 5 As shown. The alarm value is 4.8, which gives us the second alarm baseline b2:

[0116] If X >= 4.8,

[0117] b = 1;

[0118] else b = 0.

[0119] 4.8 is the minimum value in the fitted equation. If the root mean square value is greater than or equal to 4.8, the machine can issue an alarm.

[0120] Step 140: Determine the target alarm baseline based on the first alarm baseline and the second alarm baseline.

[0121] Furthermore, the warning baselines y1 and y2 are logically combined to obtain the warning baseline Y; the alarm baselines b1 and b2 are logically operated on to obtain the final alarm baseline B.

[0122] For example, by combining the early warning baselines y1 and y2 logically, the final early warning baseline can be obtained.

[0123] Therefore, the warning baseline Y can be set as:

[0124] If X >= 4.5 | k >= 1.3,

[0125] y = 1;

[0126] else y = 0.

[0127] Therefore, the warning baseline Y means that if the root mean square value is greater than or equal to 4.5 or the ratio of the current short-period root mean square value to the long-period root mean square value is greater than or equal to 1.3, the machine can perform warning processing; otherwise, the machine operates normally and does not require warning processing.

[0128] Furthermore, by combining b2 with b1 from the national standard through logical operations, alarm baseline B is obtained:

[0129] If X >= 9.3 | X >= 4.5,

[0130] b = 1;

[0131] else b = 0.

[0132] It should be noted that the value of 4.8 obtained in step 130 is the value of the lowest point in the fitted curve. Since this value is greater than the vibration standard limit for zone C specified in the national standard for mechanical vibration GB / T 6075.1-2012, the alarm value is set to 4.5 by performing logical operations in accordance with the national standard.

[0133] The alarm baseline B means that if the root mean square value is greater than or equal to 9.3 or greater than or equal to the lowest point value of the fitted equation, an early warning can be issued; otherwise, no alarm is required.

[0134] In some embodiments, after monitoring the operating status of the target bearing via the target alarm baseline, the method further includes:

[0135] When the operating state meets preset conditions, fault data is determined;

[0136] The preset explicit regression model is trained based on the fault data, and the alarm value is redefined. The second alarm baseline is then updated based on the redefined alarm value.

[0137] Furthermore, the alarm baseline B is updated based on the first alarm baseline b1 and the updated second alarm baseline b2.

[0138] Step 150: Monitor the operating status of the target bearing through the target alarm baseline.

[0139] Optionally, after obtaining the warning baseline and alarm baseline, these two baselines should be exported, along with the preset linear regression model used to train the alarm baseline. The exported model and baselines need to be saved on a storage device.

[0140] Furthermore, baselines and models from storable devices are deployed to the production site to monitor the operating status of target bearings.

[0141] Furthermore, after obtaining the monitoring baseline, this early warning baseline and alarm baseline are used to monitor the bearing's condition in real time on-site. If the collected data, after being converted to root mean square (RMS) values, shows a value greater than or equal to 4.5, it is automatically marked as oil film whirl fault data. The fault data is then input into a preset linear regression model for training. The lowest point in the newly fitted equation is used as the new alarm value, thereby updating the alarm value in the alarm baseline to achieve adaptive updating of the alarm value.

[0142] In some embodiments, after monitoring the operating status of the target bearing via the target alarm baseline, the method further includes:

[0143] An alarm message is issued when the operating state meets preset conditions.

[0144] It should be noted that an alarm will be triggered if the corresponding conditions of the warning baseline Y and / or alarm baseline B are met.

[0145] As will be understood by those skilled in the art, the preset conditions include:

[0146] The root mean square (RMS) value is greater than or equal to 4.5, or the ratio of the current short-period RMS value to the long-period RMS value is greater than or equal to 1.3; and / or,

[0147] The root mean square value is greater than or equal to 9.3 or greater than or equal to the minimum value of the fitted equation.

[0148] The oil film eddy monitoring method provided in this embodiment overcomes the shortcomings of fixed threshold settings, which heavily rely on human experience and expertise, thus improving accuracy and versatility. Specifically, it includes the following steps: acquiring first operating data of the bearing under normal conditions and second operating data of the bearing under oil film eddy fault conditions; preprocessing the first and second operating data to obtain preprocessed first and second operating data, respectively; determining a first alarm baseline based on a preset mechanical vibration standard; determining a second alarm baseline based on the preprocessed first and second operating data; determining a target alarm baseline based on the first and second alarm baselines; and monitoring the operating status of the target bearing using the target alarm baseline. This application uses the warning and alarm baselines set in the national standard for mechanical vibration GB / T 6075.1-2012 as a safety net strategy, and uses the ratio k of the short-period root mean square value to the long-period root mean square value and the lowest point of the fitted equation as an advance strategy, resulting in better accuracy and safety.

[0149] Example 2

[0150] This embodiment provides an oil film eddy monitoring system. This system embodiment can be used to execute the method embodiments of this application. For details not disclosed in this system embodiment, please refer to the method embodiments of this application. The system disclosed in this embodiment includes:

[0151] The acquisition module is used to acquire the first operating data of the bearing under normal conditions and the second operating data of the bearing under the condition of oil film whirl fault, and to preprocess the first operating data and the second operating data respectively to obtain the preprocessed first operating data and the preprocessed second operating data.

[0152] The first determination module is used to determine the first alarm baseline according to a preset mechanical vibration standard;

[0153] The second determining module is used to determine a second alarm baseline based on the preprocessed first operating data and the preprocessed second operating data;

[0154] The third determining module is used to determine the target alarm baseline based on the first alarm baseline and the second alarm baseline;

[0155] The detection module is used to monitor the operating status of the target bearing through the target alarm baseline.

[0156] In some embodiments, the acquisition module further includes a preprocessing unit for converting the first running data and the second running data into root mean square data, respectively.

[0157] In some embodiments, an alarm module is further included, which is used to issue an alarm message when the operating status of the target bearing meets preset conditions after the operating status is monitored through the target alarm baseline.

[0158] In some embodiments, the second determining module includes a first determining unit and a second determining unit; wherein...

[0159] The first determining unit is used to determine the current acquisition cycle value when an abnormal state occurs;

[0160] The second determining unit is used to determine the ratio of the short-cycle root mean square value to the long-cycle root mean square value based on the current acquisition cycle value, the preprocessed first operating data, and the preprocessed second operating data, and to determine the second early warning baseline based on the ratio of the short-cycle root mean square value to the long-cycle root mean square value.

[0161] In some embodiments, the second determining module includes a third determining unit, configured to determine an alarm value based on the preprocessed second operating data using a preset explicit regression model, and to determine a second alarm baseline based on the alarm value.

[0162] In some embodiments, the preset explicit regression model includes:

[0163]

[0164] in, Let be the total number of scatter points, i be the i-th scatter point, and β be the scatter point. i Let δ be the fitting coefficient for the i-th scatter point. i Additional parameters, X, are added to the fitting of the i-th scatter point. i Let be the mean square value of the i-th scatter point.

[0165] In some embodiments, the second alarm baseline includes:

[0166] b = (x > f) min )? 1:0

[0167] Where b indicates whether to issue an early warning, f min is the alarm value, and x is the root mean square value.

[0168] In some embodiments, the system further includes a fault determination unit and an update unit; wherein,

[0169] The fault determination unit is used to determine fault data when the operating state meets preset conditions;

[0170] The update unit is used to train the preset explicit regression model based on the fault data and redetermine the alarm value, and update the second alarm baseline based on the redetermined alarm value.

[0171] As an example, the oil film eddy monitoring system disclosed in this embodiment may specifically include the following modules:

[0172] The system includes modules for data acquisition and preprocessing, dataset storage, data conversion and visualization, linear modeling, alarm updates, monitoring baselines, early warning judgment, alarm judgment, and a computer. Among these:

[0173] The data acquisition module and preprocessing module are used for acquiring machine vibration data, labeling the data as normal data and oil film whirl fault data for preprocessing, saving the normal and fault data into a dataset, and storing it in the data storage module.

[0174] The dataset storage module is used to store the data obtained by the data acquisition module, combining them into a dataset, including normal data and oil film whirl fault data;

[0175] The data conversion and visualization module is used to convert the original vibration waveform data into root mean square (RMS) values ​​and to plot the time-domain graph of the RMS values.

[0176] The linear model module is used to build a linear regression model. The model is input with oil film eddy data, and then a fitting equation is plotted and the minimum value of the fitting equation is output.

[0177] The alarm update module reads the lowest point value f of the fitted equation in the linear model module. min According to f min The value updates the alarm baseline in the monitoring baseline module;

[0178] The monitoring baseline module is used to store early warning baselines and alarm baselines;

[0179] The early warning judgment module is used to read the early warning baseline in the monitoring baseline and determine whether the root mean square value meets the condition expression of the early warning baseline. If the condition is met, early warning processing can be performed; otherwise, early warning processing will not be performed.

[0180] The alarm judgment module is used to read the alarm baseline in the monitoring baseline and determine whether the root mean square value meets the condition expression of the alarm baseline. If the condition is met, alarm processing can be performed; otherwise, alarm processing can be performed.

[0181] The judgment module is used to determine whether the root mean square value is greater than 4.5. If the condition is true, data with a root mean square value greater than 4.5 are input into the linear model module; if the condition is false, no processing is performed.

[0182] Computers are used to deploy and train linear regression models and store collected data.

[0183] Those skilled in the art will understand that the modules or steps described above can be implemented using general-purpose computing devices, either centralized on a single computing device or distributed across a network of multiple computing devices. Optionally, they can be implemented using computer-executable program code, thereby allowing them to be stored in a storage device for execution by a computing device. Furthermore, in some cases, the steps shown or described can be performed in a different order than presented herein, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module.

[0184] Example 3

[0185] This embodiment provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, which, when executed by a processor, can implement the method steps as described in the foregoing method embodiments; these steps will not be repeated here.

[0186] Computer-readable storage media may individually include computer programs, data files, data structures, etc., or combinations thereof. The computer-readable storage media or computer program may be specifically designed and understood by those skilled in the art of computer software, or the computer-readable storage media may be known and available to those skilled in the art of computer software. Examples of computer-readable storage media include: magnetic media, such as hard disks, floppy disks, and magnetic tapes; optical media, such as CD-ROMs and DVDs; magneto-optical media, such as optical discs; and hardware devices specifically configured to store and execute computer programs, such as read-only memory (ROM), random access memory (RAM), flash memory; or servers, application stores, etc. Examples of computer programs include machine code (e.g., code generated by a compiler) and files containing high-level code that can be executed by a computer using an interpreter. The described hardware devices may be configured to function as one or more software modules to perform the operations and methods described above, and vice versa. Furthermore, computer-readable storage media may be distributed across networked computer systems, allowing for the decentralized storage and execution of program code or computer programs.

[0187] Example 4

[0188] This embodiment provides a computer program product. The computer program product includes a computer program or instructions, which, when executed by a processor, implement all or part of the steps of the method as described in the foregoing method embodiments; these will not be repeated here.

[0189] Furthermore, the computer program product may include one or more computer-executable components configured to perform an embodiment when the program is run; the computer program product may also include a computer program tangibly contained on a readable medium thereof, the computer program containing program code for performing any of the methods described in the embodiments of this disclosure. In such embodiments, the computer program may be downloaded and installed from a network via a communication component, and / or installed from a removable medium.

[0190] Example 5

[0191] This embodiment provides an electronic device. Figure 6 A connection block diagram of an electronic device provided in an embodiment of this application, such as... Figure 6 As shown, the electronic device 600 may include: one or more processors 601, memory 602, multimedia component 603, input / output (I / O) interface 604, and communication component 605.

[0192] One or more processors 601 are used to execute all or part of the steps as described in the foregoing method embodiments. Memory 602 is used to store various types of data, which may include, for example, instructions for any application or method in the electronic device, as well as application-related data.

[0193] One or more processors 601 may be implemented as an Application Specific Integrated Circuit (ASIC), a Digital Signal Processor (DSP), a Digital Signal Processing Device (DSPD), a Programmable Logic Device (PLD), a Field Programmable Gate Array (FPGA), a controller, a microcontroller, a microprocessor, or other electronic components, for performing the methods as described in the foregoing method embodiments.

[0194] The memory 602 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0195] Multimedia component 603 may include a screen, which may be a touchscreen, and an audio component for outputting and / or inputting audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in memory or transmitted via a communication component. The audio component also includes at least one speaker for outputting audio signals.

[0196] I / O interface 604 provides an interface between one or more processors 601 and other interface modules, such as a keyboard, mouse, buttons, etc. These buttons can be virtual buttons or physical buttons.

[0197] The communication component 605 is used for wired or wireless communication between the electronic device 600 and other devices. Wired communication includes communication via network ports, serial ports, etc.; wireless communication includes Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, 4G, 5G, or one or more combinations thereof. Therefore, the corresponding communication component 605 may include a Wi-Fi module, a Bluetooth module, and an NFC module.

[0198] In summary, this application provides a method, apparatus, computer-readable storage medium, computer program product, and electronic device for monitoring oil film whirl. The method includes: acquiring first operating data of a bearing under normal conditions and second operating data of a bearing experiencing an oil film whirl fault; preprocessing the first and second operating data to obtain preprocessed first and second operating data, respectively; determining a first alarm baseline based on a preset mechanical vibration standard; determining a second alarm baseline based on the preprocessed first and second operating data; determining a target alarm baseline based on the first and second alarm baselines; and monitoring the operating status of a target bearing using the target alarm baseline. This method overcomes the limitation of fixed threshold settings being highly dependent on human experience and expertise, improving accuracy and offering better versatility.

[0199] It should also be understood that the methods or systems disclosed in the embodiments provided in this application can also be implemented in other ways. The method or system embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the architecture, functions, and operations of possible implementations of methods and apparatus according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, computer program segment, or part of a computer program, which includes one or more computer programs for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings, and may actually be executed substantially in parallel. They may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or can be implemented using a combination of dedicated hardware and computer programs.

[0200] In this application, the terms “comprising,” “including,” or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "including one..." does not exclude the presence of other identical elements in the process, method, apparatus, or device that includes the element; the use of terms such as "first" and "second" is for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly indicating the number or sequence of the indicated technical features; in the description of this application, unless otherwise stated, the terms "multiple" or "many" mean at least two; if a server is described, it should be noted that a server can be an independent physical server or terminal, or a server cluster consisting of multiple physical servers, or a cloud server capable of providing basic cloud computing services such as cloud servers, cloud databases, cloud storage, and CDN; if a smart terminal or mobile device is described in this application, it should be noted that a smart terminal or mobile device can be a mobile phone, tablet computer, smartwatch, netbook, wearable electronic device, personal digital assistant (PDA), augmented reality (AR) device, virtual reality (VR) device, smart TV, smart speaker, personal computer (PC). Computer (PC) etc., but not limited to these, this application does not make any special restrictions on the specific form of smart terminals or mobile devices.

[0201] Finally, it should be noted that in the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "a single example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0202] Although embodiments of this application have been shown and described above, it is to be understood that the above embodiments are exemplary and the content is only for the purpose of facilitating understanding of this application, and is not intended to limit this application. Any person skilled in the art to which this application pertains may make any modifications and changes in form and detail of the implementation without departing from the spirit and scope disclosed in this application, but the scope of protection of this application shall still be determined by the scope defined in the appended claims.

Claims

1. A method for monitoring oil film eddy current, characterized in that, The method includes: The first operating data of the bearing under normal conditions and the second operating data of the bearing under oil film whirl fault conditions are obtained, and the first operating data and the second operating data are preprocessed to obtain preprocessed first operating data and preprocessed second operating data, respectively; wherein, the preprocessing of the first operating data and the second operating data includes converting the first operating data and the second operating data into root mean square data, respectively. A first alarm baseline is determined based on a preset mechanical vibration standard; wherein, the first alarm baseline includes a first warning baseline and a first alarm baseline; A second alarm baseline is determined based on the preprocessed first operating data and the preprocessed second operating data; wherein, the second alarm baseline includes a second early warning baseline and a second alarm baseline; A target alarm baseline is determined based on the first alarm baseline and the second alarm baseline; wherein, the target alarm baseline includes a final warning baseline and a final alarm baseline; wherein, the first warning baseline and the second warning baseline are logically combined to obtain the final warning baseline, which is used to determine whether to perform warning processing based on root mean square data; the first alarm baseline and the second alarm baseline are logically combined to obtain the final alarm baseline, which is used to determine whether to perform alarm processing based on root mean square data; The operating status of the target bearing is monitored using the target alarm baseline.

2. The oil film eddy monitoring method according to claim 1, characterized in that, After monitoring the operating status of the target bearing via the target alarm baseline, the method further includes: An alarm message is issued when the operating state meets preset conditions.

3. The oil film eddy monitoring method according to claim 1, characterized in that, The step of determining the second alarm baseline based on the preprocessed first operating data and the preprocessed second operating data includes: Determine the current acquisition cycle value when an abnormal state occurs; The ratio of the short-cycle root mean square value to the long-cycle root mean square value is determined based on the current acquisition cycle value, the preprocessed first operating data, and the preprocessed second operating data, and a second early warning baseline is determined based on the ratio of the short-cycle root mean square value to the long-cycle root mean square value.

4. The oil film eddy monitoring method according to claim 1, characterized in that, The step of determining the second alarm baseline based on the preprocessed first operating data and the preprocessed second operating data includes: The alarm value is determined by a preset explicit regression model based on the preprocessed second operating data, and the second alarm baseline is determined based on the alarm value.

5. The oil film eddy monitoring method according to claim 4, characterized in that, After monitoring the operating status of the target bearing via the target alarm baseline, the method further includes: When the operating state meets preset conditions, fault data is determined; The preset explicit regression model is trained based on the fault data, and the alarm value is redefined. The second alarm baseline is then updated based on the redefined alarm value.

6. An oil film eddy monitoring system applying the method as described in claim 1, characterized in that, include: The acquisition module is used to acquire the first operating data of the bearing under normal conditions and the second operating data of the bearing under the condition of oil film whirl fault, and to preprocess the first operating data and the second operating data respectively to obtain the preprocessed first operating data and the preprocessed second operating data. The first determination module is used to determine the first alarm baseline according to a preset mechanical vibration standard; The second determining module is used to determine a second alarm baseline based on the preprocessed first operating data and the preprocessed second operating data; The third determining module is used to determine the target alarm baseline based on the first alarm baseline and the second alarm baseline; The detection module is used to monitor the operating status of the target bearing through the target alarm baseline.

7. A computer program product, said computer program product comprising a computer program or instructions, characterized in that, When the computer program or instructions are executed by a processor, they implement the steps of the method as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer program stored in the computer-readable storage medium, when executed by one or more processors, implements the steps of the method as described in any one of claims 1 to 5.

9. An electronic device, characterized in that, The method includes a memory and one or more processors, wherein a computer program is stored in the memory, and the memory and the one or more processors are communicatively connected to each other. When the computer program is executed by the one or more processors, the steps of the method as described in any one of claims 1 to 5 are performed.

Images