A bearing temperature early warning method and system based on the Internet of Things

Abstract

The present invention discloses a bearing temperature early warning method and system based on the Internet of Things, and relates to the field of bearing temperature testing technology. The bearing temperature early warning method based on the Internet of Things includes the following steps: data collection; abnormality analysis and deviation analysis; step-by-step adjustment; and early warning operation. The present invention obtains a temperature anomaly index and an operating environment deviation index by performing abnormality analysis and deviation analysis on the collected bearing temperature and operating environment data, respectively, marks the abnormal moment by the temperature anomaly index and the preset abnormal threshold, and then determines whether to perform step-by-step adjustment by the operating environment deviation index and the preset deviation threshold. Finally, an early warning operation is performed according to the temperature anomaly index, thereby achieving the effect of improving the accuracy of bearing temperature anomaly monitoring, and solving the problem of insufficient correlation between operating environment changes and temperature anomalies in the bearing temperature monitoring process in the prior art.

Description

Technical Field

[0001] The present invention relates to the technical field of bearing temperature testing, and in particular to a bearing temperature early warning method and system based on the Internet of Things. Background Art

[0002] With the development of industrial automation, the operational stability and safety of mechanical equipment have become one of the key factors in enterprise production. Bearings are important components of mechanical equipment. During the operation of mechanical equipment, bearings are subjected to huge loads and continuous friction. These factors can easily lead to bearing failures and affect the entire mechanical equipment. Usually, bearing failures are often accompanied by abnormal temperature increases. Abnormal temperature changes are early signs of insufficient lubrication, increased wear or other potential failures inside the bearing. Therefore, real-time monitoring of bearing temperature and early warning are of great practical significance for preventing equipment failures. By introducing a bearing temperature early warning system, enterprises can achieve real-time monitoring of bearing temperature and detect temperature abnormalities in a timely manner. This not only helps to take effective maintenance measures when problems first occur to prevent further deterioration of the fault, but also can significantly reduce downtime caused by sudden equipment failures.

[0003] Existing bearing temperature early warning systems mostly use traditional temperature sensors for direct measurement. This method collects temperature data in real time and transmits it to the early warning system by installing the temperature sensor near the bearing or on the bearing seat. The early warning system compares this data with the set temperature threshold. When the temperature exceeds the preset safety threshold, the early warning system will trigger an alarm signal to remind the preset personnel to take necessary measures. In addition, some advanced early warning systems also combine data analysis and machine learning algorithms to model based on historical temperature data, thereby obtaining flexible temperature thresholds and warning of possible abnormal conditions in advance.

[0004] For example, the invention patent with announcement number: CN114813105B announces a gearbox fault warning method and system based on working condition similarity assessment, including: automatically identifying the historical working condition that is most similar to the current working condition of the gearbox, and analyzing the similarity between the historical monitoring data and the current monitoring data under the same or similar working conditions to achieve fault warning of the gearbox monitoring parameters; based on the proposed historical data longitudinal comparison and analysis method, respectively establish a gearbox oil temperature warning model, a front-end bearing temperature warning model, a gearbox rear-end bearing temperature warning model, a gearbox pump outlet pressure warning model and a gearbox inlet pressure warning model, and by integrating the output results of each warning model, a comprehensive evaluation of the gearbox operating status is achieved.

[0005] For example, the invention patent with announcement number CN108051211B discloses a method for early warning and diagnosis of the temperature of the main bearing of a wind turbine generator set, comprising: (1) collecting monitoring data of a wind farm; (2) acquiring parameters related to the temperature of the main bearing of a wind turbine generator set; (3) establishing a normal temperature model of the main bearing of a wind turbine generator set; (4) calculating the theoretical value of the real-time normal temperature of the main bearing of a wind turbine generator set: selecting the real-time values ​​of the parameters related to the temperature of the main bearing of the wind turbine generator set in step (2) from the real-time data collected in step (1), inputting the real-time values ​​of the above-mentioned related parameters into the neural network after training in step (3) and generating a normal temperature value of the main bearing of the wind turbine generator set; and (5) judging whether the real-time temperature of the main bearing of the wind turbine generator set is abnormal.

[0006] However, in the process of implementing the technical solution of the invention in the embodiments of the present application, the present application found that the above technology has at least the following technical problems:

[0007] In the prior art, the bearing temperature warning system usually relies on a fixed temperature threshold or a simple temperature change trend to judge the working status of the bearing. As a result, when the operating environment changes, the bearing temperature warning system cannot accurately identify the real temperature anomaly. There is a problem of insufficient correlation between the operating environment changes and temperature anomalies during the bearing temperature monitoring process. Summary of the invention

[0008] The embodiments of the present application provide a bearing temperature early warning method and system based on the Internet of Things, thereby solving the problem of insufficient correlation between operating environment changes and temperature anomalies in the bearing temperature monitoring process in the prior art, and improving the accuracy of bearing temperature anomaly monitoring.

[0009] The embodiment of the present application provides a bearing temperature early warning method based on the Internet of Things, comprising the following steps: S1, performing data collection at a preset time to obtain the bearing temperature and operating environment data of the bearing to be tested, wherein the operating environment data includes environmental data and running data; S2, obtaining a temperature anomaly index of the bearing to be tested by performing an abnormal analysis on the operating environment data and the bearing temperature, performing a deviation analysis on the operating environment data at the preset time to obtain an operating environment deviation index of the bearing to be tested, and judging whether the temperature anomaly index is greater than a preset abnormal threshold value. If the temperature anomaly index is greater than the preset abnormal threshold value, marking the corresponding preset time as an abnormal time and executing S3, otherwise no processing is performed, wherein the temperature anomaly index is used to describe the degree of actual temperature anomaly of the bearing to be tested, and the operating environment deviation index is used to describe the degree of deviation of the operating environment data compared with the preset operating environment; S3, judging whether the obtained operating environment deviation index is greater than the preset deviation threshold value. If the operating environment deviation index is greater than the preset deviation threshold value, performing step-by-step adjustment, otherwise executing S4; S4, performing an early warning operation according to the temperature anomaly index.

[0010] Furthermore, the process of collecting data at a preset time to obtain the bearing temperature and operating environment data of the bearing to be tested is as follows: collecting the bearing temperature of the bearing to be tested at a preset time through a temperature sensor; collecting the environmental data of the bearing to be tested at a preset time through an environmental sensor, and the environmental data includes the ambient temperature and the ambient humidity; collecting the operating data of the bearing to be tested at a preset time through an operating status sensor, and the operating data includes the real-time load and bearing speed.

[0011] Furthermore, the specific process of obtaining the temperature anomaly index of the bearing to be tested by performing abnormal analysis on the operating environment data and the bearing temperature is as follows: obtaining a state parameter weight factor from a preset database, wherein the state parameter weight factor includes a first weight factor and a second weight factor; obtaining a bearing temperature threshold and an operation limit parameter from a preset database, wherein the operation limit parameter includes an upper limit of ambient humidity, an upper limit of ambient temperature, an upper limit of bearing speed, and an upper limit of real-time load; obtaining the temperature state parameter of the bearing to be tested at a preset time according to the bearing temperature, the operating environment data, the operation limit parameter, and the state parameter weight factor at a preset time; obtaining the temperature anomaly index of the bearing to be tested through the temperature state parameter and the bearing temperature threshold, wherein the specific calculation formula of the temperature anomaly index is as follows:

[0012]

[0013] Where n is the number of the preset time, n = 1, 2, ..., N, N is the total number of preset time, AT n is the temperature state parameter of the bearing to be tested at the nth preset time, T n is the bearing temperature of the bearing to be tested at the nth preset time, H n is the ambient humidity of the bearing to be tested at the nth preset time, P n is the ambient temperature of the bearing to be tested at the nth preset time, R n is the bearing speed of the bearing to be tested at the nth preset moment, L n is the real-time load of the bearing to be tested at the nth preset moment, H max is the upper limit of ambient humidity, P max is the upper limit of ambient temperature, R max is the upper limit of bearing speed, L max is the upper limit of real-time load, σ is the first weight factor, ρ is the second weight factor, TEI n is the temperature anomaly index of the bearing to be tested at the nth preset time, and T0 is the bearing temperature threshold.

[0014] Furthermore, the specific process of performing deviation analysis on the operating environment data at a preset time to obtain the operating environment deviation index of the bearing to be tested is as follows: obtaining a deviation index weight from a preset database, the deviation index weight including a first index weight, a second index weight, a third index weight and a fourth index weight; extracting historical operating environment data from a preset database, the historical operating environment data including historical humidity, historical temperature, historical speed and historical load; performing statistical analysis on the historical operating environment data to obtain reference operating environment data and operating environment data reference deviation, the reference operating environment data including reference humidity, reference temperature, reference speed and reference load, the operating environment data reference deviation including humidity reference deviation, temperature reference deviation, speed reference deviation and load reference deviation; obtaining the operating environment deviation index by referring to the operating environment data, the operating environment data reference deviation, the operating environment data at a preset time and the deviation index weight, the specific calculation formula of the operating environment deviation index is as follows:

[0015]

[0016] Where, DI n H is the operating environment deviation index of the bearing to be tested at the nth preset time. n is the ambient humidity of the bearing to be tested at the nth preset time, P n is the ambient temperature of the bearing to be tested at the nth preset time, R n is the bearing speed of the bearing to be tested at the nth preset moment, L n is the real-time load of the bearing to be tested at the nth preset moment, H0 is the reference humidity, P0 is the reference temperature, R0 is the reference speed, L0 is the reference load, ΔH is the humidity reference deviation, ΔP is the temperature reference deviation, ΔR is the speed reference deviation, ΔL is the load reference deviation, b1 is the first index weight, b2 is the second index weight, b3 is the third index weight, and b4 is the fourth index weight.

[0017] Furthermore, the specific steps of the step-by-step adjustment are as follows: A1, obtaining the operating environment data difference based on the reference operating environment data and the operating environment data at a preset time, wherein the operating environment data difference includes temperature difference, humidity difference, load difference and speed difference; A2, judging whether the temperature difference exceeds the temperature difference threshold, if the temperature difference exceeds the temperature difference threshold, starting the temperature adjustment measure; A3, judging whether the humidity difference exceeds the humidity difference threshold, if the humidity difference exceeds the humidity difference threshold, starting the humidity control measure; A4, judging whether the load difference exceeds the load difference threshold, if the load difference exceeds the load difference threshold, starting the load reduction measure; A5, judging whether the speed difference exceeds the speed difference threshold, if the speed difference exceeds the speed difference threshold, starting the speed reduction measure; A6, collecting data on the bearing to be tested to obtain the bearing temperature and operating environment data, and analyzing to obtain the temperature anomaly index, judging whether the temperature anomaly index is not greater than the preset anomaly threshold, if it is not greater than the preset anomaly threshold, ending the step-by-step adjustment, otherwise executing the early warning operation.

[0018] Furthermore, the early warning operation based on the temperature anomaly index also includes: fault grading the bearing to be tested according to the temperature anomaly index of the bearing to be tested and a preset abnormal threshold to obtain a fault level, wherein the fault grading represents the classification of the severity of the fault of the bearing to be tested; the preset abnormal threshold includes a first threshold, a second threshold and a third threshold.

[0019] Furthermore, the early warning operation includes a first warning, a second warning, a third warning and a fourth warning; the first warning is to send a reminder message to a preset personnel that the temperature abnormality index is lower than a first threshold; the second warning is to send a reminder message to a preset personnel that the temperature abnormality index exceeds the first threshold but does not reach the second threshold, and automatically activates the abnormal indicator light; the third warning is to send a reminder message to a preset personnel that the temperature abnormality index exceeds the second threshold but does not reach the third threshold, and automatically triggers the sound and light alarm device; the fourth warning is to send a reminder message to a preset personnel that the temperature abnormality index exceeds the third threshold, and automatically triggers the emergency shutdown procedure; the early warning operation also includes sending an abnormal visualization chart to the preset personnel, and the abnormal visualization chart is used to intuitively display the changing trend of abnormal conditions in the bearing to be tested.

[0020] Furthermore, the sending of abnormal visualization charts to preset personnel also includes obtaining a stability evaluation index based on the temperature anomaly index and the operating environment deviation index, and the stability evaluation index is used to indicate the stability degree of the bearing to be tested under current conditions. The specific process is as follows: obtaining a stability evaluation weight from a preset database, and the stability evaluation weight includes a first stability evaluation weight and a second stability evaluation weight; extracting the temperature anomaly index and the operating environment deviation index of the historical time period from the preset database, and statistically analyzing the preset moments of adjacent temperature anomaly indexes according to the preset anomaly threshold to obtain a temperature anomaly interval time period, and statistically analyzing the preset moments of adjacent operating environment deviation indexes according to the preset deviation threshold to obtain an environment deviation interval time period; obtaining the total temperature anomaly time by statistically analyzing the temperature anomaly interval time period, and obtaining the total environment deviation time by statistically analyzing the environment deviation interval time period; obtaining the stability evaluation index of the bearing to be tested by the temperature anomaly index, the operating environment deviation index, the total temperature anomaly time, the total environment deviation time and the stability evaluation weight, and the specific calculation formula of the stability evaluation index is as follows:

[0021]

[0022] Where RL n is the stability evaluation index of the bearing to be tested at the nth preset time, L total is the running time of the bearing to be tested, LT n LD is the total abnormal temperature time of the bearing to be tested at the nth preset time. n is the total environmental deviation time of the bearing to be tested at the nth preset moment, α is the first stability evaluation weight, and β is the second stability evaluation weight.

[0023] Furthermore, the specific steps of drawing the abnormal visualization chart are as follows: drawing a time series chart of the temperature abnormality index according to the changing relationship between the temperature abnormality index and the preset moment; drawing a time series chart of the operating environment deviation index according to the changing relationship between the operating environment deviation index and the preset moment; drawing an abnormal moment marking chart according to the relationship between the preset moment and the abnormal moment; drawing a stability assessment index time series chart according to the changing relationship between the stability assessment index and the preset moment; the abnormal visualization chart includes a temperature abnormality index time series chart, an operating environment deviation index time series chart, an abnormal moment marking chart and a stability assessment index time series chart.

[0024] The embodiment of the present application provides a bearing temperature early warning system based on the Internet of Things, comprising: a data acquisition module, a temperature anomaly judgment module, a step-by-step adjustment module and an early warning module; wherein the data acquisition module is used to perform data acquisition at a preset time to obtain the bearing temperature and operating environment data of the bearing to be tested, and the operating environment data includes environmental data and running data; the temperature anomaly judgment module is used to obtain the temperature anomaly index of the bearing to be tested by performing an abnormal analysis on the operating environment data and the bearing temperature, and to obtain the operating environment deviation index of the bearing to be tested by performing a deviation analysis on the operating environment data at the preset time, and to judge whether the temperature anomaly index is greater than a preset abnormal threshold value. If the temperature anomaly index is greater than the preset abnormal threshold value, the corresponding preset time is marked as an abnormal time and then the function of the step-by-step adjustment module is executed, otherwise no processing is performed, the temperature anomaly index is used to describe the degree of actual temperature anomaly of the bearing to be tested, and the operating environment deviation index is used to describe the degree of deviation of the operating environment data compared with the preset operating environment; the step-by-step adjustment module is used to judge whether the obtained operating environment deviation index is greater than the preset deviation threshold value, if the operating environment deviation index is greater than the preset deviation threshold value, step-by-step adjustment is performed, otherwise the function of the early warning module is executed; the early warning module is used to perform an early warning operation according to the temperature anomaly index.

[0025] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0026] 1. By performing abnormal analysis and deviation analysis on the collected bearing temperature and operating environment data, the temperature abnormality index and operating environment deviation index are obtained respectively. Then, by comparing the operating environment deviation index and the preset deviation threshold, it is determined whether to perform step-by-step adjustment. Finally, an early warning operation is performed according to the temperature abnormality index, thereby achieving timely early warning of bearing temperature abnormalities, and further improving the accuracy of bearing temperature abnormality monitoring, effectively solving the problem of insufficient correlation between operating environment changes and temperature abnormalities in the bearing temperature monitoring process in the prior art.

[0027] 2. By obtaining the bearing temperature threshold and operating limit parameters from the preset database, the temperature anomaly index of the bearing to be tested is obtained by combining the state parameter weight factor, the bearing temperature at the preset time and the operating environment data. Then, the fault level of the bearing to be tested is classified according to the preset abnormal threshold to obtain the fault level. Finally, a warning message is sent to the preset personnel according to the fault level, thereby achieving effective distinction and timely response to bearing faults of different severity, thereby realizing the warning efficiency of the bearing temperature early warning method.

[0028] 3. According to the preset abnormal threshold and the preset deviation threshold, the temperature anomaly index and the operating environment deviation index of the historical time period extracted from the preset database are analyzed to obtain the temperature anomaly interval time period and the environmental deviation interval time period, and the total temperature anomaly time and the total environmental deviation time are obtained by statistics. The temperature anomaly index, the operating environment deviation index and the stability evaluation weight obtained from the preset database are combined to obtain the stability evaluation index of the bearing to be tested, so as to quantitatively evaluate the operating stability of the bearing to be tested, thereby realizing the stability of the bearing temperature early warning method. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 A flowchart of a bearing temperature early warning method based on the Internet of Things provided in an embodiment of the present application;

[0030] Figure 2 A variable relationship diagram of the operating environment deviation index provided in this embodiment;

[0031] Figure 3 A structural schematic diagram of a bearing temperature early warning system based on the Internet of Things provided in an embodiment of the present application. DETAILED DESCRIPTION

[0032] The embodiment of the present application solves the problem of insufficient correlation between operating environment changes and temperature anomalies in the bearing temperature monitoring process in the prior art by providing a bearing temperature early warning method and system based on the Internet of Things. The bearing temperature and operating environment data of the bearing to be tested are obtained by data collection at a preset time, and an abnormality analysis is performed to obtain a temperature anomaly index. The operating environment data is subjected to a deviation analysis to obtain an operating environment deviation index. The preset time is then marked by the temperature anomaly index and a preset abnormal threshold to obtain an abnormal time. Whether to perform step-by-step adjustment is then determined by the operating environment deviation index and the preset deviation threshold. Finally, an early warning operation is performed according to the temperature anomaly index, thereby improving the accuracy of bearing temperature anomaly monitoring.

[0033] The technical solution in the embodiment of the present application is to solve the problem that the operating environment changes and temperature anomalies are not sufficiently correlated during the above-mentioned bearing temperature monitoring process. The overall idea is as follows:

[0034] By performing abnormality analysis and deviation analysis on the collected bearing temperature and operating environment data, the temperature abnormality index and operating environment deviation index are obtained respectively. The operating environment deviation index and the preset deviation threshold are then used to determine whether to perform step-by-step adjustment. Finally, early warning operations are performed based on the temperature abnormality index, thereby achieving the effect of improving the accuracy of bearing temperature abnormality monitoring.

[0035] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0036] like Figure 1 As shown, it is a flow chart of a bearing temperature early warning method based on the Internet of Things provided by an embodiment of the present application, the method comprising the following steps: S1, performing data collection at a preset time to obtain the bearing temperature and operating environment data of the bearing to be tested, the operating environment data including environmental data and operating data, the bearing to be tested refers to the bearing for which temperature early warning is performed, the bearing temperature represents the real-time temperature information of the bearing to be tested during operation, the environmental data represents the temperature and humidity information of the environment in which the bearing to be tested is located during operation, and the operating data represents the load and speed information of the bearing to be tested during operation; S2, obtaining a temperature anomaly index of the bearing to be tested by performing an abnormal analysis on the operating environment data and the bearing temperature, performing a deviation analysis on the operating environment data at a preset time to obtain an operating environment deviation index of the bearing to be tested, judging whether the temperature anomaly index is greater than a preset abnormal threshold, and if the temperature anomaly index is greater than the preset abnormal threshold, marking the corresponding preset time. S3 is executed after the abnormal moment is recorded, otherwise no processing is performed. The abnormal moment indicates the preset moment when the temperature abnormality index of the bearing to be tested becomes abnormal. The preset abnormal threshold is determined by the preset personnel according to the accuracy of the bearing temperature early warning method. The temperature abnormality index is used to describe the degree of actual temperature abnormality of the bearing to be tested, and the operating environment deviation index is used to describe the degree of deviation of the operating environment data compared with the preset operating environment; S3, judge whether the obtained operating environment deviation index is greater than the preset deviation threshold. If the operating environment deviation index is greater than the preset deviation threshold, perform step-by-step adjustment, otherwise execute S4. The preset deviation threshold is determined by the preset personnel according to the accuracy of the bearing temperature early warning method. Step-by-step adjustment refers to adjusting the operating environment data to reduce the temperature of the bearing to be tested; S4, perform early warning operation according to the temperature abnormality index. The early warning operation means sending a warning message to the preset personnel according to the severity of the fault of the bearing to be tested.

[0037] In this embodiment, the setting of the preset abnormality threshold and the preset deviation threshold should be determined based on the temperature abnormality index and the operating environment deviation index of the historical time period. For example, by obtaining the temperature abnormality index and the operating environment deviation index of the historical time period from the preset database, and obtaining the mean and standard deviation respectively, the preset abnormality threshold is set to the mean of the temperature abnormality index plus twice the standard deviation, and the preset deviation threshold is set to the mean of the operating environment deviation index plus twice the standard deviation, thereby covering more than 95% of the distribution of the corresponding data, thereby enhancing the accuracy of the bearing temperature early warning method; by continuously monitoring the bearing temperature and operating environment data of the bearing to be tested, and calculating the temperature abnormality index and the operating environment deviation index in real time, and comparing them with the preset abnormality threshold and the preset deviation threshold, the accuracy of bearing temperature abnormality monitoring is improved, and the problem of insufficient correlation between operating environment changes and temperature abnormalities in the bearing temperature monitoring process in the prior art is effectively solved.

[0038] Furthermore, the process of collecting data at a preset time to obtain the bearing temperature and operating environment data of the bearing to be tested is as follows: the bearing temperature of the bearing to be tested is collected at a preset time by a temperature sensor, and the temperature sensor refers to a high-precision resistance temperature detector installed on the surface of the bearing to be tested; the environmental data of the bearing to be tested is collected at a preset time by an environmental sensor, and the environmental data includes ambient temperature and ambient humidity. The environmental sensor refers to a temperature and humidity sensor installed at a monitoring point, and the monitoring point is determined by the preset personnel according to the specific position of the bearing to be tested. The ambient temperature is used to describe the temperature of the environment in which the bearing to be tested is located, and the ambient humidity is used to describe the humidity of the environment in which the bearing to be tested is located; the operating data of the bearing to be tested is collected at a preset time by an operating status sensor, and the operating data includes real-time load and bearing speed. The operating status sensor refers to a load sensor and a speed sensor installed in the bearing system. The real-time load is used to describe the force that the bearing to be tested is subjected to during operation, and the bearing speed is used to describe the actual rotation speed of the bearing to be tested.

[0039] In this embodiment, the bearing temperature is collected by a temperature sensor installed on the surface of the bearing to be tested, which represents the temperature of the center point of the outer ring of the bearing to be tested. The temperature sensor used in this embodiment is a Pt100 resistance temperature detector, which is suitable for various industrial environments, especially for bearing temperature monitoring in high temperature, high pressure or humid environments. The monitoring point of environmental data should be able to fully reflect the temperature and humidity conditions of the environment in which the bearing to be tested is located. The specific position should be determined by the preset personnel through experiments. For example, by setting multiple monitoring points above and below the bearing and near the vents of the room where the bearing is located, and collecting data for a period of time, by comparing the measured values ​​at different positions, the position corresponding to the measured value with the largest sum of the standard deviation of the temperature and the standard deviation of the humidity is selected as the final monitoring point. In this embodiment, a DHT22 temperature and humidity sensor is used as an environmental sensor. The DHT22 temperature and humidity sensor can reflect the changes in temperature and humidity at the monitoring point in real time. In this embodiment, a strain gauge load sensor is used as an operation status sensor. The strain gauge load sensor can accurately measure the dynamic load borne by the bearing. The installation position of the load sensor is the outer center point of the bearing seat to ensure that the stress changes suffered by the bearing during operation are measured. In this embodiment, a Hall effect speed sensor is used as a speed sensor to accurately measure the speed of the bearing. The installation position of the speed sensor is the inner center point of the bearing seat to ensure that the sensor can obtain the speed data of the bearing in real time and accurately. The accurate selection of the sensor ensures the reliability and accuracy of data acquisition and effectively improves the reliability of the bearing temperature early warning method.

[0040] Furthermore, the specific process of obtaining the temperature anomaly index of the bearing to be tested by performing abnormal analysis on the operating environment data and the bearing temperature is as follows: obtain the state parameter weight factor from the preset database, the state parameter weight factor includes a first weight factor and a second weight factor, the first weight factor is used to describe the influence of the environmental data on the temperature anomaly index, and the second weight factor is used to describe the influence of the operating data on the temperature anomaly index; obtain the bearing temperature threshold and the operating limit parameter from the preset database, the operating limit parameter includes the upper limit of the ambient humidity, the upper limit of the ambient temperature, the upper limit of the bearing speed and the upper limit of the real-time load, the bearing temperature threshold indicates the maximum temperature that the bearing to be tested can withstand during operation, the upper limit of the ambient humidity indicates the maximum ambient humidity allowed by the bearing to be tested under normal working conditions, the upper limit of the ambient temperature indicates the maximum ambient temperature allowed by the bearing to be tested under normal working conditions, the upper limit of the bearing speed indicates the maximum speed allowed by the bearing to be tested under normal working conditions, and the upper limit of the real-time load indicates the maximum load that the bearing to be tested can withstand under normal working conditions; obtain the temperature state parameter of the bearing to be tested at the preset time according to the bearing temperature, the operating environment data, the operating limit parameter and the state parameter weight factor at the preset time; obtain the temperature anomaly index of the bearing to be tested through the temperature state parameter and the bearing temperature threshold, and the specific calculation formula of the temperature anomaly index is as follows:

[0041]

[0042]

[0043] Where n is the number of the preset time, n = 1, 2, ..., N, N is the total number of preset time, AT n is the temperature state parameter of the bearing to be tested at the nth preset time, T n is the bearing temperature of the bearing to be tested at the nth preset time, H n is the ambient humidity of the bearing to be tested at the nth preset time, P n is the ambient temperature of the bearing to be tested at the nth preset time, R n is the bearing speed of the bearing to be tested at the nth preset moment, L n is the real-time load of the bearing to be tested at the nth preset moment, H max is the upper limit of ambient humidity, P max is the upper limit of ambient temperature, R max is the upper limit of bearing speed, L max is the upper limit of real-time load, σ is the first weight factor, ρ is the second weight factor, TEI n is the temperature anomaly index of the bearing to be tested at the nth preset time, and T0 is the bearing temperature threshold.

[0044] In this embodiment, the bearing temperature of the bearing to be tested at a preset time is a direct influencing factor of the temperature state parameter. The higher the bearing temperature of the bearing to be tested at the preset time, the higher the temperature state parameter; the ambient humidity, ambient temperature, bearing speed and real-time load of the bearing to be tested are used to correct the influence of the operating environment data on the actual temperature state of the bearing to be tested. If these data are closer to the upper limit, it means that the operating environment data has a greater influence on the actual temperature state of the bearing to be tested, so the temperature state parameter will be reduced; the first weight factor and the second weight factor are respectively used to measure the contribution of environmental data and operating data to the temperature state parameter. The larger the value, the greater the influence of such data on the actual temperature state of the bearing to be tested, so the temperature state parameter will be lower; the temperature state parameter It is obtained through the temperature, operating environment data and state parameter weight factor of the bearing to be tested at the preset time, and is used to reflect the actual temperature state of the bearing to be tested. The larger the temperature state parameter, the higher the actual temperature state of the bearing to be tested, and therefore the larger the temperature anomaly index; the bearing temperature threshold is used as a comparison benchmark, reflecting the maximum tolerable temperature of the bearing to be tested under normal working conditions. The ratio of the temperature state parameter to the bearing temperature threshold directly determines the size of the temperature anomaly index; the temperature anomaly index is obtained through the temperature state parameter and the bearing temperature threshold at the preset time, and is used to describe the degree of temperature anomaly of the bearing to be tested at the preset time. The higher the temperature anomaly index, the more it means that the temperature state parameter of the bearing is close to or exceeds the bearing temperature threshold, and needs to be adjusted step by step.

[0045] In order to simplify the description of the independent variable of the temperature anomaly index, the environmental index is defined as HP n is the environmental index of the bearing to be tested at the nth preset time, and the operating index RL n is the running index of the bearing to be tested at the nth preset time, and the simplified formula is: Taking T0 as 50°, σ as 0.4, and ρ as 0.6 as an example, the first weight factor and the second weight factor are used to measure the contribution of environmental data and operating data to the temperature state parameters, respectively, and both are less than 1. The statistical table of the change of the temperature anomaly index is shown in Table 1:

[0046] Table 1 Statistics of changes in temperature anomaly index

[0047]

[0048] According to the first, second and third columns of data in Table 1, it can be found that when the temperature at the preset time is close to the bearing temperature threshold, the temperature anomaly index is close to 1, and when the temperature at the preset time is much lower than the bearing temperature threshold, the temperature anomaly index is close to 0; according to the first and fourth columns of data in Table 1, it can be found that when the environmental index increases, the temperature anomaly index decreases, and the environmental index is inversely correlated with the temperature anomaly index; according to the first and fourth columns of data in Table 1, it can be found that when the operating index increases, the temperature anomaly index decreases, and the operating index is inversely correlated with the temperature anomaly index; the temperature anomaly index obtained through multiple factors can accurately reflect the current temperature state of the bearing to be tested, and can also reflect the influence of the operating environment data on the bearing temperature, further improving the accuracy of the bearing temperature early warning method.

[0049] Specifically, the first weight factor is the weight corresponding to the preset environmental data in the preset database, which represents the numerical value of the influence of the environmental data on the temperature anomaly index. When used, the weight corresponding to the preset environmental data can be directly obtained from the preset database, and the corresponding relationship can be a pre-set mapping relationship. For example, the environmental data value of the bearing to be tested and the weight corresponding to the preset environmental data value in the preset database form a mapping set, and the real-time environmental data value is input into the mapping set to obtain the corresponding weight, wherein the mapping relationship can be one-to-one or many-to-one. In this example, its value range is [0, 1]; the sum of the second weight factor and the first weight factor is 1.

[0050] The algorithm of this embodiment combines "the temperature of the bearing to be tested at the nth preset moment", "the environmental index of the bearing to be tested at the nth preset moment" and "the operating index of the bearing to be tested at the nth preset moment", and comprehensively analyzes to obtain the "temperature anomaly index of the bearing to be tested at the nth preset moment", and each parameter is related to each other, not independent, it is a whole, and the "temperature anomaly index of the bearing to be tested at the nth preset moment" cannot be obtained by simple combination and addition. For example, in this formula, "the temperature of the bearing to be tested at the nth preset moment" is conducive to increasing the "temperature anomaly index of the bearing to be tested at the nth preset moment", which does not necessarily mean that the "temperature anomaly index of the bearing to be tested at the nth preset moment" is large. At this time, it is also necessary to consider that "the environmental index of the bearing to be tested at the nth preset moment" and "the operating index of the bearing to be tested at the nth preset moment" can also determine the degree of abnormality of the temperature state of the bearing to be tested at the preset moment. The correlation and mutual influence between various factors are considered in a quantitative manner, and the algorithm itself is obtained by comprehensive analysis, which can accurately and quantitatively analyze the degree of abnormality of the temperature state of the bearing to be tested at the preset moment, indicating the effect of comprehensive evaluation of the temperature anomaly index, so accurate analysis is performed by establishing a mathematical form.

[0051] Furthermore, the specific process of performing deviation analysis on the operating environment data at a preset time to obtain the operating environment deviation index of the bearing to be tested is as follows: obtaining deviation index weights from a preset database, the deviation index weights include a first index weight, a second index weight, a third index weight and a fourth index weight, the first index weight is used to describe the influence of ambient humidity on the operating environment deviation index, the second index weight is used to describe the influence of ambient temperature on the operating environment deviation index, the third index weight is used to describe the influence of bearing speed on the operating environment deviation index, and the second index weight is used to describe the influence of real-time load on the operating environment deviation index; extracting historical operating environment data from the preset database, traversing the historical operating environment data, and determining whether there are missing historical operating environment data. If there are missing historical operating environment data, the missing data is filled with the mean of adjacent data in the corresponding data type. The historical operating environment data includes historical humidity, historical temperature, historical speed and historical load. The historical humidity indicates the ambient humidity of the bearing to be tested in the historical time period, the historical temperature indicates the ambient temperature of the bearing to be tested in the historical time period, the historical load indicates the real-time load of the bearing to be tested in the historical time period, and the historical speed indicates the bearing speed of the bearing to be tested in the historical time period; the historical operating environment data is statistically analyzed to obtain reference operating environment data and operating environment data reference deviation, the reference operating environment data indicates the average value of operating environment data of the same data type in the historical operating environment data, including reference humidity, reference temperature, reference speed and reference load, the operating environment data reference deviation indicates the standard deviation of operating environment data of the same data type in the historical operating environment data, including humidity reference deviation, temperature reference deviation, speed reference deviation and load reference deviation; the operating environment deviation index is obtained by using the reference operating environment data, the operating environment data reference deviation, the operating environment data at a preset time and the deviation index weight, and the specific calculation formula of the operating environment deviation index is as follows:

[0052]

[0053] Where, DI n H is the operating environment deviation index of the bearing to be tested at the nth preset time. n is the ambient humidity of the bearing to be tested at the nth preset time, P n is the ambient temperature of the bearing to be tested at the nth preset time, R n is the bearing speed of the bearing to be tested at the nth preset moment, L n is the real-time load of the bearing to be tested at the nth preset moment, H0 is the reference humidity, P0 is the reference temperature, R0 is the reference speed, L0 is the reference load, ΔH is the humidity reference deviation, ΔP is the temperature reference deviation, ΔR is the speed reference deviation, ΔL is the load reference deviation, b1 is the first index weight, b2 is the second index weight, b3 is the third index weight, and b4 is the fourth index weight.

[0054] In this embodiment, the calculation of the operating environment deviation index involves a comprehensive analysis of multiple parameters such as ambient humidity, ambient temperature, bearing speed and real-time load, wherein the deviation of each parameter is standardized and then weighted according to its own weight coefficient, and finally the result is nonlinearly mapped through the tanh function, ensuring that the operating environment deviation index varies between 0 and 1, which is convenient for quantifying and comparing the degree of operating environment deviation at different preset times. The larger the values ​​of the first index weight, the second index weight, the third index weight and the fourth index weight, the more significant the impact of the factor on the operating environment deviation. Therefore, the deviation of the factor will make a greater contribution to the operating environment deviation index during the calculation process.

[0055] In order to simplify the description of the independent variables of the operating environment deviation index, the humidity index is defined as H ′ n The temperature index is defined as the humidity index of the bearing to be tested at the nth preset time. P ′ n The speed index is defined as the temperature index of the bearing to be tested at the nth preset time. R′ n The load index is defined as the speed index of the bearing to be tested at the nth preset time. L′ n is the load index of the bearing to be tested at the nth preset time, and the simplified formula is: For example, b1 is 0.1, b2 is 0.2, b3 is 0.3, and b4 is 0.4. Figure 2 As shown, this is a variable relationship diagram of the operating environment deviation index provided in this embodiment. It can be seen from the figure that the effects of humidity index, temperature index, rotation speed index and load index on the operating environment deviation index all show similar trends, that is, at low values, they contribute more to the growth of the operating environment deviation index, but as the variable value increases, due to the characteristics of the tanh function, the growth gradually slows down and eventually reaches a stable state.

[0056] Specifically, the first index weight is the weight corresponding to the humidity index preset in the preset database, which represents the numerical value of the influence degree of the humidity index on the operating environment deviation index. When used, the weight corresponding to the preset humidity index can be directly obtained from the preset database, and the corresponding relationship can be a pre-set mapping relationship. For example, the humidity index value of the bearing to be tested and the weight corresponding to the humidity index value preset in the preset database form a mapping set, and the real-time humidity index value is input into the mapping set to obtain the corresponding weight, wherein the mapping relationship can be one-to-one or many-to-one. In this example, its value range is [0, 1].

[0057] Specifically, the second index weight is the weight corresponding to the preset temperature index in the preset database, which represents the value of the influence of the temperature index on the operating environment deviation index. When used, the weight corresponding to the preset temperature index can be directly obtained from the preset database, and the corresponding relationship can be a pre-set mapping relationship. For example, the temperature index value of the bearing to be tested and the weight corresponding to the preset temperature index value in the preset database form a mapping set, and the real-time temperature index value is input into the mapping set to obtain the corresponding weight, wherein the mapping relationship can be one-to-one or many-to-one. In this example, its value range is [0, 1].

[0058] Specifically, the third index weight is the weight corresponding to the preset speed index in the preset database, which represents the numerical value of the influence of the speed index on the operating environment deviation index. When used, the weight corresponding to the preset speed index can be directly obtained from the preset database, and the corresponding relationship can be a pre-set mapping relationship. For example, the speed index value of the bearing to be tested and the weight corresponding to the preset speed index value in the preset database form a mapping set, and the real-time speed index value is input into the mapping set to obtain the corresponding weight, wherein the mapping relationship can be one-to-one or many-to-one. In this example, its value range is [0, 1].

[0059] It should be understood that the sum of the fourth index weight and the first index weight, the second index weight and the third index weight is 1; the algorithm of this embodiment combines the "humidity index of the bearing to be tested at the nth preset time", "the temperature index of the bearing to be tested at the nth preset time", "the speed index of the bearing to be tested at the nth preset time" and "the load index of the bearing to be tested at the nth preset time", and comprehensively analyzes to obtain the "operating environment deviation index of the bearing to be tested at the nth preset time", and each parameter is related to each other, and does not exist independently. It is a whole, and it is not possible to obtain the "operating environment deviation index of the bearing to be tested at the nth preset time" by simple combination and addition. For example, the "humidity index of the bearing to be tested at the nth preset time" in this formula is conducive to increasing the "humidity index of the bearing to be tested at the nth preset time". The "operating environment deviation index at the preset moment" does not necessarily mean that the "operating environment deviation index of the bearing to be tested at the nth preset moment" is large. At this time, it is also necessary to consider the "temperature index of the bearing to be tested at the nth preset moment", "speed index of the bearing to be tested at the nth preset moment" and "load index of the bearing to be tested at the nth preset moment". They can also determine the degree of deviation between the operating environment of the bearing to be tested at the preset moment and the reference operating environment. The correlation and mutual influence between various factors are considered in a quantitative way, and the algorithm itself is obtained through comprehensive analysis. The degree of deviation between the operating environment of the bearing to be tested at the preset moment and the reference operating environment can be accurately and quantitatively analyzed, which shows the effect of comprehensive evaluation of the operating environment deviation index. Therefore, accurate analysis is carried out by establishing mathematical forms.

[0060] Furthermore, the specific steps of step-by-step adjustment are as follows: A1, obtaining the difference of operating environment data according to the reference operating environment data and the operating environment data at the preset time, the operating environment data difference includes temperature difference, humidity difference, load difference and speed difference, the temperature difference represents the difference between the ambient temperature at the preset time and the reference temperature, the humidity difference represents the difference between the ambient humidity at the preset time and the reference humidity, the load difference represents the difference between the real-time load at the preset time and the reference load, and the speed difference represents the difference between the speed difference at the preset time and the reference speed difference; A2, judging whether the temperature difference exceeds the temperature difference threshold, if the temperature difference exceeds the temperature difference threshold, starting the temperature adjustment measure, the temperature adjustment measure is determined by the preset personnel according to the standard temperature range of the environment in which the bearing to be tested is located, and the temperature difference threshold is determined by the preset personnel according to the upper limit of the ambient temperature of the bearing to be tested; A3, judging whether the humidity difference exceeds the humidity difference threshold, if the humidity difference exceeds the humidity difference threshold, starting the humidity control measure, the humidity control measure is determined by the preset personnel The preset personnel determine it according to the standard humidity range of the environment in which the bearing to be tested is located, and the humidity difference threshold is determined by the preset personnel according to the upper limit of the environmental humidity of the bearing to be tested; A4, judge whether the load difference exceeds the load difference threshold. If the load difference exceeds the load difference threshold, start the load reduction measure. The load reduction measure is determined by the preset personnel according to the load distribution strategy of the bearing to be tested, and the load difference threshold is determined by the preset personnel according to the real-time load upper limit of the bearing to be tested; A5, judge whether the speed difference exceeds the speed difference threshold. If the speed difference exceeds the speed difference threshold, start the speed reduction measure. The speed reduction measure is determined by the preset personnel according to the actual production demand of the bearing to be tested, and the speed difference threshold is determined by the preset personnel according to the bearing speed upper limit of the bearing to be tested; A6, collect data for the bearing to be tested to obtain the bearing temperature and operating environment data, and analyze it to obtain the temperature anomaly index, judge whether the temperature anomaly index is not greater than the preset anomaly threshold, if it is not greater than the preset anomaly threshold, end the step-by-step adjustment, otherwise perform the early warning operation.

[0061] In this embodiment, the temperature difference threshold, humidity difference threshold, load difference threshold and speed difference threshold are represented by the mean of the corresponding data in the historical time period plus the corresponding two standard deviations. For example, the temperature difference mean of a certain type of bearing under a standard operating environment is 5°C, and the standard deviation is 2°C. The temperature difference threshold is the mean plus two standard deviations, i.e., 11°C. The selection and implementation of step-by-step adjustment measures are key. In this embodiment, installing a cooling fan is selected as a temperature adjustment measure. By starting the cooling fan, the heat around the bearing is reduced in time. A dehumidifier is selected as a humidity control measure. By starting the dehumidifier, the humidity near the bearing is prevented from being too high, resulting in lubrication failure. Adjusting the load distribution of the equipment is selected as a load adjustment measure, thereby reducing the instantaneous load of the bearing and avoiding temperature surges caused by overload. Reducing the working voltage of the motor is selected as a speed control measure, thereby reducing the speed of the bearing and reducing frictional heat. A variety of step-by-step adjustment measures are used to effectively alleviate the risk of abnormal bearing temperature, ensuring the stability and safety of the bearing temperature early warning method.

[0062] Furthermore, an early warning operation is performed based on the temperature anomaly index, which also includes grading the fault of the bearing to be tested according to the temperature anomaly index of the bearing to be tested and the preset abnormal threshold to obtain a fault level. The fault grading indicates that the severity of the fault of the bearing to be tested is classified, and the fault level is used to describe the severity of the fault of the bearing to be tested; the preset abnormal threshold includes a first threshold, a second threshold and a third threshold; the fault level includes a first level, a second level, a third level and a fourth level. The first level is the bearing to be tested whose temperature anomaly index does not exceed the first threshold, the second level is the bearing to be tested whose temperature anomaly index is higher than the first threshold but not higher than the second threshold, the third level is the bearing to be tested whose temperature anomaly index is higher than the second threshold but not higher than the third threshold, and the fourth level is the bearing to be tested whose temperature anomaly index exceeds the third threshold. The sorting indicates that the temperature anomaly index of the bearings in each fault level is arranged from low to high.

[0063] In this embodiment, the method for setting the preset abnormal threshold is as follows: first, by performing statistical analysis on a large amount of historical operating data, the temperature mean and standard deviation of the bearing are calculated, and the preset abnormal threshold is represented by the sum of the temperature mean and different multiples of the standard deviation. For example, the temperature data of a certain type of bearing under various operating conditions is collected through experiments, and through analysis, it is obtained that the temperature mean of this type of bearing is 60°C and the standard deviation is 10°C. The first threshold is set to the temperature mean plus one times the standard deviation, that is, 70°C; the second threshold is set to the temperature mean plus two times the standard deviation, that is, 80°C; the third threshold is set to the temperature mean plus three times the standard deviation, that is, 90°C; through the fault classification method based on the temperature anomaly index, the bearing temperature warning method can accurately distinguish and handle abnormal conditions of different severity, thereby significantly improving the efficiency of the bearing temperature warning method.

[0064] Furthermore, the early warning operation should be determined according to the fault level, and the early warning operation includes the first warning, the second warning, the third warning and the fourth warning; the first warning is to send a reminder message to the preset personnel that the temperature abnormality index is lower than the first threshold; the second warning is to send a reminder message to the preset personnel that the temperature abnormality index exceeds the first threshold but does not reach the second threshold, and automatically activate the abnormal indicator light; the third warning is to send a reminder message to the preset personnel that the temperature abnormality index exceeds the second threshold but does not reach the third threshold, and automatically trigger the sound and light alarm device; the fourth warning is to send a reminder message to the preset personnel that the temperature abnormality index exceeds the third threshold, and automatically trigger the emergency shutdown procedure; the early warning operation also includes sending an abnormal visualization chart to the preset personnel, and the abnormal visualization chart is used to intuitively display the changing trend of the abnormal situation of the bearing to be tested.

[0065] In this embodiment, the hierarchical processing of the early warning operation can implement corresponding countermeasures according to the severity of the fault. The first warning information reminds the preset personnel to conduct routine inspections; after the second warning is triggered, the bearing temperature early warning system will automatically activate the abnormal indicator light of the equipment to attract the attention of the preset personnel; the third warning will trigger the sound and light alarm device to remind the preset personnel to immediately partially or fully shut down the equipment for inspection. The sound and light alarm device is installed near the bearing to be tested; and the fourth warning means that there is a serious safety risk to the equipment, and the bearing temperature early warning system will automatically execute the emergency shutdown procedure to prevent further damage or accidents; at the same time, the bearing temperature early warning system will generate a detailed abnormality report and display it to the preset personnel in the form of a chart so that they can conduct fault analysis and decision-making. This hierarchical early warning mechanism ensures the flexibility and pertinence of the early warning measures, thereby improving the practicality of the bearing temperature early warning method.

[0066] Furthermore, an abnormal visualization chart is sent to the preset personnel, which also includes obtaining a stability evaluation index based on the temperature anomaly index and the operating environment deviation index. The stability evaluation index is used to indicate the degree of stability of the bearing to be tested under current conditions. The specific process is as follows: obtaining a stability evaluation weight from a preset database, the stability evaluation weight including a first stability evaluation weight and a second stability evaluation weight, the first stability evaluation weight being used to describe the degree of influence of the temperature anomaly index on the stability evaluation index, and the second stability evaluation weight being used to describe the degree of influence of the operating environment deviation index on the stability evaluation index; extracting the temperature anomaly index and the operating environment deviation index of the historical time period from the preset database, performing statistics on the preset moments of adjacent temperature anomaly indices according to the preset anomaly threshold to obtain the temperature anomaly interval time period, and performing statistics on the preset moments of adjacent operating environment deviation indices according to the preset deviation threshold to obtain the environment deviation interval time The temperature anomaly interval time period represents the interval time period between the preset moment of each temperature anomaly index greater than the preset anomaly threshold and the preset moment of the last temperature anomaly index greater than the preset anomaly threshold, and the environmental deviation interval time period represents the interval time period between the preset moment of each operating environment deviation index greater than the preset deviation threshold and the preset moment of the last operating environment deviation index greater than the preset deviation threshold; the total temperature anomaly time is obtained by statistically analyzing the temperature anomaly interval time periods, and the total environmental deviation time is obtained by statistically analyzing the environmental deviation interval time periods. The total temperature anomaly time represents the sum of all temperature anomaly interval time periods, and the total environmental deviation time represents the sum of all environmental deviation interval time periods; the stability evaluation index of the bearing to be tested is obtained by the temperature anomaly index, the operating environment deviation index, the total temperature anomaly time, the total environmental deviation time and the stability evaluation weight. The specific calculation formula of the stability evaluation index is as follows:

[0067]

[0068] Where RL n is the stability evaluation index of the bearing to be tested at the nth preset time, L total is the running time of the bearing to be tested, LT n LD is the total abnormal temperature time of the bearing to be tested at the nth preset time. n is the total environmental deviation time of the bearing to be tested at the nth preset moment, α is the first stability evaluation weight, and β is the second stability evaluation weight.

[0069] In this embodiment, the stability evaluation index is calculated based on the temperature anomaly index, the operating environment deviation index, the total temperature anomaly time, the total environment deviation time and the stability evaluation weight, and is used to describe the stability state of the bearing to be tested at a preset time. The lower the stability evaluation index, the worse the stability of the bearing under the current environment and operating state; the ratio of the total temperature anomaly time to the total environment deviation time will affect the result of the stability evaluation index. An increase in the ratio indicates that the bearing has experienced a longer period of abnormal moments during operation, which reduces the stability of the bearing to be tested; the lower the temperature anomaly index and the operating environment deviation index, the more stable the bearing to be tested, and the higher the value of the stability evaluation index; the stability evaluation weight is used to adjust the degree of influence of the temperature anomaly index and the operating environment deviation index on the stability evaluation index. The larger the weight value, the more significant the contribution of these factors to the stability evaluation index; the stability evaluation index integrates the influence of the temperature anomaly index and the operating environment deviation index in the historical process, and comprehensively describes the stability state of the bearing to be tested at a preset time. The lower the value of the stability evaluation index, the poorer the stability of the bearing under current conditions, and further measures may need to be taken for inspection or maintenance to ensure the normal operation of the equipment.

[0070] Specifically, the first stability evaluation weight is the weight corresponding to the preset temperature anomaly index in the preset database, which represents the numerical value of the influence of the temperature anomaly index on the stability evaluation index. When used, the weight corresponding to the preset temperature anomaly index can be directly obtained from the preset database, and the corresponding relationship can be a pre-set mapping relationship. For example, the temperature anomaly index value of the bearing to be tested and the weight corresponding to the temperature anomaly index value preset in the preset database form a mapping set, and the real-time temperature anomaly index value is input into the mapping set to obtain the corresponding weight, wherein the mapping relationship can be one-to-one or many-to-one. In this example, its value range is [0, 1]; the sum of the second stability weight and the first stability weight is 1.

[0071] The algorithm of this embodiment combines "the total time of temperature anomaly of the bearing to be tested at the nth preset moment", "the total time of environmental deviation of the bearing to be tested at the nth preset moment", "the temperature anomaly index of the bearing to be tested at the nth preset moment" and "the operating environment deviation index of the bearing to be tested at the nth preset moment", and comprehensively analyzes to obtain the "stability evaluation index of the bearing to be tested at the nth preset moment", and each parameter is related to each other, not independent, and is a whole. It is not possible to obtain the "stability evaluation index of the bearing to be tested at the nth preset moment" by simple combination and addition. For example, in this formula, "the total time of temperature anomaly of the bearing to be tested at the nth preset moment" is conducive to increasing the "stability evaluation index of the bearing to be tested at the nth preset moment". The stability evaluation index of the bearing to be tested at the nth preset moment" does not necessarily mean that the stability evaluation index of the bearing to be tested at the nth preset moment is large. At this time, it is also necessary to consider the "total time of environmental deviation of the bearing to be tested at the nth preset moment", "temperature anomaly index of the bearing to be tested at the nth preset moment" and "operating environment deviation index of the bearing to be tested at the nth preset moment". The stability state of the bearing to be tested at the preset moment is also determined by considering the correlation and mutual influence between various factors in a quantitative way. The algorithm itself is obtained through comprehensive analysis, which can accurately and quantitatively analyze the stability state of the bearing to be tested at the preset moment, indicating the effect of comprehensive evaluation of the stability evaluation index. Therefore, accurate analysis is carried out by establishing mathematical forms.

[0072] Furthermore, the specific steps for drawing the abnormality visualization chart are as follows: draw a time series chart of the temperature abnormality index according to the changing relationship between the temperature abnormality index and the preset moment; draw a time series chart of the operating environment deviation index according to the changing relationship between the operating environment deviation index and the preset moment; draw an abnormal moment marking chart according to the relationship between the preset moment and the abnormal moment; draw a stability assessment index time series chart according to the changing relationship between the stability assessment index and the preset moment; the abnormality visualization chart includes a temperature abnormality index time series chart, an operating environment deviation index time series chart, an abnormal moment marking chart and a stability assessment index time series chart; abnormal visualization is used to intuitively display the abnormal conditions and changing trends of the temperature abnormality index, operating environment deviation index and stability assessment index that occur during the operation of the tested bearing.

[0073] In this embodiment, through the abnormal visualization chart, the abnormal conditions that occur during the operation of the bearing to be tested, as well as the changing trends of the temperature anomaly index, the operating environment deviation index, and the stability evaluation index can be intuitively displayed. Among them, the horizontal axis of the temperature anomaly index time series chart represents the preset time, and the vertical axis represents the temperature anomaly index, which can help identify the fluctuation and trend of the temperature anomaly index, and then judge the occurrence and severity of the bearing temperature anomaly; the horizontal axis of the operating environment deviation index time series chart represents the preset time, and the vertical axis represents the operating environment deviation index, which intuitively displays the degree of deviation of the operating environment relative to the historical data; the horizontal axis of the abnormal moment marking chart represents the preset time, and the vertical axis represents whether it is an abnormal moment. By marking the abnormal moment, the specific time when the temperature anomaly occurs can be clearly displayed; the horizontal axis of the stability evaluation index time series chart represents the preset time, and the vertical axis represents the stability evaluation index, which shows the operating stability of the bearing to be tested in different time periods, provides effective support for the subsequent analysis of the preset personnel, and improves the visibility of the bearing temperature early warning system.

[0074] like Figure 3As shown, it is a structural schematic diagram of a bearing temperature early warning system based on the Internet of Things provided by an embodiment of the present application. The bearing temperature early warning system based on the Internet of Things provided by an embodiment of the present application includes: a data acquisition module, a temperature anomaly judgment module, a step-by-step adjustment module and an early warning module; wherein the data acquisition module is used to perform data acquisition at a preset time to obtain the bearing temperature and operating environment data of the bearing to be tested, the operating environment data includes environmental data and operating data, the bearing to be tested refers to the bearing for temperature early warning, the bearing temperature represents the real-time temperature information of the bearing to be tested during operation, the environmental data represents the temperature and humidity information of the environment in which the bearing to be tested is located during operation, and the operating data represents the load and speed information of the bearing to be tested during operation; the temperature anomaly judgment module is used to obtain the temperature anomaly index of the bearing to be tested by performing an abnormal analysis on the operating environment data and the bearing temperature, perform a deviation analysis on the operating environment data at a preset time to obtain the operating environment deviation index of the bearing to be tested, and judge whether the temperature anomaly index is greater than a preset abnormal threshold value. If If the temperature anomaly index is greater than the preset anomaly threshold, the corresponding preset moment is marked as an abnormal moment and S3 is executed, otherwise no processing is performed. The abnormal moment indicates the preset moment when the temperature anomaly index of the bearing to be tested becomes abnormal. The preset abnormal threshold is determined by the preset personnel according to the accuracy of the bearing temperature early warning method. The temperature anomaly index is used to describe the degree of actual temperature anomaly of the bearing to be tested, and the operating environment deviation index is used to describe the degree of deviation of the operating environment data compared with the preset operating environment; the step-by-step adjustment module is used to determine whether the obtained operating environment deviation index is greater than the preset deviation threshold. If the operating environment deviation index is greater than the preset deviation threshold, step-by-step adjustment is performed, otherwise the function of the early warning module is executed. The preset deviation threshold is determined by the preset personnel according to the accuracy of the bearing temperature early warning method. Step-by-step adjustment refers to adjusting the operating environment data to reduce the temperature of the bearing to be tested; the early warning module is used to perform early warning operations according to the temperature anomaly index. The early warning operation means sending a warning message to the preset personnel according to the severity of the fault of the bearing to be tested.

[0075] In this embodiment, the data acquisition module includes a Pt100 resistance temperature detector, a DHT22 temperature and humidity sensor, a strain gauge load sensor and a Hall effect speed sensor. The Pt100 resistance temperature detector is used to monitor the operating temperature of the bearing to be tested in real time and record temperature changes. The DHT22 temperature and humidity sensor, the strain gauge load sensor and the Hall effect speed sensor are used to collect the four operating data of the ambient temperature, humidity, load and speed of the bearing to be tested during operation, and store these data in a preset database; the temperature anomaly judgment module includes a temperature analysis program and an anomaly index calculation program. The temperature analysis program is used to analyze the collected bearing temperature data, and the anomaly index calculation program calculates the temperature anomaly index by comparing the preset anomaly threshold, and identifies whether there is a temperature anomaly. Abnormal situation; the step-by-step adjustment module includes a deviation analysis program and a step-by-step adjustment controller. The deviation analysis program is used to analyze the deviation between the current operating environment data and the historical data. The step-by-step adjustment controller is used to perform step-by-step adjustment when the operating environment deviation index exceeds the preset deviation threshold, so as to adjust the environmental conditions to reduce the bearing temperature; the early warning module includes an alarm generator and a notification system. The alarm generator is used to generate early warning information according to the calculated temperature anomaly index, and the notification system transmits these early warning information to the preset personnel to deal with possible faults in a timely manner. Through the collaborative work of these four modules, this embodiment realizes real-time monitoring of bearing temperature, detection of abnormal situations, adjustment of environmental conditions, and generation and transmission of early warning information, which effectively improves the safety and reliability of bearing operation.

[0076] To summarize, the embodiment of the present application obtains a temperature anomaly index and an operating environment deviation index by performing anomaly analysis and deviation analysis on the collected bearing temperature and operating environment data, respectively, and then determines whether to perform step-by-step adjustment by comparing the operating environment deviation index and a preset deviation threshold. Finally, an early warning operation is performed based on the temperature anomaly index, thereby achieving timely early warning of bearing temperature anomalies, and further improving the accuracy of bearing temperature anomaly monitoring, effectively solving the problem of insufficient correlation between operating environment changes and temperature anomalies in the bearing temperature monitoring process in the prior art.

[0077] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0078] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0079] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0080] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0081] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0082] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A bearing temperature early warning method based on the Internet of Things, characterized in that: The following steps are involved: S1, collecting data at a preset time to obtain bearing temperature and operating environment data of the bearing to be tested, wherein the operating environment data includes environmental data and operation data; S2, by performing an abnormal analysis on the operating environment data and the bearing temperature, obtain the temperature abnormality index of the bearing to be tested, perform a deviation analysis on the operating environment data at a preset time, obtain the operating environment deviation index of the bearing to be tested, and judge whether the temperature abnormality index is greater than the preset abnormal threshold. If the temperature abnormality index is greater than the preset abnormal threshold, mark the corresponding preset time as an abnormal time and then execute S3, otherwise no processing is performed. The temperature abnormality index is used to describe the degree of actual temperature abnormality of the bearing to be tested, and the operating environment deviation index is used to describe the degree of deviation of the operating environment data compared with the preset operating environment. S3, determining whether the obtained operating environment deviation index is greater than a preset deviation threshold, if the operating environment deviation index is greater than the preset deviation threshold, performing step-by-step adjustment, otherwise executing S4; S4, perform early warning operations according to the temperature anomaly index; The process of collecting data at a preset time to obtain the bearing temperature and operating environment data of the bearing to be tested is as follows: The bearing temperature of the bearing to be tested is collected at a preset time by a temperature sensor; Collecting environmental data of the bearing to be tested at a preset time through an environmental sensor, wherein the environmental data includes environmental temperature and environmental humidity; The operating data of the bearing to be tested is collected at a preset time through the operating status sensor, wherein the operating data includes real-time load and bearing speed; The specific process of obtaining the temperature anomaly index of the bearing to be tested by performing an abnormal analysis on the operating environment data and the bearing temperature is as follows: Acquire a state parameter weight factor from a preset database, wherein the state parameter weight factor includes a first weight factor and a second weight factor; Acquire a bearing temperature threshold and operating limit parameters from a preset database, wherein the operating limit parameters include an upper limit of ambient humidity, an upper limit of ambient temperature, an upper limit of bearing speed, and an upper limit of real-time load; Obtaining the temperature state parameter of the bearing to be tested at the preset time according to the bearing temperature at the preset time, the operating environment data, the operation limit parameter and the state parameter weight factor; The temperature anomaly index of the bearing to be tested is obtained by using the temperature state parameter and the bearing temperature threshold. The specific calculation formula of the temperature anomaly index is as follows: ； ； Where n is the number of the preset time. , N is the total number of preset moments, is the temperature state parameter of the bearing to be tested at the nth preset time is the bearing temperature of the bearing to be tested at the nth preset time, is the ambient humidity of the bearing to be tested at the nth preset time, is the ambient temperature of the bearing to be tested at the nth preset time, is the bearing speed of the bearing to be tested at the nth preset moment, is the real-time load of the bearing to be tested at the nth preset moment, is the upper limit of ambient humidity, is the upper limit of ambient temperature, is the upper limit of the bearing speed, is the real-time load limit, is the first weight factor, is the second weight factor, is the temperature anomaly index of the bearing to be tested at the nth preset time, is the bearing temperature threshold; The specific process of performing deviation analysis on the operating environment data at a preset time to obtain the operating environment deviation index of the bearing to be tested is as follows: Obtaining deviation index weights from a preset database, wherein the deviation index weights include a first index weight, a second index weight, a third index weight, and a fourth index weight; Extracting historical operating environment data from a preset database, wherein the historical operating environment data includes historical humidity, historical temperature, historical rotation speed, and historical load; Performing statistical analysis on historical operating environment data to obtain reference operating environment data and operating environment data reference deviations, wherein the reference operating environment data includes reference humidity, reference temperature, reference rotation speed, and reference load, and the operating environment data reference deviations include humidity reference deviation, temperature reference deviation, rotation speed reference deviation, and load reference deviation; The operating environment deviation index is obtained by referring to the operating environment data, the operating environment data reference deviation, the operating environment data at a preset time, and the deviation index weight. The specific calculation formula of the operating environment deviation index is as follows: ； In the formula, is the operating environment deviation index of the bearing to be tested at the nth preset moment, is the ambient humidity of the bearing to be tested at the nth preset time, is the ambient temperature of the bearing to be tested at the nth preset time, is the bearing speed of the bearing to be tested at the nth preset moment, is the real-time load of the bearing to be tested at the nth preset moment, is the reference humidity, is the reference temperature, is the reference speed, is the reference load, is the humidity reference deviation, is the temperature reference deviation, is the speed reference deviation, is the load reference deviation, is the first index weight, is the second index weight, is the third index weight, is the fourth index weight.

2. A bearing temperature early warning method based on the Internet of Things as claimed in claim 1, characterized in that: The specific steps of the step-by-step adjustment are as follows: A1, obtaining an operating environment data difference according to the reference operating environment data and the operating environment data at a preset time, wherein the operating environment data difference includes a temperature difference, a humidity difference, a load difference and a speed difference; A2, judging whether the temperature difference exceeds the temperature difference threshold, if the temperature difference exceeds the temperature difference threshold, starting the temperature adjustment measure; A3, judging whether the humidity difference exceeds the humidity difference threshold, if the humidity difference exceeds the humidity difference threshold, starting the humidity control measure; A4, determining whether the load difference exceeds a load difference threshold, and if the load difference exceeds the load difference threshold, initiating load reduction measures; A5, determining whether the speed difference exceeds a speed difference threshold, and if the speed difference exceeds the speed difference threshold, initiating speed reduction measures; A6, collect data on the bearing to be tested to obtain the bearing temperature and operating environment data, and analyze it to obtain the temperature anomaly index, and determine whether the temperature anomaly index is not greater than the preset anomaly threshold. If it is not greater than the preset anomaly threshold, end the step-by-step adjustment, otherwise perform the early warning operation.

3. A bearing temperature early warning method based on the Internet of Things as claimed in claim 1, characterized in that: The warning operation according to the temperature anomaly index also includes: According to the temperature anomaly index of the bearing to be tested and the preset anomaly threshold, the fault of the bearing to be tested is graded to obtain a fault grade, wherein the fault grade represents the classification of the severity of the fault of the bearing to be tested; The preset abnormal threshold includes a first threshold, a second threshold and a third threshold.

4. A bearing temperature early warning method based on the Internet of Things as claimed in claim 3, characterized in that: The warning operation includes a first warning, a second warning, a third warning and a fourth warning; The first warning is to send a reminder message to a preset person that the temperature anomaly index is lower than a first threshold; The second warning is to send a reminder message to a preset person that the temperature abnormality index exceeds the first threshold but does not reach the second threshold, and automatically activate the abnormality indicator light; The third warning is to send a reminder message to a preset person that the temperature anomaly index exceeds the second threshold but does not reach the third threshold, and automatically trigger the sound and light alarm device; The fourth warning is to send a reminder message to a preset person that the temperature abnormality index exceeds the third threshold, and automatically trigger an emergency shutdown procedure; The early warning operation also includes sending an abnormal visualization chart to a preset person, and the abnormal visualization chart is used to intuitively display the changing trend of the abnormal situation of the bearing to be tested.

5. A bearing temperature early warning method based on the Internet of Things as claimed in claim 4, characterized in that: The sending of the abnormal visualization chart to the preset personnel also includes obtaining a stability evaluation index according to the temperature abnormality index and the operating environment deviation index. The stability evaluation index is used to indicate the stability degree of the bearing to be tested under the current conditions. The specific process is as follows: Acquire a stability assessment weight from a preset database, wherein the stability assessment weight includes a first stability assessment weight and a second stability assessment weight; Extracting the temperature anomaly index and the operating environment deviation index of the historical time period from the preset database, performing statistics on the preset moments of the adjacent temperature anomaly index according to the preset anomaly threshold to obtain the temperature anomaly interval time period, and performing statistics on the preset moments of the adjacent operating environment deviation index according to the preset deviation threshold to obtain the environment deviation interval time period; The total time of temperature anomaly is obtained by counting the time intervals of temperature anomaly, and the total time of environmental deviation is obtained by counting the time intervals of environmental deviation; The stability evaluation index of the bearing to be tested is obtained by the temperature anomaly index, the operating environment deviation index, the total temperature anomaly time, the total environment deviation time and the stability evaluation weight. The specific calculation formula of the stability evaluation index is as follows: ； In the formula, is the stability evaluation index of the bearing to be tested at the nth preset moment, is the running time of the bearing to be tested, is the total abnormal temperature time of the bearing to be tested at the nth preset moment, is the total time of the environmental deviation of the bearing to be tested at the nth preset moment, is the first stability evaluation weight, Evaluate weights for the second stability.

6. The bearing temperature early warning method based on the Internet of Things as claimed in claim 5, characterized in that: The specific steps of drawing the abnormal visualization chart are as follows: Draw a time series graph of the temperature anomaly index based on the change relationship between the temperature anomaly index and the preset time; Draw a time series graph of the operating environment deviation index according to the change relationship between the operating environment deviation index and the preset time; Draw an abnormal moment marking diagram according to the relationship between the preset moment and the abnormal moment; Draw a time series graph of the stability evaluation index based on the relationship between the stability evaluation index and the preset time; The abnormal visualization charts include a temperature anomaly index time series chart, an operating environment deviation index time series chart, an abnormal moment marking chart, and a stability assessment index time series chart.

7. A bearing temperature early warning system based on the Internet of Things, used to execute the method described in any one of claims 1 to 6, characterized in that: include: Data acquisition module, temperature anomaly judgment module, step-by-step adjustment module and early warning module; Wherein, the data acquisition module is used to acquire the bearing temperature and operating environment data of the bearing to be tested by performing data acquisition at a preset time, wherein the operating environment data includes environmental data and operation data; The temperature anomaly judgment module is used to obtain a temperature anomaly index of the bearing to be tested by performing an anomaly analysis on the operating environment data and the bearing temperature, and to obtain an operating environment deviation index of the bearing to be tested by performing a deviation analysis on the operating environment data at a preset time, and to judge whether the temperature anomaly index is greater than a preset anomaly threshold. If the temperature anomaly index is greater than the preset anomaly threshold, the corresponding preset time is marked as an abnormal time and the function of the step-by-step adjustment module is executed, otherwise no processing is performed. The temperature anomaly index is used to describe the degree of actual temperature anomaly of the bearing to be tested, and the operating environment deviation index is used to describe the degree of deviation of the operating environment data compared with the preset operating environment. The step-by-step adjustment module is used to determine whether the obtained operating environment deviation index is greater than a preset deviation threshold, and if the operating environment deviation index is greater than the preset deviation threshold, perform step-by-step adjustment, otherwise perform the function of the early warning module; The early warning module is used to perform early warning operations according to the temperature anomaly index.

Images