Belt reducer bearing performance test system

Abstract

The invention belongs to the technical field of reducer bearing performance testing, and discloses a belt reducer bearing performance testing system. The system comprises a bearing performance calculation module, a bearing performance feedback module, a multi-dimensional evaluation system module, an intelligent test adjustment module and an energy consumption optimization design module, the bearing pressure is monitored, a pressure monitoring report is obtained, analysis is carried out based on feature vectors, the bearing performance is calculated according to a multi-level nonlinear integrated model, and the energy consumption optimization design is realized. The method comprises the following steps: obtaining a performance feedback value, carrying out grading processing on the performance feedback value, calculating a multi-dimensional index of a test bearing based on the performance feedback value and a feature vector, obtaining a bearing evaluation report, comparing bearing type data with a bearing test parameter rule base, outputting to obtain a parameter adjustment report, and obtaining an energy consumption saving report. The method has the remarkable advantages of high bearing test feedback accuracy, good multi-dimensional evaluation effect and high system use economy.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of reducer bearing performance testing, and more particularly to a belt reducer bearing performance testing system. BACKGROUND

[0002] Bearing is an important part in contemporary mechanical equipment, its main function is to support the mechanical rotating body, reduce the friction coefficient in its movement process, and ensure its rotation accuracy, the belt reducer is widely used as an extremely important tool in current industry, business and civil use, etc., wherein the bearing is an indispensable important part in the belt reducer, and the performance of the bearing is directly related to the service life and use experience of the belt reducer.

[0003] In the existing use process of the belt reducer bearing, it often needs to face complex use environment, such as high temperature and high humidity, high strength and high corrosion, etc. The existing belt reducer bearing testing system usually only simulates a single working condition, such as constant speed or constant environment, while in the actual use process of the bearing, it may need to withstand the coupling action of multiple factors such as temperature and humidity change or vibration impact, and usually relies on manual setting of test parameters to test the bearing, thereby to a certain extent, the risk of inputting error of test parameters and the working strength are improved, in addition, the existing test system mostly focuses on a single index, lacks systematic evaluation of the bearing, and the energy consumption cost in the test process is also a large enterprise cost expenditure.

[0004] In view of this, the present application provides a belt reducer bearing performance testing system to solve the above problems. SUMMARY

[0005] In order to overcome the above-mentioned defects of the prior art, in order to achieve the above-mentioned purpose, the present application provides the following technical scheme, comprising:

[0006] The test data acquisition module is used for acquiring a test data set, and the test data set includes vibration amplitude data, noise level data, bearing temperature data and test speed data;

[0007] The environment data acquisition module is used for acquiring an environment data set, and the environment data set includes test temperature data, test humidity data and corrosion gas concentration data;

[0008] The pressure monitoring module is used for monitoring the bearing pressure to obtain a pressure monitoring report;

[0009] Further, the way of monitoring the bearing pressure comprises:

[0010] The product of the vibration amplitude data, the test speed data and the pressure coefficient is calculated to obtain a dynamic pressure index;

[0011] generating a pressure monitoring report when the dynamic pressure index is greater than or equal to the pressure safety threshold, and outputting the test data set and the environmental data set to a data interaction mining module when the dynamic pressure value is less than the pressure safety threshold;

[0012] The pressure monitoring report comprises a stop instruction;

[0013] The stop instruction comprises a set of characters representing the closing of the performance test equipment

[0014] The data interaction mining module is configured to preprocess the test data set and the environmental data set, and extract feature data to obtain a feature vector;

[0015] Further, the step of preprocessing the test data set and the environmental data set and extracting feature data comprises:

[0016] Q1: Data cleaning is completed by removing outliers in all sub-data items in the basic data set, and all sub-data items in the basic data set are normalized to the range of [0, 1] according to a normalization formula;

[0017] Q2: Obtain a set of vibration amplitude data S a in a preset period, and calculate the average vibration amplitude in the period to obtain average amplitude feature data A a ;

[0018] Q3: Obtain a set of noise level data S b in a preset period, and select the maximum noise level data in the period to obtain noise peak value feature data A b ;

[0019] Q4: Obtain thermal stability feature data A c by calculating the instantaneous change rate S c of the bearing temperature data;

[0020] Q5: Obtain environmental comprehensive feature data A d by multiplying test temperature data S e by test humidity data S f and then dividing by 100;

[0021] Q6: Calculate corrosion risk feature data A e based on corrosion gas concentration data S g , and the specific formula is: A e = log(1+S g );

[0022] Q7: Obtain thermal load difference feature data A f by subtracting the test temperature data from the bearing temperature data;

[0023] Q8: Based on the vibration amplitude data and the test speed data S d Calculate the speed vibration feature data A g The specific formula is:

[0024] Q9: Pack the average amplitude feature data, noise peak feature data, thermal stability feature data, environment comprehensive feature data, corrosion risk feature data, thermal load difference feature data and speed vibration feature data to obtain a feature vector;

[0025] The bearing performance calculation module is used for analysis based on the feature vector, and the bearing performance is calculated according to the multi-level nonlinear integrated model to obtain a performance feedback value;

[0026] Further, the step of analyzing based on the feature vector and calculating the bearing performance according to the multi-level nonlinear integrated model includes:

[0027] Step one: based on the feature vector and according to the multi-level nonlinear integrated model, a bearing performance calculation model is constructed;

[0028] Step two: based on the multiple heterogeneous sub-models in the multi-level nonlinear integrated model, the basic data and the feature vector are calculated, and the specific formula group is:

[0029]

[0030] The first environment coupling vector Ψ1, the second environment coupling vector Ψ2 and the third environment coupling vector Ψ3 are obtained respectively, wherein exp is an exponential function, and max is a maximum function;

[0031] Step three: based on the first environment coupling vector, the second environment coupling vector and the third environment coupling vector, the performance feedback value is calculated, and the specific formula is:

[0032]

[0033] The performance feedback value A is obtained h , wherein, is a dynamic feature weight, γ i is the feature data importance parameter of the i-th feature data, Ω is the environment severity index, F i is the i-th feature vector, tanh is the hyperbolic tangent function, and β is the environment sensitivity coefficient;

[0034] Step four: output the performance feedback value to the bearing performance feedback module;

[0035] The bearing performance feedback module is configured to perform hierarchical processing on the performance feedback value, and calculate a multi-dimensional index of the test bearing based on the performance feedback value and the feature vector to obtain a bearing evaluation report.

[0036] Further, the hierarchical processing of the performance feedback value includes:

[0037] based on the bearing performance threshold interval (W1, W2, W3);

[0038] When the performance feedback value is greater than or equal to W3, an excellent performance report is generated, when the performance feedback value is greater than or equal to W2 and less than W3, a good performance report is generated, when the performance feedback value is greater than or equal to W1 and less than W2, a general performance report is generated, and when the performance feedback value is less than W1, a dangerous performance report is generated.

[0039] The excellent performance report includes an indication that the current test bearing has excellent performance, no abnormal risk, and the staff should establish a standard maintenance suggestion for the batch of bearings;

[0040] The good performance report includes an indication that the current test bearing has stable performance, and there is slight wear, and the staff should establish a regular inspection suggestion for the batch of bearings;

[0041] The general performance report includes an indication that the current test bearing has decreased performance, and there is moderate wear, and the staff should establish a suggestion to shorten the regular inspection time of the batch of bearings to 70%;

[0042] The dangerous performance report includes an indication that the current test bearing has poor performance, and there is a risk of failure during use, and the staff should establish a suggestion to scrap the batch of bearings;

[0043] The excellent performance report, the good performance report, the general performance report and the dangerous performance report are packaged to obtain a performance feedback report.

[0044] The way of calculating the multi-dimensional index of the test bearing based on the performance feedback value and the feature vector includes:

[0045] E1: Weighted sum of the contribution values of the average amplitude feature data and the noise peak value feature data to obtain a dynamic evaluation value;

[0046] E2: Calculate the durability evaluation value B based on the thermal stability feature data and the rotational speed vibration feature data b The specific formula for calculating is: b B c =100-30×A g -20×(1-A c ).

[0047] E3: Calculate the reliability evaluation value B based on the corrosion risk feature data and the thermal load difference feature data c The specific formula for calculating is:c = max(0, 100 - 40 x A e - 30 x A f );

[0048] E4: Weighting and summing the power evaluation value, the durability evaluation value, the reliability evaluation value and the performance feedback value to obtain a comprehensive evaluation value;

[0049] E5: Integrating the performance feedback report, the power evaluation value, the durability evaluation value, the reliability evaluation value, the performance feedback value and the comprehensive evaluation value to obtain a bearing evaluation report;

[0050] The intelligent test adjustment module is configured to compare the bearing type data with a bearing test parameter rule base to output a parameter adjustment report;

[0051] Further, the comparison of the bearing type data with the bearing test parameter rule base includes:

[0052] The user inputs the bearing type data;

[0053] The bearing type data is compared with the bearing test parameter rule base;

[0054] The comparison result is output to obtain the parameter adjustment report;

[0055] The energy consumption optimization design module is configured to calculate a saved energy consumption value based on an energy saving mechanism and obtain an energy saving report in combination with a detailed description;

[0056] Further, the calculation of the saved energy consumption value based on the energy saving mechanism and the obtaining of the energy saving report in combination with the detailed description include:

[0057] The energy saving mechanism includes kinetic energy recovery and intelligent hibernation;

[0058] The specific calculation formula of the saved energy consumption of the kinetic energy recovery is: to obtain a recovered energy consumption value, wherein D a is the moment of inertia, η1 is the recovery efficiency, and T1 is the recovery duration;

[0059] The specific calculation formula of the saved energy consumption of the intelligent hibernation is: b = D b x η2 x T2 to obtain a hibernation energy consumption value, wherein D b is the idle power consumption, η2 is the hibernation efficiency, and T2 is the hibernation duration;

[0060] The sum of the recovered energy consumption value and the hibernation energy consumption value is calculated to obtain a comprehensive energy saving value;

[0061] The recovered energy consumption value, the hibernation energy consumption value and the comprehensive energy saving value are collected to obtain the energy saving report;

[0062] a system data management module configured to display the bearing evaluation report and the energy saving report through the visual panel, process the parameter adjustment report and the pressure monitoring report, and store the comprehensive data set in a database;

[0063] Further, the processing of the parameter adjustment report and the pressure monitoring report includes:

[0064] identifying data values in the parameter adjustment report, converting the data values into JSON instructions through Python, and sending the JSON instructions to a test bench executor through a REST API tool;

[0065] generating corresponding control commands through a script tool based on the stop instructions in the pressure monitoring report, and sending the control commands to an intelligent controller;

[0066] The comprehensive data set includes a test data set, an environmental data set, a feature vector, a performance feedback value, a bearing evaluation report, a parameter adjustment report, and an energy saving report.

[0067] Further, S1: collecting a test data set, the test data set including vibration amplitude data, noise level data, bearing temperature data, and test speed data;

[0068] S2: collecting an environmental data set, the environmental data set including test temperature data, test humidity data, and corrosion gas concentration data;

[0069] S3: monitoring bearing pressure to obtain a pressure monitoring report;

[0070] S4: preprocessing the test data set and the environmental data set, and extracting feature data;

[0071] S5: analyzing based on the feature vector, and calculating bearing performance based on a multi-level nonlinear integrated model to obtain a performance feedback value;

[0072] S6: classifying the performance feedback value, and calculating multi-dimensional indexes of the test bearing based on the performance feedback value and the feature vector to obtain a bearing evaluation report;

[0073] S7: comparing based on bearing type data and a bearing test parameter rule library to output a parameter adjustment report;

[0074] S8: calculating energy saving values based on an energy saving mechanism, and obtaining an energy saving report in combination with detailed descriptions;

[0075] S9: displaying the bearing evaluation report and the energy saving report through the visual panel, processing the parameter adjustment report and the pressure monitoring report, and storing the comprehensive data set in a database.

[0076] The technical effects and advantages of the belt decelerator bearing performance test system of the present application are as follows:

[0077] The present application collects a test data set, including vibration amplitude data, noise level data, bearing temperature data and test speed data, collects an environment data set, including test temperature data, test humidity data and corrosion gas concentration data, monitors the bearing pressure, obtains a pressure monitoring report, pre-processes the test data set and the environment data set, extracts feature data, analyzes based on the feature vector, calculates the bearing performance based on a multi-level nonlinear integrated model, obtains a performance feedback value, classifies the performance feedback value, calculates the multi-dimensional index of the test bearing based on the performance feedback value and the feature vector, obtains a bearing evaluation report, compares the bearing type data with the bearing test parameter rule base, outputs a parameter adjustment report, calculates the energy saving value based on the energy saving mechanism, and obtains an energy saving report in combination with the detailed description, displays the bearing evaluation report and the energy saving report through a visual panel, processes the parameter adjustment report and the pressure monitoring report, and stores the comprehensive data set in the database, so that the system can quantitatively calculate the bearing performance by combining multiple data, greatly improving the accuracy and data intuitiveness of the test compared with the traditional bearing test system. In addition, the present application integrates multi-dimensional evaluation of the performance feedback report, so that the staff can intuitively understand the performance state of the tested bearing while obtaining multi-dimensional bearing performance index values, greatly reducing the professional degree of manual labor required for bearing testing, and effectively improving the traceability of bearing performance weaknesses. It provides great convenience for seeking factors affecting poor bearing performance. At the same time, by setting the bearing test rule base for bearings of different purposes, the system can provide corresponding test conditions for bearings of various purpose types, greatly improving the flexibility of the system. Finally, through the energy saving mechanism, the high energy consumption of the traditional test system effectively reduces the high test cost of the enterprise, thereby effectively improving the economy of the system. Overall, the present application has the significant advantages of high precision of bearing test feedback, good multi-dimensional evaluation effect and strong economic efficiency of system use. BRIEF DESCRIPTION OF DRAWINGS

[0078] Figure 1 A schematic diagram of a belt decelerator bearing performance test system of the present application;

[0079] Figure 2 A schematic diagram of a belt decelerator bearing performance test method of the present application. DETAILED DESCRIPTION

[0080] Clearly, the described embodiments are only some, but not all, embodiments of the present application. Based on the embodiments in the present application, persons having ordinary skill in the art can obtain all the other embodiments from the described embodiments without creative effort, and all the embodiments shall fall within the scope of the present application.

[0081] The terminology used in the embodiments of the present application is merely for the purpose of describing particular embodiments and is not intended to limit the present application. The singular forms "a," "an," and "the" used in the embodiments of the present application are intended to include the plural forms as well, unless the context clearly indicates otherwise. "Plural" generally includes at least two.

[0082] Depending on the context, the word "if" as used herein can be interpreted to mean "when" or "while" or "in response to determining" or "in response to detecting." Similarly, the phrase "if it is determined" or "if [a stated condition or event] is detected" can be interpreted to mean "upon determining" or "in response to determining" or "upon detecting [the stated condition or event]" or "in response to detecting [the stated condition or event]."

[0083] In addition, the sequence of steps in each of the following method embodiments is merely an example, and is not strictly limited.

[0084] In fact, the server equipment deployed by the belt decelerator bearing performance test system can be composed of one or more devices. The belt decelerator bearing performance test system can be implemented as a business instance, a virtual machine, or a hardware device. For example, the belt decelerator bearing performance test system can be implemented as a business instance deployed on one or more devices in a cloud node. In short, the belt decelerator bearing performance test system can be understood as a software deployed on a cloud node, which is used to provide a belt decelerator bearing performance test system for each user terminal. Alternatively, the belt decelerator bearing performance test system can also be implemented as a virtual machine deployed on one or more devices in a cloud node. The virtual machine has application software installed therein for managing each user terminal. Alternatively, the belt decelerator bearing performance test system can also be implemented as a server composed of a plurality of same or different types of hardware devices, and one or more hardware devices are provided to provide a belt decelerator bearing performance test system for each user terminal.

[0085] In an implementation form, the belt decelerator bearing performance test system and the user end are adapted to each other. That is, the belt decelerator bearing performance test system is installed as an application on a cloud service platform, and the user end is a client that establishes a communication connection with the application; or the belt decelerator bearing performance test system is implemented as a website, and the user end is implemented as a webpage; or the belt decelerator bearing performance test system is implemented as a cloud service platform, and the user end is implemented as an applet in an instant messaging application.

[0086] As shown in Figure 1 , it is a system architecture diagram of the belt decelerator bearing performance test system provided by an embodiment of the application.

[0087] The belt decelerator bearing performance test system can be set in a cloud server, and in an implementation form, can be one or more service devices, or can be installed as an application on a cloud (such as a server of a mobile service operator, a server cluster, etc.), or can be developed as a website. According to the functions implemented, the belt decelerator bearing performance test system can include a test data acquisition module, an environmental data acquisition module, a data interaction mining module, a bearing performance calculation module, a bearing performance feedback module, a multi-dimensional evaluation system module, an intelligent test adjustment module, an energy consumption optimization design module, and a system data management module. The modules of the application can also be referred to as units, which refer to a series of computer program segments that can be executed by an electronic device processor and can complete a fixed function, and are stored in the memory of the electronic device.

[0088] In the embodiment of the application, each of the above modules in the belt decelerator bearing performance test system can be independently implemented and called by other modules. Here, calling can be understood as connecting a module to multiple modules of another type and providing corresponding services to the connected multiple modules. For example, the sharing evaluation module can call the same information acquisition module to obtain the information collected by the information acquisition module. Based on the above characteristics, the belt decelerator bearing performance test system provided by the embodiment of the application can adjust the application scope of the belt decelerator bearing performance test system architecture by increasing modules and directly calling without modifying program codes, realize cluster-level expansion, and achieve the purpose of quickly and flexibly expanding the belt decelerator bearing performance test system. In actual application, the above modules can be set in the same device or different devices, or can be set in a virtual device, such as a service instance in a cloud server.

[0089] Embodiment 1

[0090] As shown in Figure 1 , the belt decelerator bearing performance test system provided by the embodiment includes:

[0091] The test data collection module is configured to collect a test data set, which includes vibration amplitude data, noise level data, bearing temperature data, and test rotating speed data.

[0092] It should be noted that the vibration amplitude data is obtained by collecting the amplitude value of the specified bearing base through the piezoelectric acceleration sensor; the noise level data is obtained by collecting the sound pressure value within one meter of the specified bearing test equipment through the integrating sound level meter; the bearing temperature data is obtained by collecting the surface temperature value of the outer ring of the specified test bearing through the infrared thermal imager; and the test rotating speed data is obtained by collecting the rotating speed value of the specified test bearing through the photoelectric encoder.

[0093] The environmental data collection module is configured to collect an environmental data set, which includes test temperature data, test humidity data, and corrosion gas concentration data.

[0094] It should be noted that the test temperature data and the test humidity data are obtained by respectively collecting the temperature value and the humidity value in the specified test equipment through the digital temperature and humidity recorder; and the corrosion gas concentration data is obtained by collecting the sulfur dioxide concentration value at the air inlet of the specified bearing test area through the electrochemical gas sensor.

[0095] The pressure monitoring module is configured to monitor the bearing pressure to obtain a pressure monitoring report.

[0096] Further, the manner of monitoring the bearing pressure includes:

[0097] The dynamic pressure index is obtained by calculating the product of the vibration amplitude data, the test rotating speed data, and the pressure coefficient.

[0098] When the dynamic pressure index is greater than or equal to the pressure safety threshold, the pressure monitoring report is generated; and when the dynamic pressure value is less than the pressure safety threshold, the test data set and the environmental data set are output to the data interaction mining module.

[0099] It should be noted that the pressure safety threshold is an upper limit value of the bearing pressure set according to different types of test bearings, for example, the pressure safety threshold is 100; and the vibration amplitude data and the test rotating speed data are specific values after dimension elimination.

[0100] The pressure monitoring report includes a stop instruction.

[0101] The stop instruction includes a group of characters representing the shutdown of the performance test equipment.

[0102] The data interaction mining module is configured to pre-process the test data set and the environmental data set, and extract feature data to obtain a feature vector.

[0103] Further, the step of pre-processing the test data set and the environment data set and extracting feature data includes:

[0104] Q1: Data cleaning is completed on all sub-data items in the basic data set by removing outliers, and all sub-data items in the basic data set are normalized to the range of [0, 1] according to the normalization formula;

[0105] It should be explained that removing outliers means that, for example, the noise level data is negative; the basic data set includes the test data set and the environment data set; and the specific expression formula of the normalization formula is: where X new is the normalized value, X is any sub-data item of the basic data, X max is the historical maximum value of the sub-data item, and X min is the historical minimum value of the sub-data item; normalization is used to eliminate the dimensions of all sub-data items in the basic data set;

[0106] Q2: Obtain a group of vibration amplitude data S a in a preset period, and calculate the average vibration amplitude in the period to obtain average amplitude feature data A a ;

[0107] It should be explained that the preset period refers to the time period of the artificial device, for example, the past 30 minutes, one hour or three hours as a period;

[0108] Q3: Obtain a group of noise level data S b in a preset period, and select the maximum noise level data in the period to obtain noise peak value feature data A b ;

[0109] Q4: Obtain thermal stability feature data A c by calculating the instantaneous change rate S c of the bearing temperature data;

[0110] Q5: Obtain environment comprehensive feature data A d by calculating test temperature data S e times test humidity data S f and then dividing by 100;

[0111] Q6: Calculate corrosion risk feature data A e based on corrosion gas concentration data S g , and the specific formula for calculation is: A e = log(1+S g );

[0112] Q7: Obtain thermal load difference feature data Af ;

[0113] Q8: Based on the vibration amplitude data and the test speed data S d Calculate the speed vibration feature data A g , the specific formula is:

[0114] Q9: Pack the average amplitude feature data, noise peak feature data, thermal stability feature data, environmental comprehensive feature data, corrosion risk feature data, thermal load difference feature data and speed vibration feature data to get the feature vector;

[0115] It needs to be explained that the use of sub-data items in the basic data involved in steps Q2 to Q8 and all subsequent modules is the data value after data cleaning and data normalization;

[0116] The bearing performance calculation module is used to analyze based on the feature vector, and calculate the bearing performance according to the multi-level nonlinear integrated model to obtain the performance feedback value;

[0117] Further, the step of analyzing based on the feature vector and calculating the bearing performance according to the multi-level nonlinear integrated model includes:

[0118] Step one: Based on the feature vector, and according to the multi-level nonlinear integrated model, a bearing performance calculation model is constructed;

[0119] Step two: Based on the multiple heterogeneous sub-models in the multi-level nonlinear integrated model, the basic data and the feature vector are calculated, and the specific formula group is:

[0120]

[0121] The first environmental coupling vector Ψ1, the second environmental coupling vector Ψ2 and the third environmental coupling vector Ψ3 are obtained respectively, wherein exp is an exponential function, and max is a maximum function;

[0122] It needs to be explained that the exponential function is used to convert the output value immediately inside the parentheses into an exponential operation with the natural constant e as the base; the maximum function is used to select the maximum value immediately inside the parentheses as the output value;

[0123] Step three: Based on the first environmental coupling vector, the second environmental coupling vector and the third environmental coupling vector, the performance feedback value is calculated, and the specific formula is:

[0124]

[0125] The performance feedback value A h , wherein, is the dynamic feature weight, γ iis the feature data importance parameter of the ith feature data, Ω is the environment severity index, F i is the ith feature vector, tanh is the hyperbolic tangent function, and β is the environment sensitivity coefficient.

[0126] It should be explained that the hyperbolic tangent function is used to constrain the output value immediately inside the brackets within the range of [-1, 1];

[0127] Step four: output the performance feedback value to the bearing performance feedback module;

[0128] The bearing performance feedback module is used to process the performance feedback value in stages, and calculate the multi-dimensional index of the test bearing based on the performance feedback value and the feature vector to obtain a bearing evaluation report.

[0129] Further, the way of processing the performance feedback value in stages includes:

[0130] Based on the bearing performance threshold interval (W1, W2, W3);

[0131] It should be explained that the bearing performance threshold interval is used to evaluate the bearing test performance grading standard, which is obtained by manual equipment and input into the system;

[0132] When the performance feedback value is greater than or equal to W3, an excellent performance report is generated, when the performance feedback value is greater than or equal to W2 and less than W3, a good performance report is generated, when the performance feedback value is greater than or equal to W1 and less than W2, a general performance report is generated, and when the performance feedback value is less than W1, a risk performance report is generated;

[0133] The excellent performance report includes an explanation that the current test bearing performance is excellent, there is no abnormal risk, and the staff should establish a standard maintenance suggestion for the batch of bearings;

[0134] The good performance report includes an explanation that the current test bearing performance is stable, there is slight wear, and the staff should establish a regular inspection suggestion for the batch of bearings;

[0135] The general performance report includes an explanation that the current test bearing performance is declining, there is moderate wear, and the staff should establish a regular inspection time of the batch of bearings to be shortened to 70% of the original time;

[0136] The dangerous performance report includes an explanation that the current test bearing performance is poor, there is a risk of failure during use, and the staff should establish a scrap suggestion for the batch of bearings;

[0137] Packaging the excellent performance report, the good performance report, the general performance report and the dangerous performance report to obtain a performance feedback report;

[0138] The way of calculating the multi-dimensional index of the test bearing based on the performance feedback value and the feature vector includes:

[0139] E1: Weighted sum of the contribution values of the average amplitude feature data and the noise peak feature data to obtain a power evaluation value;

[0140] It needs to be explained that the contribution value in this step refers to the value obtained by subtracting the average amplitude feature data from 1 and subtracting the noise peak feature data from 1, for example, if the average amplitude feature data is 0.2, the contribution value of the average amplitude feature data is 0.8; the weighting in this step is based on a full score of 100, for example, the weight factor of the average amplitude feature data is 0.5, and the final value of the weight factor is 50;

[0141] E2: Calculate the durability evaluation value B based on the thermal stability feature data and the rotational speed vibration feature data b , the specific formula for calculation is: B b = 100-30xA c -20x(1-A g );

[0142] E3: Calculate the reliability evaluation value B based on the corrosion risk feature data and the thermal load difference feature data c , the specific formula for calculation is: B c =max(0, 100-40xA e -30xA f );

[0143] E4: Weighted sum of the power evaluation value, the durability evaluation value, the reliability evaluation value and the performance feedback value to obtain a comprehensive evaluation value;

[0144] E5: Integrate the performance feedback report, the power evaluation value, the durability evaluation value, the reliability evaluation value, the performance feedback value and the comprehensive evaluation value to obtain a bearing evaluation report;

[0145] The intelligent test adjustment module is used to compare the bearing type data with the bearing test parameter rule base to output a parameter adjustment report;

[0146] Further, the way of comparing the bearing type data with the bearing test parameter rule base includes:

[0147] The user inputs the bearing type data;

[0148] It needs to be explained that the bearing type data refers to the data set obtained by assigning values to bearings of different application types and collecting them, for example, a deep groove ball bearing is assigned a value of 1 and a tapered roller bearing is assigned a value of 2;

[0149] Compare the bearing type data with the bearing test parameter rule base;

[0150] It needs to be explained that the bearing test parameter rule base refers to the pre-set test parameters according to the different bearing type data, for example, when the bearing type data is 1, the recommended test rotating speed data is 1500;

[0151] Output the comparison result to obtain a parameter adjustment report;

[0152] The energy consumption optimization design module is configured to calculate a saved energy consumption value based on an energy saving mechanism, and obtain an energy saving report in combination with the detailed description;

[0153] Further, the way of calculating a saved energy consumption value based on an energy saving mechanism and obtaining an energy saving report in combination with the detailed description includes:

[0154] The energy saving mechanism includes kinetic energy recovery and intelligent hibernation;

[0155] The specific calculation formula of the kinetic energy recovery saved energy consumption is: to obtain a recovered energy consumption value, wherein D a is the moment of inertia, η1 is the recovery efficiency, and T1 is the recovery duration;

[0156] The specific calculation formula of the intelligent hibernation saved energy consumption is: b b to obtain a hibernation energy consumption value, wherein D b is the idle power consumption, η2 is the hibernation efficiency, and T2 is the hibernation duration;

[0157] The comprehensive energy saving value is obtained by calculating the sum of the recovered energy consumption value and the hibernation energy consumption value;

[0158] The energy saving report is obtained by collecting the recovered energy consumption value, the hibernation energy consumption value, and the comprehensive energy saving value;

[0159] The system data management module is configured to display the bearing evaluation report and the energy saving report through a visual panel, process the parameter adjustment report and the pressure monitoring report, and store the comprehensive data set in a database;

[0160] Further, the way of processing the parameter adjustment report and the pressure monitoring report includes:

[0161] The data values in the parameter adjustment report are identified, the data values are converted into JSON instructions through Python, and the JSON instructions are sent to the test bench executor through a REST API tool;

[0162] The stop instructions in the pressure monitoring report are used to generate corresponding control commands through a script tool, and the control commands are sent to the intelligent controller;

[0163] ​The comprehensive data set includes a test data set, an environment data set, a feature vector, a performance feedback value, a bearing evaluation report, a parameter adjustment report and an energy saving report;

[0164] In this embodiment, the beneficial effects are achieved by collecting a test data set, the test data set including vibration amplitude data, noise level data, bearing temperature data and test speed data, collecting an environment data set, the environment data set including test temperature data, test humidity data and corrosion gas concentration data, preprocessing the test data set and the environment data set, and extracting feature data, analyzing based on the feature vector, calculating the bearing performance based on the multi-level nonlinear integrated model, obtaining the performance feedback value, classifying the performance feedback value, calculating the multi-dimensional index of the test bearing based on the performance feedback value and the feature vector, obtaining the bearing evaluation report, calculating the multi-dimensional index of the test bearing based on the performance feedback value and the feature vector, integrating the performance feedback report, obtaining the bearing evaluation report, comparing the bearing type data with the bearing test parameter rule library, outputting the parameter adjustment report, calculating the energy saving value based on the energy saving mechanism, and obtaining the energy saving report in combination with the detailed description, displaying the bearing evaluation report and the energy saving report through the visual panel, processing the parameter adjustment report and the pressure monitoring report, and storing the comprehensive data set in the database, so that the system can quantitatively calculate the bearing performance by combining multiple data. Compared with the traditional bearing test system, the accuracy and data intuitiveness of the test are greatly improved. In addition, the present application also integrates multi-dimensional evaluation of the performance feedback report, so that the staff can intuitively understand the performance state of the tested bearing while obtaining multi-dimensional bearing performance index values, greatly reducing the professional degree of manual bearing test, and effectively improving the traceability of bearing performance weaknesses. It provides great convenience for seeking factors affecting poor bearing performance. At the same time, by setting the bearing test rule library for bearings of different purposes, the system can provide corresponding test conditions for bearings of various purpose types, greatly improving the flexibility of the system. Finally, through the energy saving mechanism, the high energy consumption of the traditional test system is effectively reduced, thereby effectively improving the economy of the system. Overall, the present application has the significant advantages of high precision of bearing test feedback, good multi-dimensional evaluation effect and strong economic efficiency of system use.

[0165] Embodiment 2

[0166] Please refer to Figure 2 The method comprises the following steps: S1: collecting a test data set, the test data set including vibration amplitude data, noise level data, bearing temperature data and test speed data;

[0167] S2: Collect environmental data sets, which include test temperature data, test humidity data, and corrosive gas concentration data;

[0168] S3: Monitor the bearing pressure and obtain a pressure monitoring report;

[0169] S4: Preprocess the test dataset and environment dataset and extract feature data;

[0170] S5: Analyze the eigenvectors and calculate the bearing performance based on the multi-level nonlinear integrated model to obtain performance feedback values;

[0171] S6: performing graded processing on the performance feedback values, and calculating multi-dimensional indicators of the test bearing based on the performance feedback values ​​and the characteristic vectors to obtain a bearing evaluation report;

[0172] S7: Compare the bearing type data with the bearing test parameter rule library and output a parameter adjustment report;

[0173] S8: Calculate the energy saving value based on the energy saving mechanism, and obtain an energy saving report based on the detailed description;

[0174] S9: Display the bearing evaluation report and energy saving report through the visual panel, process the parameter adjustment report and pressure monitoring report, and store the comprehensive data set in the database.

[0175] The above description is merely illustrative of certain exemplary embodiments of the present invention. It goes without saying that those skilled in the art will be able to modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and description are illustrative in nature and should not be construed as limiting the scope of protection of the present invention.

Claims

1. A belt reducer bearing performance testing system, characterized in that: The system includes: a bearing performance calculation module, a bearing performance feedback module, a multi-dimensional evaluation system module, an intelligent test and adjustment module, and an energy consumption optimization design module, wherein: The pressure monitoring module is used to monitor the bearing pressure and obtain a pressure monitoring report; The bearing performance calculation module is used to perform analysis based on the characteristic vector and calculate the bearing performance according to the multi-level nonlinear integrated model to obtain the performance feedback value; The bearing performance feedback module is used to perform classification processing on the performance feedback values ​​and calculate the multi-dimensional indicators of the test bearing based on the performance feedback values ​​and the characteristic vectors to obtain a bearing evaluation report; The intelligent test and adjustment module is used to compare the bearing type data with the bearing test parameter rule library and output a parameter adjustment report; The energy consumption optimization design module is used to calculate the energy saving value based on the energy saving mechanism and obtain an energy saving report in combination with the detailed description.

2. A belt reducer bearing performance testing system according to claim 1, characterized in that: The system also includes: a test data acquisition module, an environmental data acquisition module, a data interaction mining module and a system data management module, wherein: The test data acquisition module is used to acquire a test data set, which includes vibration amplitude data, noise level data, bearing temperature data and test speed data; The environmental data acquisition module is used to collect environmental data sets, which include test temperature data, test humidity data and corrosive gas concentration data; The data interaction mining module is used to preprocess the test data set and the environment data set and extract feature data; The system data management module is used to display the bearing evaluation report and energy saving report through a visual panel, process the parameter adjustment report and pressure monitoring report, and store the comprehensive data set in a database.

3. A belt reducer bearing performance testing system according to claim 1, characterized in that: The steps of preprocessing the test data set and the environmental data set and extracting feature data include: The methods of monitoring the bearing pressure include: Calculate the product of vibration amplitude data, test speed data and pressure coefficient to obtain dynamic pressure index; When the dynamic pressure index is greater than or equal to the pressure safety threshold, a pressure monitoring report is generated. When the dynamic pressure value is less than the pressure safety threshold, the test data set and the environmental data set are output to the data interaction mining module. The pressure monitoring report includes a stop instruction; The stop command consists of a set of characters that represent shutting down the performance test equipment.

4. A belt reducer bearing performance testing system according to claim 2, characterized in that: The steps of preprocessing the test dataset and environment dataset and extracting feature data include: Q1: Complete data cleaning of all sub-data items in the basic data set by removing outliers, and normalize all sub-data items in the basic data set to the range of [0, 1] according to the normalization formula; Q2: Get a set of vibration amplitude data S within a preset period a , and calculate the average vibration amplitude within the period to obtain the average amplitude characteristic data A a ; Q3: Obtain a set of noise level data S within a preset period b , and select the maximum noise level data in the period to obtain the noise peak characteristic data A b ; Q4: By calculating the instantaneous rate of change S of the bearing temperature data c , get thermal stability characteristic data A c ; Q5: Calculate the test temperature data S e Multiply by the test humidity data S f Divide by 100 to get the comprehensive environmental characteristic data A d ; Q6: Based on the corrosive gas concentration data S g Calculate corrosion risk characteristic data A e The specific calculation formula is: A e =log(1+S g ); Q7: By subtracting the test temperature data from the bearing temperature data, the thermal load difference characteristic data A is obtained. f ; Q8: Based on the vibration amplitude data and test speed data S d Calculate the speed vibration characteristic data A g , the specific calculation formula is: Q9: Package the average amplitude characteristic data, noise peak characteristic data, thermal stability characteristic data, environmental comprehensive characteristic data, corrosion risk characteristic data, thermal load difference characteristic data and speed vibration characteristic data to obtain a characteristic vector.

5. A belt reducer bearing performance testing system according to claim 1, characterized in that: The steps for analyzing the eigenvectors and calculating the bearing performance based on the multi-level nonlinear integrated model include: Step 1: Based on the eigenvector and the multi-level nonlinear integrated model, a bearing performance calculation model is constructed; Step 2: Calculate the basic data and eigenvectors based on the multiple heterogeneous sub-models in the multi-layer set nonlinear integration model. The specific formula group for the calculation is: The first environment coupling vector Ψ1, the second environment coupling vector Ψ2 and the third environment coupling vector Ψ3 are obtained respectively, where exp is an exponential function and max is a maximization function; Step 3: Calculate the performance feedback value based on the first environment coupling vector, the second environment coupling vector, and the third environment coupling vector. The specific calculation formula is: Get performance feedback value A h ,in, is the dynamic feature weight, γ i is the characteristic data importance parameter of the i-th characteristic data, Ω is the environmental severity index, F i is the eigenvector of the i-th item, tanh is the hyperbolic tangent function, and β is the environmental sensitivity coefficient; Step 4: Output the performance feedback value to the bearing performance feedback module.

6. A belt reducer bearing performance testing system according to claim 1, characterized in that: The methods for grading performance feedback values ​​include: Based on bearing performance threshold intervals (W1, W2, W3); When the performance feedback value is greater than or equal to W3, an excellent performance report is generated; when the performance feedback value is greater than or equal to W2 and less than W3, a good performance report is generated; when the performance feedback value is greater than or equal to W1 and less than W2, a general performance report is generated; when the performance feedback value is less than W1, a risk performance report is generated; The excellent performance report includes a statement that the current tested bearing has excellent performance and no abnormal risks, and asks staff to establish standard maintenance recommendations for this batch of bearings; A good performance report includes a statement that the current tested bearing has stable performance and slight wear, and asks staff to establish regular inspection recommendations for this batch of bearings; The general performance report includes a description of the deterioration in the performance of the currently tested bearings, the presence of moderate wear, and a recommendation that the staff shorten the scheduled inspection period for this batch of bearings to 70 percent; The hazardous performance report includes a description of the poor performance of the currently tested bearings and the risk of failure during use. The staff is asked to create a scrapping recommendation for the bearings in this batch. Package excellent performance reports, good performance reports, average performance reports and dangerous performance reports to obtain performance feedback reports; Methods for calculating multi-dimensional indicators of the tested bearing based on performance feedback values ​​and eigenvectors include: E1: Perform weighted summation on the contribution values ​​of the average amplitude characteristic data and the noise peak characteristic data to obtain the dynamic evaluation value; E2: Calculate the durability evaluation value B based on the thermal stability characteristic data and the speed vibration characteristic data b The specific calculation formula is: b =100-30×A c -20×(1-A g ); E3: Calculate the reliability evaluation value B based on the corrosion risk characteristic data and the thermal load difference characteristic data c The specific calculation formula is: c =max(0,100-40×A e -30×A f ); E4: Perform weighted summation of the power evaluation value, durability evaluation value, reliability evaluation value, and performance feedback value to obtain a comprehensive evaluation value; E5: Integrate the performance feedback report, power evaluation value, durability evaluation value, reliability evaluation value, performance feedback value and comprehensive evaluation value to obtain the bearing evaluation report.

7. A belt reducer bearing performance testing system according to claim 1, characterized in that: The methods for comparing bearing type data with the bearing test parameter rule library include: The user enters bearing type data; Compare bearing type data with the bearing test parameter rule library; Output the comparison results and obtain the parameter adjustment report.

8. A belt reducer bearing performance testing system according to claim 1, characterized in that: Methods for calculating energy savings based on energy saving mechanisms and obtaining energy savings reports in combination with detailed descriptions include: Energy-saving mechanisms include kinetic energy recovery and intelligent sleep; The specific calculation formula for energy saving by kinetic energy recovery is: Get the recovery energy consumption value, where D a is the moment of inertia, η1 is the recovery efficiency, and T1 is the recovery time; The specific calculation formula for energy saving of intelligent sleep is: C b =D b ×η2×T2, we get the dormant energy consumption value, where D b is the idle power consumption, η2 is the sleep efficiency, and T2 is the sleep duration; By calculating the sum of the recovery energy consumption value and the dormant energy consumption value, the comprehensive energy saving value is obtained; Collect the recycling energy consumption value, dormant energy consumption value and comprehensive energy saving value to obtain an energy saving report.

9. A belt reducer bearing performance testing system according to claim 2, characterized in that: The methods for processing parameter adjustment reports and pressure monitoring reports include: Identify the data values ​​in the parameter adjustment report, convert the data values ​​into JSON instructions using Python, and send the JSON instructions to the test bench executor through the REST API tool; Generate corresponding control commands from the stop instructions in the pressure monitoring report through the script tool, and send the control commands to the intelligent controller; Generate corresponding control commands from the stop instructions in the pressure monitoring report through the script tool, and send the control commands to the intelligent controller; The comprehensive data set includes test data set, environmental data set, feature vector, performance feedback value, bearing evaluation report, parameter adjustment report and energy saving report.

10. A belt reducer bearing performance testing method, implemented by a belt reducer bearing performance testing system according to any one of claims 1 to 9, characterized in that: The following steps are included: S1: Collect test data sets, including vibration amplitude data, noise level data, bearing temperature data, and test speed data; S2: Collect environmental data sets, which include test temperature data, test humidity data, and corrosive gas concentration data; S3: Monitor the bearing pressure and obtain a pressure monitoring report; S4: Preprocess the test dataset and environment dataset and extract feature data; S5: Analyze the eigenvectors and calculate the bearing performance based on the multi-level nonlinear integrated model to obtain performance feedback values; S6: performing graded processing on the performance feedback values, and calculating multi-dimensional indicators of the test bearing based on the performance feedback values ​​and the characteristic vectors to obtain a bearing evaluation report; S7: Compare the bearing type data with the bearing test parameter rule library and output a parameter adjustment report; S8: Calculate the energy saving value based on the energy saving mechanism, and obtain an energy saving report based on the detailed description; S9: Display the bearing evaluation report and energy saving report through the visual panel, process the parameter adjustment report and pressure monitoring report, and store the comprehensive data set in the database.

Images