A rolling bearing fault feature diagnosis and management system based on data analysis

Abstract

The present invention relates to the technical field of rolling bearing fault management, and in particular to a rolling bearing fault feature diagnosis and management system based on data analysis, comprising a management platform, a supervision and analysis unit, a collection and analysis unit, a filtering analysis unit, a diagnosis and analysis unit, an operation and management analysis unit, and an early warning display unit; the present invention performs secondary analysis on abnormal filters, transmits the results by means of data feedback, and analyzes the fault features of rolling bearings by converting vibration signals into time-frequency ridge feature maps, and then performs targeted fault management on rolling bearings according to the fault features, so as to improve the diagnostic accuracy and management rationality of rolling bearings, and performs analysis through a two-dimensional coordinate system and in combination with historical rolling bearing operation risk assessment coefficients, so that operation and management personnel can perform reasonable and targeted maintenance and management of rolling bearings according to the different maintenance levels obtained, thereby reducing the failure rate of rolling bearings.

Description

Technical Field

[0001] The present invention relates to the technical field of rolling bearing fault management, and in particular to a rolling bearing fault feature diagnosis and management system based on data analysis. Background Art

[0002] Rolling bearings are widely used general mechanical parts. Their main function is to support shafts. Keeping rolling bearings in good working condition is very important for the safe operation of mechanical equipment. Therefore, accurate diagnosis of rolling bearing fault types and fault severity is the basis for ensuring the normal operation of machinery.

[0003] Rolling bearings are widely used in industrial systems. As a key component of rotating machinery, their operating status determines the performance of the entire system. According to incomplete statistics, about 30% of the causes of rotating machinery failures are due to rolling bearing failures. However, in the diagnosis process of rolling bearings in the prior art, the diagnostic data is single, and the validity of the data is difficult to support, which in turn affects the fault diagnosis results. Corresponding normal rolling bearings cannot be reasonably maintained according to their usage, which increases the subsequent failure rate. It can be seen that how to achieve effective fault diagnosis and management of rolling bearings to ensure the safe and efficient long-term operation of equipment is a problem that needs to be solved by operation management personnel. Summary of the invention

[0004] The purpose of the present invention is to provide a rolling bearing fault characteristic diagnosis and management system based on data analysis to solve the technical defects mentioned above, to perform a secondary analysis on the abnormal filter, and to transmit the result by means of data feedback, and to analyze the fault characteristics of the rolling bearing by converting the vibration signal into a time-frequency ridge feature diagram, and then to perform targeted fault management on the rolling bearing according to the fault characteristics, so as to improve the diagnostic accuracy and management rationality of the rolling bearing, and to analyze the operation risk trend rate through a two-dimensional coordinate system and the operation risk assessment coefficient of the historical rolling bearing, and to judge the operation risk trend rate, so that the operation management personnel can perform reasonable and targeted maintenance and management of the rolling bearing according to the different maintenance levels obtained, so as to reduce the failure rate of the rolling bearing.

[0005] The object of the present invention can be achieved by the following technical solutions: A rolling bearing fault feature diagnosis and management system based on data analysis, comprising a management platform, a supervision and analysis unit, a collection and analysis unit, a filtering and analysis unit, a diagnosis and analysis unit, an operation and management analysis unit, and an early warning and display unit;

[0006] When the management platform generates an operation management instruction and sends the operation management instruction to the supervision and analysis unit, the supervision and analysis unit is used to collect the working data of the rolling bearing, the working data includes the operating temperature of the rolling bearing and the running track characteristic diagram of the rolling element in the rolling bearing, and perform fault risk assessment and analysis on the working data, and send the obtained operation signal to the operation management analysis unit, and send the obtained risk signal to the collection analysis unit and the filtering analysis unit;

[0007] After receiving the operation signal, the operation management analysis unit immediately retrieves the working data from the supervision analysis unit, and further analyzes the trend development of the working data, and sends the obtained primary maintenance signal, secondary maintenance signal and tertiary maintenance signal to the early warning display unit;

[0008] The filter analysis unit immediately collects the filter operation data after receiving the risk signal, the operation data includes the line risk value and the abnormal characteristic value, and performs filter operation risk assessment and analysis on the operation data, sends the obtained normal signal to the diagnosis analysis unit, and sends the obtained abnormal signal to the early warning display unit and the collection and analysis unit;

[0009] Upon receiving the risk signal and abnormal signal, the collection and analysis unit immediately collects the operation data of the filter after maintenance, performs secondary analysis on the operation data, sends the obtained feedback signal to the diagnosis and analysis unit, and sends the obtained display signal to the early warning display unit via the filter analysis unit;

[0010] After receiving the feedback signal or the normal signal, the diagnostic analysis unit immediately collects the vibration signal of the rolling bearing, converts the vibration signal into a time-frequency ridge feature diagram according to the existing technology, and performs in-depth diagnostic evaluation and analysis on the time-frequency ridge feature diagram, and sends the obtained fault result to the early warning display unit.

[0011] Preferably, the failure risk assessment and analysis process of the supervision and analysis unit is as follows:

[0012] The duration between the start and end of the running time of the rolling bearing is collected and marked as the time threshold, the time threshold is divided into i sub-time periods, i is a natural number greater than zero, the running temperature of the rolling bearing in each sub-time period is obtained, and the running temperature is compared and analyzed with the preset running temperature threshold. If the running temperature is greater than the preset running temperature threshold, the part where the running temperature is greater than the preset running temperature threshold is marked as an overheating value, so as to obtain the sum of the overheating values ​​of the rolling bearing within the time threshold, and mark it as the overtemperature risk value;

[0013] Obtain a running track characteristic diagram of the rolling element in the rolling bearing in each sub-time period, and compare and analyze the running track characteristic diagram with the preset running track characteristic diagram for coincidence, obtain the difference value between the running track characteristic diagram and the preset running track characteristic diagram, obtain the number of sub-time periods corresponding to which the difference value is greater than the preset standard value, and mark the ratio of the number of sub-time periods corresponding to which the difference value is greater than the preset standard value to the total number of sub-time periods as the deviation risk value;

[0014] Compare and analyze the over-temperature risk value and the offset risk value with the preset over-temperature risk value threshold and the preset offset risk value threshold that are stored internally:

[0015] If the over-temperature risk value is less than or equal to the preset over-temperature risk value threshold, and the offset risk value is less than or equal to the preset offset risk value threshold, then an operation signal is generated;

[0016] If the over-temperature risk value is greater than a preset over-temperature risk value threshold, or the offset risk value is greater than a preset offset risk value threshold, a risk signal is generated.

[0017] Preferably, the further trend development analysis process of the operation management analysis unit is as follows:

[0018] Obtain the over-temperature risk value and offset risk value within the time threshold, and label them as GW and PX respectively;

[0019] According to the formula An operation risk assessment coefficient is obtained, wherein b1 and b2 are respectively preset weight coefficients of the overtemperature risk value and the offset risk value, b3 is a preset fault tolerance coefficient, b1, b2 and b3 are all positive numbers greater than zero, G is an operation risk assessment coefficient, and at the same time, the operation risk assessment coefficient of the rolling bearing that operates normally within the historical k time thresholds is obtained, k is a natural number greater than zero, and a rectangular coordinate system is established with time as the X-axis and the operation risk assessment coefficient Gk as the Y-axis. An operation risk assessment coefficient curve is drawn by drawing points, and an ascending segment and a descending segment are obtained from the operation risk assessment coefficient curve, and then the difference between the two endpoints of the ascending end is obtained, thereby obtaining the sum of the differences between the two endpoints of the ascending end, and marking it as a risk trend value FQ, and the difference between the two endpoints of the descending segment is obtained, thereby obtaining the sum of the differences between the two endpoints of the descending segment, and marking it as a safety trend value AD;

[0020] According to the formula The operation risk trend rate is obtained, where F is the operation risk trend rate, and the operation risk trend rate F is compared and analyzed with the preset operation risk trend rate range stored in the internal entry:

[0021] If the operation risk trend rate F is greater than the maximum value in the preset operation risk trend rate interval, a first-level maintenance signal is generated; if the operation risk trend rate F is within the preset operation risk trend rate interval, a second-level maintenance signal is generated; if the operation risk trend rate F is less than the minimum value in the preset operation risk trend rate interval, a third-level maintenance signal is generated.

[0022] Preferably, the filtering operation risk assessment analysis process of the filtering analysis unit is as follows:

[0023] The line risk value of the filter in each sub-time period is obtained. The line risk value refers to the product of the reactive power value of the filter internal line, the oxidation area of ​​the line port, and the number of line bulges after normalization. After taking time as X and the line risk value as the Y axis, a rectangular coordinate system is established. The line risk value curve is drawn by plotting points. The ratio of the number of segments corresponding to the rising segment to the number of segments corresponding to the falling segment is obtained from the line risk value curve, and it is marked as the line risk trend value XQ;

[0024] The abnormal characteristic value of the filter in each sub-time period is obtained, and the abnormal characteristic value refers to the sum of the temperature difference of the filter and the part of the noise decibel value exceeding the preset noise decibel value after dedimensionalization, wherein the temperature difference refers to the difference between the internal temperature of the filter and the external shell temperature, and the abnormal characteristic value is compared and analyzed with the preset abnormal characteristic value threshold. If the abnormal characteristic value is greater than the preset abnormal characteristic value threshold, the ratio of the part of the abnormal characteristic value greater than the preset abnormal characteristic value threshold to the preset abnormal characteristic value threshold is marked as the abnormal risk value YZ;

[0025] The filtering risk assessment coefficient Q is obtained according to the formula, and the filtering risk assessment coefficient Q is compared and analyzed with the preset filtering risk assessment coefficient threshold value recorded and stored internally: if the ratio of the filtering risk assessment coefficient Q to the preset filtering risk assessment coefficient threshold value is less than one, a normal signal is generated; if the ratio of the filtering risk assessment coefficient Q to the preset filtering risk assessment coefficient threshold value is greater than or equal to one, an abnormal signal is generated.

[0026] Preferably, the secondary analysis process of the acquisition and analysis unit is as follows:

[0027] The secondary filtering risk assessment coefficient is obtained, and the secondary filtering risk assessment coefficient is compared and analyzed with the preset filtering risk assessment coefficient threshold value recorded and stored internally: if the secondary filtering risk assessment coefficient is less than the preset filtering risk assessment coefficient threshold value, a feedback signal is generated; if the secondary filtering risk assessment coefficient is greater than or equal to the preset filtering risk assessment coefficient threshold value, a display signal is generated.

[0028] Preferably, the in-depth diagnostic evaluation and analysis process of the diagnostic analysis unit is as follows:

[0029] The time-frequency ridge feature diagram of the rolling bearing corresponding to each risk signal within the time threshold is obtained, and the time-frequency ridge feature diagram is compared and analyzed with the preset fault samples recorded and stored internally to obtain the fault result. After receiving the fault result, the early warning display unit displays it in the form of text and images.

[0030] The beneficial effects of the present invention are as follows:

[0031] (1) The present invention collects the working data of rolling bearings, and performs fault risk assessment analysis and further trend development analysis on the working data, that is, analyzes from the two perspectives of rolling bearing fault risk and fault risk development trend, so as to reasonably and targetedly perform maintenance and management on rolling bearings, and perform fault diagnosis on abnormal rolling bearings. Before diagnosis, the filter that affects the analysis and results of the collected data is analyzed, the line risk value and abnormal characteristic value of the filter are collected, and it is determined whether the filter is operating normally, so as to avoid the environment from interfering with the vibration signal of the rolling bearing and affecting the accuracy of the rolling bearing fault diagnosis analysis results, thereby helping to ensure the validity of subsequent analysis data;

[0032] (2) The present invention also performs secondary analysis on the abnormal filter and transmits the result by means of data feedback. It converts the vibration signal into a time-frequency ridge feature diagram to analyze the fault characteristics of the rolling bearing, and then performs targeted fault management on the rolling bearing according to the fault characteristics to improve the diagnostic accuracy and management rationality of the rolling bearing. It also performs analysis through a two-dimensional coordinate system and the operation risk assessment coefficient of the historical rolling bearing to obtain the operation risk trend rate, and distinguishes the operation risk trend rate, so that the operation management personnel can perform reasonable and targeted maintenance and management of the rolling bearing according to the different maintenance levels obtained to reduce the failure rate of the rolling bearing. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The present invention will be further described below in conjunction with the accompanying drawings;

[0034] Figure 1 It is a flowchart of the system of the present invention;

[0035] Figure 2 It is a local analysis reference diagram of the present invention. DETAILED DESCRIPTION

[0036] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0037] Embodiment 1:

[0038] See also Figure 1 to Figure 2 As shown, the present invention is a rolling bearing fault feature diagnosis and management system based on data analysis, including a management platform, a supervision and analysis unit, a collection and analysis unit, a filtering analysis unit, a diagnosis and analysis unit, an operation and management analysis unit and an early warning display unit, the management platform is connected to the supervision and analysis unit in a one-way communication, the supervision and analysis unit is connected to the collection and analysis unit, the filtering analysis unit and the operation and management analysis unit in a one-way communication, the collection and analysis unit is connected to the filtering analysis unit in a two-way communication, the collection and analysis unit and the filtering analysis unit are connected to the diagnosis and analysis unit in a one-way communication, the operation and management analysis unit, the filtering analysis unit and the diagnosis and analysis unit are connected to the early warning display unit in a one-way communication;

[0039] When the management platform generates an operation management instruction and sends it to the supervision and analysis unit, the supervision and analysis unit is used to collect the working data of the rolling bearing, including the operating temperature of the rolling bearing and the running track characteristic diagram of the rolling element in the rolling bearing, and conduct a fault risk assessment and analysis on the working data to determine whether the rolling bearing has a fault so as to carry out management in a timely manner. The specific fault risk assessment and analysis process is as follows:

[0040] The duration between the start and end of the running time of the rolling bearing is collected and marked as the time threshold. The time threshold is divided into i sub-time periods, where i is a natural number greater than zero. The running temperature of the rolling bearing in each sub-time period is obtained, and the running temperature is compared and analyzed with the preset running temperature threshold. If the running temperature is greater than the preset running temperature threshold, the part where the running temperature is greater than the preset running temperature threshold is marked as an overheating value, thereby obtaining the sum of the overheating values ​​of the rolling bearing within the time threshold, and marking it as an overtemperature risk value. It should be noted that the larger the value of the overtemperature risk value, the greater the abnormal risk of the rolling bearing.

[0041] Obtain a running track characteristic diagram of the rolling element in the rolling bearing in each sub-time period, and compare and analyze the running track characteristic diagram with the preset running track characteristic diagram for coincidence, obtain the difference value between the running track characteristic diagram and the preset running track characteristic diagram, obtain the number of sub-time periods corresponding to which the difference value is greater than the preset standard value, and mark the ratio of the number of sub-time periods corresponding to which the difference value is greater than the preset standard value to the total number of sub-time periods as the deviation risk value, wherein the larger the deviation risk value, the greater the abnormal risk of the rolling bearing;

[0042] Compare and analyze the over-temperature risk value and the offset risk value with the preset over-temperature risk value threshold and the preset offset risk value threshold that are stored internally:

[0043] If the over-temperature risk value is less than or equal to the preset over-temperature risk value threshold, and the deviation risk value is less than or equal to the preset deviation risk value threshold, an operation signal is generated and sent to the operation management analysis unit;

[0044] If the over-temperature risk value is greater than the preset over-temperature risk value threshold, or the offset risk value is greater than the preset offset risk value threshold, a risk signal is generated, and the risk signal is sent to the acquisition and analysis unit and the filtering and analysis unit to further analyze whether the rolling bearing is faulty, so as to improve the accuracy of the analysis result;

[0045] After receiving the operation signal, the operation management analysis unit immediately retrieves the working data from the supervision analysis unit and conducts further trend development analysis on the working data, so as to rationalize the management of rolling bearings in the later stage and reduce the failure rate of rolling bearings. The specific further trend development analysis process is as follows:

[0046] Obtain the over-temperature risk value and offset risk value within the time threshold, and label them as GW and PX respectively;

[0047] According to the formula An operation risk assessment coefficient is obtained, wherein b1 and b2 are respectively preset weight coefficients of the overtemperature risk value and the offset risk value, b3 is a preset fault tolerance coefficient, b1, b2 and b3 are all positive numbers greater than zero, G is an operation risk assessment coefficient, and at the same time, the operation risk assessment coefficient of the rolling bearing that operates normally within the historical k time thresholds is obtained, k is a natural number greater than zero, and a rectangular coordinate system is established with time as the X-axis and the operation risk assessment coefficient Gk as the Y-axis. An operation risk assessment coefficient curve is drawn by drawing points, and an ascending segment and a descending segment are obtained from the operation risk assessment coefficient curve, and then the difference between the two endpoints of the ascending end is obtained, thereby obtaining the sum of the differences between the two endpoints of the ascending end, and marking it as a risk trend value FQ, and the difference between the two endpoints of the descending segment is obtained, thereby obtaining the sum of the differences between the two endpoints of the descending segment, and marking it as a safety trend value AD;

[0048] According to the formula Obtain the operation risk trend rate, where F is the operation risk trend rate, and compare and analyze the operation risk trend rate F with the preset operation risk trend rate interval stored internally: if the operation risk trend rate F is greater than the maximum value in the preset operation risk trend rate interval, a primary maintenance signal is generated; if the operation risk trend rate F is within the preset operation risk trend rate interval, a secondary maintenance signal is generated;

[0049] If the operation risk trend rate F is less than the minimum value in the preset operation risk trend rate interval, a three-level maintenance signal is generated, wherein the maintenance degrees corresponding to the first-level maintenance signal, the second-level maintenance signal and the third-level maintenance signal are successively reduced, and the first-level maintenance signal, the second-level maintenance signal and the third-level maintenance signal are sent to the early warning display unit. After receiving the first-level maintenance signal, the second-level maintenance signal and the third-level maintenance signal, the early warning display unit immediately displays the preset early warning texts corresponding to the first-level maintenance signal, the second-level maintenance signal and the third-level maintenance signal, thereby helping the operation management personnel to perform reasonable and targeted maintenance and management of the rolling bearings according to the early warning texts to reduce the failure rate of the rolling bearings.

[0050] Embodiment 2:

[0051] After receiving the risk signal, the filter analysis unit immediately collects the filter operation data, including the line risk value and abnormal characteristic value, and performs filter operation risk assessment and analysis on the operation data to determine whether the filter is operating normally, so as to avoid the environment from interfering with the vibration signal of the rolling bearing and affecting the accuracy of the rolling bearing fault diagnosis and analysis results. The specific filter operation risk assessment and analysis process is as follows:

[0052] The line risk value of the filter in each sub-time period is obtained. The line risk value refers to the product of the reactive power value of the line inside the filter, the oxidation area of ​​the line port, and the number of line bulges after normalization. After taking time as X and the line risk value as the Y axis, a rectangular coordinate system is established. The line risk value curve is drawn by plotting points. The ratio of the number of segments corresponding to the rising segment to the number of segments corresponding to the falling segment is obtained from the line risk value curve, and it is marked as the line risk trend value XQ. It should be noted that the larger the value of the line risk trend value XQ, the greater the risk of filter abnormality.

[0053] The abnormal characteristic value of the filter in each sub-time period is obtained, and the abnormal characteristic value refers to the sum of the temperature difference of the filter and the part of the noise decibel value exceeding the preset noise decibel value after dedimensionalization, wherein the temperature difference refers to the difference between the internal temperature of the filter and the external shell temperature, and the abnormal characteristic value is compared and analyzed with the preset abnormal characteristic value threshold. If the abnormal characteristic value is greater than the preset abnormal characteristic value threshold, the ratio of the part of the abnormal characteristic value greater than the preset abnormal characteristic value threshold to the preset abnormal characteristic value threshold is marked as an abnormal risk value, which is labeled YZ. It should be noted that the abnormal risk value is an influencing parameter reflecting the operation of the filter;

[0054] According to the formula The filtering risk assessment coefficient is obtained, where a1 and a2 are preset proportional factor coefficients for the line risk trend value and the abnormal risk value, respectively. The proportional factor coefficient is used to correct the deviation of various parameters in the formula calculation process, so as to make the calculation result more accurate. Both a1 and a2 are positive numbers greater than zero. A3 is the preset correction factor coefficient, which is 2.868. Q is the filtering risk assessment coefficient. The size of the coefficient is to quantify each parameter to obtain a specific value, which is convenient for subsequent comparison. As long as it does not affect the proportional relationship between the parameter and the quantified value, the filtering risk assessment coefficient Q is compared with the preset filtering risk assessment coefficient threshold value stored in the internal input:

[0055] If the ratio of the filtering risk assessment coefficient Q to the preset filtering risk assessment coefficient threshold is less than one, a normal signal is generated and sent to the diagnosis and analysis unit;

[0056] If the ratio of the filter risk assessment coefficient Q to the preset filter risk assessment coefficient threshold is greater than or equal to one, an abnormal signal is generated and sent to the early warning display unit and the acquisition and analysis unit. After receiving the abnormal signal, the early warning display unit immediately displays the warning in the form of the text "filter abnormality", and then promptly repairs the abnormal filter to ensure the validity of the subsequent analysis data and the accuracy of the analysis results;

[0057] Upon receiving the risk signal and abnormal signal, the acquisition and analysis unit immediately collects the operation data of the filter after maintenance, and performs secondary analysis on the operation data to obtain the secondary filtering risk assessment coefficient, and compares and analyzes the secondary filtering risk assessment coefficient with the preset filtering risk assessment coefficient threshold value stored in the internal input:

[0058] If the secondary filtering risk assessment coefficient is less than the preset filtering risk assessment coefficient threshold, a feedback signal is generated and sent to the diagnosis and analysis unit;

[0059] If the secondary filtering risk assessment coefficient is greater than or equal to the preset filtering risk assessment coefficient threshold, a display signal is generated, and the display signal is sent to the early warning display unit through the filtering analysis unit. After receiving the display signal, the early warning display unit immediately displays an early warning in the form of text "filter secondary abnormality" to remind the operation management personnel to ensure that the filter maintenance is normal;

[0060] After receiving the feedback signal or the normal signal, the diagnosis and analysis unit immediately collects the vibration signal of the rolling bearing, converts the vibration signal into a time-frequency ridge feature graph according to the prior art, and performs an in-depth diagnosis, evaluation and analysis on the time-frequency ridge feature graph. The specific in-depth diagnosis, evaluation and analysis process is as follows:

[0061] The time-frequency ridge feature diagram of the rolling bearing corresponding to each risk signal within the time threshold is obtained, and the time-frequency ridge feature diagram is compared and analyzed with the preset fault samples recorded and stored internally to obtain the fault result, and the fault result is sent to the early warning display unit. After receiving the fault result, the early warning display unit displays it in the form of text and images, and then performs fault management on the rolling bearing.

[0062] In summary, the present invention collects the working data of rolling bearings, and performs fault risk assessment analysis and further trend development analysis on the working data, that is, analyzes from two perspectives: rolling bearing fault risk and fault risk development trend, so as to reasonably and targetedly perform maintenance and management on rolling bearings, and perform fault diagnosis on abnormal rolling bearings. Before diagnosis, the filter that affects the analysis and results of the collected data is analyzed, the line risk value and abnormal characteristic value of the filter are collected, and it is judged whether the filter is operating normally, so as to avoid the environment from interfering with the vibration signal of the rolling bearing and affecting the accuracy of the rolling bearing fault diagnosis analysis results, thereby helping to ensure subsequent analysis The validity of the data is evaluated, and a secondary analysis is performed on the abnormal filters. The results are transmitted through data feedback. The fault characteristics of the rolling bearing are analyzed by converting the vibration signal into a time-frequency ridge feature diagram, and then targeted fault management is performed on the rolling bearing according to the fault characteristics to improve the diagnostic accuracy and management rationality of the rolling bearing. The operation risk trend rate is obtained by analyzing the two-dimensional coordinate system and the historical rolling bearing operation risk assessment coefficient, and the operation risk trend rate is judged so that the operation management personnel can perform reasonable and targeted maintenance management on the rolling bearing according to the different maintenance levels obtained to reduce the failure rate of the rolling bearing.

[0063] The size of the threshold is set to facilitate comparison. The size of the threshold depends on the amount of sample data and the number of bases set by technicians in this field for each group of sample data; as long as it does not affect the proportional relationship between the parameter and the quantized value. The above formulas are obtained by collecting a large amount of data for software simulation and selecting a formula close to the true value. The coefficients in the formula are set by technicians in this field according to actual conditions. The above is only a preferred specific implementation of the present invention, but the protection scope of the present invention is not limited to this. Any technician familiar with this technical field, within the technical scope disclosed by the present invention, shall make equivalent replacements or changes according to the technical solution and inventive concept of the present invention, which should be covered within the protection scope of the present invention.

Claims

1. A rolling bearing fault feature diagnosis and management system based on data analysis, characterized in that: It includes a management platform, a supervision and analysis unit, a collection and analysis unit, a filtering and analysis unit, a diagnosis and analysis unit, an operation and management analysis unit, and an early warning and display unit; When the management platform generates an operation management instruction and sends the operation management instruction to the supervision and analysis unit, the supervision and analysis unit is used to collect the working data of the rolling bearing, the working data includes the operating temperature of the rolling bearing and the running track characteristic diagram of the rolling element in the rolling bearing, and perform fault risk assessment and analysis on the working data, and send the obtained operation signal to the operation management analysis unit, and send the obtained risk signal to the collection analysis unit and the filtering analysis unit; After receiving the operation signal, the operation management analysis unit immediately retrieves the working data from the supervision analysis unit, and further analyzes the trend development of the working data, and sends the obtained primary maintenance signal, secondary maintenance signal and tertiary maintenance signal to the early warning display unit; The filter analysis unit immediately collects the filter operation data after receiving the risk signal, the operation data includes the line risk value and the abnormal characteristic value, and performs filter operation risk assessment and analysis on the operation data, sends the obtained normal signal to the diagnosis analysis unit, and sends the obtained abnormal signal to the early warning display unit and the collection and analysis unit; Upon receiving the risk signal and abnormal signal, the collection and analysis unit immediately collects the operation data of the filter after maintenance, performs secondary analysis on the operation data, sends the obtained feedback signal to the diagnosis and analysis unit, and sends the obtained display signal to the early warning display unit via the filter analysis unit; After receiving the feedback signal or the normal signal, the diagnostic analysis unit immediately collects the vibration signal of the rolling bearing, converts the vibration signal into a time-frequency ridge feature diagram according to the existing technology, and performs in-depth diagnostic evaluation and analysis on the time-frequency ridge feature diagram, and sends the obtained fault result to the early warning display unit.

2. A rolling bearing fault feature diagnosis and management system based on data analysis according to claim 1, characterized in that: The fault risk assessment and analysis process of the supervision and analysis unit is as follows: The duration between the start and end of the running time of the rolling bearing is collected and marked as the time threshold, the time threshold is divided into i sub-time periods, i is a natural number greater than zero, the running temperature of the rolling bearing in each sub-time period is obtained, and the running temperature is compared and analyzed with the preset running temperature threshold. If the running temperature is greater than the preset running temperature threshold, the part where the running temperature is greater than the preset running temperature threshold is marked as an overheating value, so as to obtain the sum of the overheating values ​​of the rolling bearing within the time threshold, and mark it as the overtemperature risk value; Obtain a running track characteristic diagram of the rolling element in the rolling bearing in each sub-time period, and compare and analyze the running track characteristic diagram with the preset running track characteristic diagram for coincidence, obtain the difference value between the running track characteristic diagram and the preset running track characteristic diagram, obtain the number of sub-time periods corresponding to which the difference value is greater than the preset standard value, and mark the ratio of the number of sub-time periods corresponding to which the difference value is greater than the preset standard value to the total number of sub-time periods as the deviation risk value; Compare and analyze the over-temperature risk value and the offset risk value with the preset over-temperature risk value threshold and the preset offset risk value threshold that are stored internally: If the over-temperature risk value is less than or equal to the preset over-temperature risk value threshold, and the offset risk value is less than or equal to the preset offset risk value threshold, then an operation signal is generated; If the over-temperature risk value is greater than a preset over-temperature risk value threshold, or the offset risk value is greater than a preset offset risk value threshold, a risk signal is generated.

3. A rolling bearing fault feature diagnosis and management system based on data analysis according to claim 1, characterized in that: The further trend development analysis process of the operation management analysis unit is as follows: Obtain the over-temperature risk value and offset risk value within the time threshold, and label them as GW and PX respectively; According to the formula An operation risk assessment coefficient is obtained, wherein b1 and b2 are respectively preset weight coefficients of the overtemperature risk value and the offset risk value, b3 is a preset fault tolerance coefficient, b1, b2 and b3 are all positive numbers greater than zero, G is an operation risk assessment coefficient, and at the same time, the operation risk assessment coefficient of the rolling bearing that operates normally within the historical k time thresholds is obtained, k is a natural number greater than zero, and a rectangular coordinate system is established with time as the X-axis and the operation risk assessment coefficient Gk as the Y-axis. An operation risk assessment coefficient curve is drawn by drawing points, and an ascending segment and a descending segment are obtained from the operation risk assessment coefficient curve, and then the difference between the two endpoints of the ascending end is obtained, thereby obtaining the sum of the differences between the two endpoints of the ascending end, and marking it as a risk trend value FQ, and the difference between the two endpoints of the descending segment is obtained, thereby obtaining the sum of the differences between the two endpoints of the descending segment, and marking it as a safety trend value AD; According to the formula The operation risk trend rate is obtained, where F is the operation risk trend rate, and the operation risk trend rate F is compared and analyzed with the preset operation risk trend rate range stored in the internal entry: If the operation risk trend rate F is greater than the maximum value in the preset operation risk trend rate interval, a first-level maintenance signal is generated; if the operation risk trend rate F is within the preset operation risk trend rate interval, a second-level maintenance signal is generated; if the operation risk trend rate F is less than the minimum value in the preset operation risk trend rate interval, a third-level maintenance signal is generated.

4. A rolling bearing fault feature diagnosis and management system based on data analysis according to claim 1, characterized in that: The filtering operation risk assessment analysis process of the filtering analysis unit is as follows: The line risk value of the filter in each sub-time period is obtained. The line risk value refers to the product of the reactive power value of the filter internal line, the oxidation area of ​​the line port, and the number of line bulges after normalization. After taking time as X and the line risk value as the Y axis, a rectangular coordinate system is established. The line risk value curve is drawn by plotting points. The ratio of the number of segments corresponding to the rising segment to the number of segments corresponding to the falling segment is obtained from the line risk value curve, and it is marked as the line risk trend value XQ; The abnormal characteristic value of the filter in each sub-time period is obtained, and the abnormal characteristic value refers to the sum of the temperature difference of the filter and the part of the noise decibel value exceeding the preset noise decibel value after dedimensionalization, wherein the temperature difference refers to the difference between the internal temperature of the filter and the external shell temperature, and the abnormal characteristic value is compared and analyzed with the preset abnormal characteristic value threshold. If the abnormal characteristic value is greater than the preset abnormal characteristic value threshold, the ratio of the part of the abnormal characteristic value greater than the preset abnormal characteristic value threshold to the preset abnormal characteristic value threshold is marked as the abnormal risk value YZ; According to the formula The filtering risk assessment coefficient Q is obtained, wherein a1 and a2 are the preset proportional factor coefficients of the line risk trend value and the abnormal risk value respectively, a1 and a2 are both positive numbers greater than zero, a3 is the preset correction factor coefficient, and its value is 2.

868. The filtering risk assessment coefficient Q is compared and analyzed with the preset filtering risk assessment coefficient threshold value entered and stored internally: if the ratio of the filtering risk assessment coefficient Q to the preset filtering risk assessment coefficient threshold value is less than one, a normal signal is generated; if the ratio of the filtering risk assessment coefficient Q to the preset filtering risk assessment coefficient threshold value is greater than or equal to one, an abnormal signal is generated.

5. The rolling bearing fault feature diagnosis and management system based on data analysis according to claim 1, characterized in that: The secondary analysis process of the acquisition and analysis unit is as follows: Obtain the secondary filtering risk assessment coefficient, and compare and analyze the secondary filtering risk assessment coefficient with the preset filtering risk assessment coefficient threshold value stored internally: if the secondary filtering risk assessment coefficient is less than the preset filtering risk assessment coefficient threshold value, generate a feedback signal; If the secondary filtering risk assessment coefficient is greater than or equal to the preset filtering risk assessment coefficient threshold, a display signal is generated.

6. The rolling bearing fault feature diagnosis and management system based on data analysis according to claim 1, characterized in that: The in-depth diagnostic evaluation and analysis process of the diagnostic analysis unit is as follows: The time-frequency ridge feature diagram of the rolling bearing corresponding to each risk signal within the time threshold is obtained, and the time-frequency ridge feature diagram is compared and analyzed with the preset fault samples recorded and stored internally to obtain the fault result. After receiving the fault result, the early warning display unit displays it in the form of text and images.

Images