Mechanical equipment operation data management method and system based on big data

Abstract

The invention discloses a mechanical equipment operation data management method and system based on big data, and belongs to the technical field of equipment detection. The system comprises a data acquisition module, an anomaly analysis module, an operation management module and a visualization module. The data acquisition module is used for acquiring historical logs and structural diagrams of the mechanical equipment and vibration amplitudes of all parts; the anomaly analysis module is used for analyzing fault records in historical logs, establishing sampling points, sorting the sampling points, dividing the sorted sampling points into different combination areas, calculating a first coefficient according to information of the sampling points in the different combination areas, and defining an abnormal object; the operation management module analyzes a conduction relation between the parts according to the structure chart, defines a conduction object, calculates a second coefficient and a third index after associating an abnormal object with the conduction object, and identifies the abnormal parts and a potential safety hazard area through the third index; and the visual module is used for displaying a potential safety hazard area in the mechanical equipment, recording information of each part and storing the information into a historical log.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment detection, and in particular to a method and system for managing mechanical equipment operation data based on big data. Background Art

[0002] With the acceleration of industrialization, mechanical equipment is increasingly used in various industries. However, the downtime and maintenance costs caused by equipment failure have a huge impact on production efficiency and equipment life. Therefore, improving the reliability and availability of equipment has become an urgent need for enterprises.

[0003] At present, the detection of equipment failures usually relies on automated control systems, which automatically monitor the operating data of various components in mechanical equipment by setting programs and sensors, and automatically handle minor faults according to the control system or control the shutdown and waiting for maintenance when facing major faults. This method has certain problems. On the one hand, the existing technology only performs simple threshold judgment on the operating data to detect anomalies, and does not conduct in-depth analysis and processing of these data. It is impossible to predict the probability of failure and cannot quickly locate the source of the failure. On the other hand, there is often force transmission between the various components in mechanical equipment. When they are connected and moving with each other, the failure of one component will often affect another component, causing the failure of another component not caused by itself under long-term influence. The existing technology usually does not consider the impact of this aspect, and the lack of data accuracy in the fault detection and analysis process leads to invalid analysis. Therefore, at this stage, a more intelligent and efficient operation data management technology solution is needed to solve the above problems. Summary of the invention

[0004] The purpose of the present invention is to provide a mechanical equipment operation data management method and system based on big data to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the present invention provides a mechanical equipment operation data management method based on big data, comprising the following steps:

[0006] S100, collecting historical logs and structural diagrams of mechanical equipment, and collecting vibration amplitude information of each component during the operation of the mechanical equipment in real time through sensors and monitoring software.

[0007] S200, establishing sampling points by analyzing the fault records in the historical log, sorting the sampling points and dividing them into different combination areas, calculating the first coefficient according to the standard deviation of the interval time of the sampling points in different combination areas, and defining abnormal objects.

[0008] S300, analyzing the conduction relationship between components according to the structural diagram and defining conduction objects, associating abnormal objects with the conduction objects, calculating a second coefficient and a third index, and identifying abnormal components and safety hazard areas through the third index.

[0009] S400, display the potential safety hazard areas in the mechanical equipment through a visual screen, update the potential safety hazard areas in real time according to the vibration amplitude information, record the information of each component in the mechanical equipment and store it in a historical log.

[0010] In S100, the history log includes the fault record and operation record of each component of the mechanical equipment. Each fault record includes the component code and fault time, and each operation record includes the component code and vibration change graph. The vibration change graph represents the vibration amplitude change of the component during each operation time. The vibration information is collected in real time by the sensor and handed over to the monitoring software to draw the vibration change graph.

[0011] The structural diagram shows the various components in the mechanical equipment and the conduction relationship between them. Conduction refers to the transmission of force between the components inside the mechanical equipment through contact and connection.

[0012] Only when a component fails will the failure time be automatically recorded and a failure record generated. Failure means that the component has abnormal parameters that do not meet the normal operating state, not that it is completely paralyzed and cannot work. After the failure occurs, the correction system in the mechanical equipment will automatically handle the faulty component.

[0013] The operation record is automatically generated only when the parts are started and operated each time the mechanical equipment is running. The vibration change graph in the operation record refers to the line graph of the vibration amplitude of the parts changing with time during the operation process. By analyzing the line graph, you can quickly understand the vibration amplitude of the parts at different times.

[0014] In S200, the specific steps are as follows:

[0015] S201. Obtain all fault records of component BN1 in the history log and count the total number h of fault records, and sort the h fault records in order from earliest to latest according to the fault time.

[0016] A sampling point is established for every two adjacent fault records according to the arrangement order, and the difference dt and the average te of the fault time in the two adjacent fault records are calculated respectively. dt and te are used as the interval duration and sampling time of the corresponding sampling point respectively.

[0017] According to the number of fault records L of each component, L-1 sampling points are established, and the interval duration and sampling time of each sampling point are calculated.

[0018] The interval time refers to the interval time between the sampling point and the two fault records. The sampling time refers to the middle time between the sampling point and the two fault records.

[0019] S202: Create a sampling set for each component, count the number of sampling points e for the same component, and put them into the corresponding sampling set in order from early to late according to the sampling time, and obtain {n1, n2, n3, ..., n e}.

[0020] Set the gap threshold Q thr , calculate the standard deviation of the interval between sampling points n1 and n2 and determine whether it is less than Q thr If it is less than, create a combined area and add n1 and n2, and calculate n1, n2 and n again. e If it is not less than, calculate the standard deviation of the interval between sampling points n2 and n3 and make a judgment.

[0021] Similarly, two or more adjacent sampling points are placed in the same combination area according to the standard deviation. The sampling points in different combination areas are different and the standard deviation of the interval time of all sampling points in each combination area is less than Q thr .

[0022] The setting of the combined area can avoid the interference of sudden accidental failures on the overall data, and screen out stable failure intervals to make subsequent analysis results more accurate and stable.

[0023] S203, analyzing the earliest fault time T in the fault records corresponding to all sampling points in the combined area early and the latest failure time T late ; T early to T late As the fault time period of the corresponding combination area.

[0024] Get the sampling set of component BN2, and select the last combination area Z according to the order of sampling points in the sampling set. last , analyze the vibration change diagram in the operation record of component BN2 and calculate the average vibration amplitude zfd ave and Z last The average amplitude of vibration during the fault period fd ave .

[0025] Substitute into the formula to calculate the first coefficient XS for each component one , set the coefficient threshold XS thr , the first coefficient greater than XS thr The parts are taken as abnormal objects; the first coefficient calculation formula is as follows:

[0026]

[0027] In the formula, α is a constant, k is the number of combination zones in the sampling set, and BZ i is the standard deviation of the interval time of all sampling points in the i-th combined area.

[0028] Each combination area has a fault time period. First, obtain all sampling points under the combination and the two fault records corresponding to each sampling point. Then analyze the fault time in these fault records, find the earliest fault time and the latest fault time as the interval endpoints, and establish the fault time period according to the interval value.

[0029] Amplitude refers to the maximum distance that a vibrating particle deviates from its equilibrium position, and it reflects the strength or magnitude of the vibration. The larger the amplitude, the more violent the vibration and the greater the energy. Amplitude is usually expressed in units of length, and for complex vibration waveforms, the peak value or root mean square value can also be used to describe the amplitude.

[0030] In S300, the specific steps are as follows:

[0031] S301, analyzing the conduction relationship between the components in the structure diagram, selecting the components that have a conduction relationship with the abnormal object DX1 as the conduction objects of DX1. Associating the abnormal object with each of its conduction objects, respectively, obtaining the sampling time of each sampling point under each pair of associated objects and the fault time period of each combination area.

[0032] Set the impact duration s, associate the two sampling points in each pair of associated objects whose sampling time difference is less than s and do not belong to the same object, and associate the two combination areas whose fault time period difference is less than s and do not belong to the same object.

[0033] S302: Divide the interval time difference of each pair of associated sampling points by the sampling time difference to obtain a sampling coefficient, and divide the standard deviation difference of each pair of associated combination areas by the fault time difference to obtain a gap coefficient. Substitute the sampling coefficient and the gap coefficient into the formula to calculate the second coefficient XS of each pair of associated objects. two , the formula is as follows:

[0034]

[0035] Where v is the logarithm of the associated sampling points, jS c is the sampling coefficient of the cth pair of associated sampling points, JS ave is the average sampling coefficient of all associated sampling points, f is the logarithm of the associated combination area, CJ g is the gap coefficient of the g-th pair of associated combination areas, CJ ave is the average value of the gap coefficients of all associated combination areas.

[0036] The first coefficient indicates the abnormality of the state of the component. When the average amplitude of the vibration at the latest time is larger than before, and the standard deviation of the interval time of all sampling points in the combination area increases one by one, the abnormality of the state is higher. The second coefficient indicates the difference between the states of the two components corresponding to each pair of associated objects. When the standard deviation of the sampling coefficient and the gap coefficient of each pair of associated combination areas is larger, the difference between the two states is higher.

[0037] S303: Obtain the second coefficient of each pair of associated objects and the first coefficient of each object therein, and substitute them into the formula to calculate the third index of each pair of associated objects. Set the index threshold ZS thr , marking the third index greater than ZS thr The associated object of the mark is used, and the two parts corresponding to the associated object are regarded as abnormal parts, and the connection between the abnormal parts is regarded as the safety hazard area; wherein, the calculation formula of the third index is as follows:

[0038]

[0039] In the formula, ZS is the third index, β is a constant, is the first coefficient of one of the objects in the associated object, The first coefficient of another object in the associated object.

[0040] The third index indicates the degree of state synchronization of the two components corresponding to each pair of associated objects. When the first coefficient is higher and the second coefficient is lower, it means that there is a high degree of synchronization between the two in the frequency of failure, which can be regarded as a mutual influence relationship between the failures.

[0041] In S400, each potential safety hazard area is displayed in real time through a visual screen on the mechanical equipment, and a vibration change diagram of the corresponding components in the potential safety hazard area is displayed.

[0042] The relationship between components includes one-to-many, many-to-one and many-to-many. Therefore, even the same component connection can be marked as a safety hazard area multiple times. On the structure diagram, multiple marked associated objects are marked according to the conduction relationship, and the number of marks for each safety hazard area is marked, and the fault conduction direction, route and source location are intuitively displayed on the visualization screen.

[0043] The safety hazard area is updated in real time according to the change of vibration amplitude. The vibration change diagram is drawn in real time through the amplitude change of each component of the mechanical equipment and the failure time of each component is recorded. The fault record and operation record are generated and stored in the historical log.

[0044] The mechanical equipment operation data management system based on big data includes data acquisition module, abnormality analysis module, operation management module and visualization module.

[0045] The data acquisition module is used to collect historical logs and structural diagrams of mechanical equipment, as well as the vibration amplitude of each component during the operation of the mechanical equipment.

[0046] The abnormal analysis module is used to analyze the fault records in the historical log and establish sampling points, sort the sampling points and divide them into different combination areas, calculate the first coefficient according to the standard deviation of the interval time of the sampling points in different combination areas, and define the abnormal object.

[0047] The operation management module analyzes the conduction relationship between components according to the structural diagram and defines the conduction object. After associating the abnormal object with the conduction object, the second coefficient and the third index are calculated. The abnormal components and safety hazard areas are identified through the third index.

[0048] The visualization module is used to display the potential safety hazards in mechanical equipment, record the information of each component and store it in the historical log.

[0049] The data collection module includes a history log collection unit, a structure information collection unit and an operation status collection unit.

[0050] The historical log collection unit is used to collect the fault records and operation records of each component under the mechanical equipment.

[0051] Each fault record includes a component code and fault time, and each operation record includes a component code and a vibration change graph. The vibration change graph indicates the change in vibration amplitude of the component during each operation time.

[0052] The structural information acquisition unit is used to acquire the structural diagram of the mechanical equipment.

[0053] The structural diagram shows the various components in the mechanical equipment and the conduction relationship between them. Conduction refers to the transmission of force between the components inside the mechanical equipment through contact and connection.

[0054] The operation status acquisition unit is used to collect the vibration amplitude of each component during the operation of the mechanical equipment.

[0055] The abnormality analysis module includes a region division unit and an abnormality analysis unit.

[0056] The area division unit is used to establish sampling points and divide them into different combination areas.

[0057] First, retrieve all fault records under the same component in the historical log, and sort these fault records in order of fault time. Establish a sampling point for every two adjacent fault records, and calculate the difference dt and average te of the fault time in the two adjacent fault records as the interval length and sampling time of the corresponding sampling point respectively.

[0058] Then, a sampling set is established for each component, and the number of sampling points under the component is counted, and they are put into the corresponding sampling set in order from early to late according to the sampling time, and {n1, n2, n3, ..., n e}.

[0059] Set the gap threshold Q thr , calculate the standard deviation of the interval between sampling points n1 and n2 and determine whether it is less than Q thr If it is less than, create a combined area and add n1 and n2, and calculate n1, n2 and n again. e If it is not less than, calculate the standard deviation of the interval between sampling points n2 and n3 and make a judgment.

[0060] Similarly, two or more adjacent sampling points are placed in the same combination area according to the standard deviation. The sampling points in different combination areas are different and the standard deviation of the interval time of all sampling points in each combination area is less than Q thr .

[0061] The anomaly analysis unit is used to calculate the first coefficient of each component and define anomaly objects.

[0062] First, analyze the earliest fault time T in the fault records corresponding to all sampling points in the combined area early and the latest failure time T late ; T early to T lat e as the fault time period of the corresponding combination area.

[0063] Secondly, obtain the sampling set of parts and select the last combination area Z according to the order of sampling points in the sampling set. last , analyze the vibration change diagram in the component operation record and calculate the average vibration amplitude zfd ave and Z last The average amplitude of vibration during the fault period fd ave .

[0064] Finally, according to the formula Calculate the first coefficient XS for each component one , set the coefficient threshold XS thr , the first coefficient greater than XS thr The parts are taken as abnormal objects. Among them, α is a constant, k is the number of combination areas in the sampling set, BZ i is the standard deviation of the interval time of all sampling points in the i-th combined area.

[0065] The operation management module includes a relationship analysis unit and a hidden danger identification unit.

[0066] The relationship analysis unit is used to establish the relationship between components.

[0067] First, the conduction relationship between the components in the structure diagram is analyzed, and the components that have a conduction relationship with the abnormal object DX1 are selected as the conduction objects of DX1.

[0068] Secondly, the abnormal object is associated with each of its conductive objects respectively, and the sampling time of each sampling point under each pair of associated objects and the fault time period of each combination area are obtained.

[0069] Finally, the impact duration s is set, and the two sampling points in each pair of associated objects whose sampling time difference is less than s and do not belong to the same object are associated, and the two combined areas whose fault time period difference is less than s and do not belong to the same object are associated.

[0070] The hidden danger identification unit is used to identify abnormal parts and safety hazard areas.

[0071] First, divide the interval time difference of each pair of associated sampling points by the sampling time difference to obtain the sampling coefficient, and divide the standard deviation difference of each pair of associated combination areas by the fault time difference to obtain the gap coefficient. Substitute the sampling coefficient and gap coefficient into the formula In the above example, the second coefficient XS of each pair of associated objects is calculated separately. two .

[0072] Where v is the logarithm of the associated sampling points, JS c is the sampling coefficient of the cth pair of associated sampling points, JS ave is the average sampling coefficient of all associated sampling points, f is the logarithm of the associated combination area, CJ g is the gap coefficient of the g-th pair of associated combination areas, CJ ave is the average value of the gap coefficients of all associated combination areas.

[0073] Then set the index threshold ZS thr , and obtain the second coefficient of each pair of associated objects and the first coefficient of each object in it, according to the formula Compute the third index of each pair of associated objects.

[0074] Mark the third index greater than ZS thr The associated objects are marked, the two parts corresponding to the associated objects are marked as abnormal parts, and the connection between the abnormal parts is regarded as a safety hazard area.

[0075] Where β is a constant, is the first coefficient of one of the objects in the associated object, The first coefficient of another object in the associated object.

[0076] The visualization module displays various safety hazard areas through the visualization screen on the mechanical equipment, and updates the safety hazard areas in real time according to the changes in vibration amplitude. It draws a vibration change graph in real time and records the failure time of each component each time. It generates fault records and operation records and stores them in the history log.

[0077] Compared with the prior art, the beneficial effects achieved by the present invention are:

[0078] First, we conduct data analysis on the fault records of each component of the mechanical equipment, establish several sampling points, and calculate the interval and sampling time of each sampling point, so as to calculate the first coefficient and identify abnormal objects based on the first coefficient. Secondly, we analyze the conduction relationship between the components in the mechanism diagram, and calculate the second coefficient by analyzing the degree of difference between the two components through the sampling coefficient and the gap coefficient. Finally, we calculate the third index of each pair of associated objects based on the first coefficient and the second coefficient, so as to identify abnormal components and safety hazard areas. We mark the abnormal components on the structure diagram according to the conduction relationship, as well as the number of marks for each safety hazard area, which can intuitively display the direction, route and source location of the fault conduction.

[0079] To sum up, compared with traditional monitoring methods, the technology of the present application provides a more comprehensive fault monitoring and early warning technical solution by analyzing fault records and operation records in operation data. It can more accurately judge abnormal situations and take corresponding measures in advance, and has higher practicality and innovation. BRIEF DESCRIPTION OF THE DRAWINGS

[0080] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0081] Figure 1 It is a flow chart of a method for managing mechanical equipment operation data based on big data of the present invention;

[0082] Figure 2 It is a structural diagram of the mechanical equipment operation data management system based on big data of the present invention. DETAILED DESCRIPTION

[0083] 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.

[0084] See also Figure 1The present invention provides a mechanical equipment operation data management method based on big data, comprising the following steps:

[0085] S100, collecting historical logs and structural diagrams of mechanical equipment, and collecting vibration amplitude information of each component during the operation of the mechanical equipment in real time through sensors and monitoring software.

[0086] S200, establishing sampling points by analyzing the fault records in the historical log, sorting the sampling points and dividing them into different combination areas, calculating the first coefficient according to the standard deviation of the interval time of the sampling points in different combination areas, and defining abnormal objects.

[0087] S300, analyzing the conduction relationship between components according to the structural diagram and defining conduction objects, associating abnormal objects with the conduction objects, calculating a second coefficient and a third index, and identifying abnormal components and safety hazard areas through the third index.

[0088] S400, display the potential safety hazard areas in the mechanical equipment through a visual screen, update the potential safety hazard areas in real time according to the vibration amplitude information, record the information of each component in the mechanical equipment and store it in a historical log.

[0089] In S100, the history log includes the fault record and operation record of each component of the mechanical equipment. Each fault record includes the component code and fault time, and each operation record includes the component code and vibration change graph. The vibration change graph represents the vibration amplitude change of the component during each operation time. The vibration information is collected in real time by the sensor and handed over to the monitoring software to draw the vibration change graph.

[0090] The structural diagram shows the various components in the mechanical equipment and the conduction relationship between them. Conduction refers to the transmission of force between the components inside the mechanical equipment through contact and connection.

[0091] Only when a component fails will the failure time be automatically recorded and a failure record generated. Failure means that the component has abnormal parameters that do not meet the normal operating state, not that it is completely paralyzed and cannot work. After the failure occurs, the correction system in the mechanical equipment will automatically handle the faulty component.

[0092] The operation record is automatically generated only when the parts are started and operated each time the mechanical equipment is running. The vibration change graph in the operation record refers to the line graph of the vibration amplitude of the parts changing with time during the operation process. By analyzing the line graph, you can quickly understand the vibration amplitude of the parts at different times.

[0093] In S200, the specific steps are as follows:

[0094] S201. Obtain all fault records of component BN1 in the history log and count the total number h of fault records, and sort the h fault records in order from earliest to latest according to the fault time.

[0095] A sampling point is established for every two adjacent fault records according to the arrangement order, and the difference dt and the average te of the fault time in the two adjacent fault records are calculated respectively. dt and te are used as the interval duration and sampling time of the corresponding sampling point respectively.

[0096] According to the number of fault records L of each component, L-1 sampling points are established, and the interval duration and sampling time of each sampling point are calculated.

[0097] The interval time refers to the interval time between the sampling point and the two fault records. The sampling time refers to the middle time between the sampling point and the two fault records.

[0098] S202: Create a sampling set for each component, count the number of sampling points e for the same component, and put them into the corresponding sampling set in order from early to late according to the sampling time, and obtain {n1, n2, n3, ..., n e}.

[0099] Set the gap threshold Q thr , calculate the standard deviation of the interval between sampling points n1 and n2 and determine whether it is less than Q thr If it is less than, create a combined area and add n1 and n2, and calculate n1, n2 and n again. e If it is not less than, calculate the standard deviation of the interval between sampling points n2 and n3 and make a judgment.

[0100] Similarly, two or more adjacent sampling points are placed in the same combination area according to the standard deviation. The sampling points in different combination areas are different and the standard deviation of the interval time of all sampling points in each combination area is less than Q thr .

[0101] The setting of the combined area can avoid the interference of sudden accidental failures on the overall data, and screen out stable failure intervals to make subsequent analysis results more accurate and stable.

[0102] S203, analyzing the earliest fault time T in the fault records corresponding to all sampling points in the combined area early and the latest failure time T late ; T early to T late As the fault time period of the corresponding combination area.

[0103] Get the sampling set of component BN2, and select the last combination area Z according to the order of sampling points in the sampling set. last, analyze the vibration change diagram in the operation record of component BN2 and calculate the average vibration amplitude zfd ave and Z last The average amplitude of vibration during the fault period fd ave .

[0104] Substitute into the formula to calculate the first coefficient XS for each component one , set the coefficient threshold XS thr , the first coefficient greater than XS thr The parts are taken as abnormal objects; the first coefficient calculation formula is as follows:

[0105]

[0106] In the formula, α is a constant, k is the number of combination zones in the sampling set, and BZ i is the standard deviation of the interval time of all sampling points in the i-th combined area.

[0107] Each combination area has a fault time period. First, obtain all sampling points under the combination and the two fault records corresponding to each sampling point. Then analyze the fault time in these fault records, find the earliest fault time and the latest fault time as the interval endpoints, and establish the fault time period according to the interval value.

[0108] Amplitude refers to the maximum distance that a vibrating particle deviates from its equilibrium position, and it reflects the strength or magnitude of the vibration. The larger the amplitude, the more violent the vibration and the greater the energy. Amplitude is usually expressed in units of length, and for complex vibration waveforms, the peak value or root mean square value can also be used to describe the amplitude.

[0109] In S300, the specific steps are as follows:

[0110] S301, analyzing the conduction relationship between the components in the structure diagram, selecting the components that have a conduction relationship with the abnormal object DX1 as the conduction objects of DX1. Associating the abnormal object with each of its conduction objects, respectively, obtaining the sampling time of each sampling point under each pair of associated objects and the fault time period of each combination area.

[0111] Set the impact duration s, associate the two sampling points in each pair of associated objects whose sampling time difference is less than s and do not belong to the same object, and associate the two combination areas whose fault time period difference is less than s and do not belong to the same object.

[0112] S302: Divide the interval time difference of each pair of associated sampling points by the sampling time difference to obtain a sampling coefficient, and divide the standard deviation difference of each pair of associated combination areas by the fault time difference to obtain a gap coefficient. Substitute the sampling coefficient and the gap coefficient into the formula to calculate the second coefficient XS of each pair of associated objects. two , the formula is as follows:

[0113]

[0114] Where v is the logarithm of the associated sampling points, JS c is the sampling coefficient of the cth pair of associated sampling points, JS ave is the average sampling coefficient of all associated sampling points, f is the logarithm of the associated combination area, CJ g is the gap coefficient of the g-th pair of associated combination areas, CJ ave is the average value of the gap coefficients of all associated combination areas.

[0115] The first coefficient indicates the abnormality of the state of the component. When the average amplitude of the vibration at the latest time is larger than before, and the standard deviation of the interval time of all sampling points in the combination area increases one by one, the abnormality of the state is higher. The second coefficient indicates the difference between the states of the two components corresponding to each pair of associated objects. When the standard deviation of the sampling coefficient and the gap coefficient of each pair of associated combination areas is larger, the difference between the two states is higher.

[0116] S303: Obtain the second coefficient of each pair of associated objects and the first coefficient of each object therein, and substitute them into the formula to calculate the third index of each pair of associated objects. Set the index threshold ZS thr , marking the third index greater than ZS thr The associated object of the mark is used, and the two parts corresponding to the associated object are regarded as abnormal parts, and the connection between the abnormal parts is regarded as the safety hazard area; wherein, the calculation formula of the third index is as follows:

[0117]

[0118] In the formula, ZS is the third index, β is a constant, is the first coefficient of one of the objects in the associated object, The first coefficient of another object in the associated object.

[0119] The third index indicates the degree of state synchronization of the two components corresponding to each pair of associated objects. When the first coefficient is higher and the second coefficient is lower, it means that there is a high degree of synchronization between the two in the frequency of failure, which can be regarded as a mutual influence relationship between the failures.

[0120] In S400, each potential safety hazard area is displayed in real time through a visual screen on the mechanical equipment, and a vibration change diagram of the corresponding components in the potential safety hazard area is displayed.

[0121] The relationship between components includes one-to-many, many-to-one and many-to-many. Therefore, even the same component connection can be marked as a safety hazard area multiple times. On the structure diagram, multiple marked associated objects are marked according to the conduction relationship, and the number of marks for each safety hazard area is marked, and the fault conduction direction, route and source location are intuitively displayed on the visualization screen.

[0122] The safety hazard area is updated in real time according to the change of vibration amplitude. The vibration change diagram is drawn in real time through the amplitude change of each component of the mechanical equipment and the failure time of each component is recorded. The fault record and operation record are generated and stored in the historical log.

[0123] See also Figure 2 The present invention provides a mechanical equipment operation data management system based on big data, including a data acquisition module, an abnormality analysis module, an operation management module and a visualization module.

[0124] The data acquisition module is used to collect historical logs and structural diagrams of mechanical equipment, as well as the vibration amplitude of each component during the operation of the mechanical equipment.

[0125] The abnormal analysis module is used to analyze the fault records in the historical log and establish sampling points, sort the sampling points and divide them into different combination areas, calculate the first coefficient according to the standard deviation of the interval time of the sampling points in different combination areas, and define the abnormal object.

[0126] The operation management module analyzes the conduction relationship between components according to the structural diagram and defines the conduction object. After associating the abnormal object with the conduction object, the second coefficient and the third index are calculated. The abnormal components and safety hazard areas are identified through the third index.

[0127] The visualization module is used to display the potential safety hazards in mechanical equipment, record the information of each component and store it in the historical log.

[0128] The data collection module includes a history log collection unit, a structure information collection unit and an operation status collection unit.

[0129] The historical log collection unit is used to collect the fault records and operation records of each component under the mechanical equipment.

[0130] Each fault record includes a component code and fault time, and each operation record includes a component code and a vibration change graph. The vibration change graph indicates the change in vibration amplitude of the component during each operation time.

[0131] The structural information acquisition unit is used to acquire the structural diagram of the mechanical equipment.

[0132] The structural diagram shows the various components in the mechanical equipment and the conduction relationship between them. Conduction refers to the transmission of force between the components inside the mechanical equipment through contact and connection.

[0133] The operation status acquisition unit is used to collect the vibration amplitude of each component during the operation of the mechanical equipment.

[0134] The abnormality analysis module includes a region division unit and an abnormality analysis unit.

[0135] The area division unit is used to establish sampling points and divide them into different combination areas.

[0136] First, retrieve all fault records under the same component in the historical log, and sort these fault records in order of fault time. Establish a sampling point for every two adjacent fault records, and calculate the difference dt and average te of the fault time in the two adjacent fault records as the interval length and sampling time of the corresponding sampling point respectively.

[0137] Then, a sampling set is established for each component, and the number of sampling points under the component is counted, and they are put into the corresponding sampling set in order from early to late according to the sampling time, and {n1, n2, n3, ..., n e}.

[0138] Set the gap threshold Q thr , calculate the standard deviation of the interval between sampling points n1 and n2 and determine whether it is less than Q thr If it is less than, create a combined area and add n1 and n2, and calculate n1, n2 and n again. e If it is not less than, calculate the standard deviation of the interval between sampling points n2 and n3 and make a judgment.

[0139] Similarly, two or more adjacent sampling points are placed in the same combination area according to the standard deviation. The sampling points in different combination areas are different and the standard deviation of the interval time of all sampling points in each combination area is less than Q thr .

[0140] The anomaly analysis unit is used to calculate the first coefficient of each component and define anomaly objects.

[0141] First, analyze the earliest fault time T in the fault records corresponding to all sampling points in the combined area early and the latest failure time T late ; T early to T late As the fault time period of the corresponding combination area.

[0142] Secondly, obtain the sampling set of parts and select the last combination area Z according to the order of sampling points in the sampling set. last, analyze the vibration change diagram in the component operation record and calculate the average vibration amplitude zfd ave and Z last The average amplitude of vibration during the fault period fd ave .

[0143] Finally, according to the formula Calculate the first coefficient XS for each component one , set the coefficient threshold XS thr , the first coefficient greater than XS thr The parts are taken as abnormal objects. Among them, α is a constant, k is the number of combination areas in the sampling set, BZ i is the standard deviation of the interval time of all sampling points in the i-th combined area.

[0144] The operation management module includes a relationship analysis unit and a hidden danger identification unit.

[0145] The relationship analysis unit is used to establish the relationship between components.

[0146] First, the conduction relationship between the components in the structure diagram is analyzed, and the components that have a conduction relationship with the abnormal object DX1 are selected as the conduction objects of DX1.

[0147] Secondly, the abnormal object is associated with each of its conductive objects respectively, and the sampling time of each sampling point under each pair of associated objects and the fault time period of each combination area are obtained.

[0148] Finally, the impact duration s is set, and the two sampling points in each pair of associated objects whose sampling time difference is less than s and do not belong to the same object are associated, and the two combined areas whose fault time period difference is less than s and do not belong to the same object are associated.

[0149] The hidden danger identification unit is used to identify abnormal parts and safety hazard areas.

[0150] First, divide the interval time difference of each pair of associated sampling points by the sampling time difference to obtain the sampling coefficient, and divide the standard deviation difference of each pair of associated combination areas by the fault time difference to obtain the gap coefficient. Substitute the sampling coefficient and gap coefficient into the formula In the above example, the second coefficient XS of each pair of associated objects is calculated separately. two .

[0151] Where v is the logarithm of the associated sampling points, JS c is the sampling coefficient of the cth pair of associated sampling points, JS ave is the average sampling coefficient of all associated sampling points, f is the logarithm of the associated combination area, CJ g is the gap coefficient of the g-th pair of associated combination areas, CJ aveis the average value of the gap coefficients of all associated combination areas.

[0152] Then set the index threshold ZS thr , and obtain the second coefficient of each pair of associated objects and the first coefficient of each object in it, according to the formula Compute the third index of each pair of associated objects.

[0153] Mark the third index greater than ZS thr The associated objects are marked, the two parts corresponding to the associated objects are marked as abnormal parts, and the connection between the abnormal parts is regarded as a safety hazard area.

[0154] Where β is a constant, is the first coefficient of one of the objects in the associated object, The first coefficient of another object in the associated object.

[0155] The visualization module displays various safety hazard areas through the visualization screen on the mechanical equipment, and updates the safety hazard areas in real time according to the changes in vibration amplitude. It draws a vibration change graph in real time and records the failure time of each component each time. It generates fault records and operation records and stores them in the history log.

[0156] Embodiment 1:

[0157] Assuming that the component BN a There are three combined areas in the sampling set. The standard deviations of the intervals of all sampling points in these three combined areas are 1.2, 1.5 and 2 respectively. By analyzing the BN of the parts a The vibration change diagram in the operation record shows that the average vibration amplitude is 0.2mm, and the average vibration amplitude in the last combined zone failure time period is 0.4mm. When the constant α is 1.2 and the gap threshold is 1.2, substitute the formula to calculate the BN of the component a The first coefficient of:

[0158]

[0159] Then the component BN a The first coefficient is 4.25.

[0160] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0161] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A mechanical equipment operation data management method based on big data, characterized in that: The method comprises the following steps: S100, collecting historical logs and structural diagrams of mechanical equipment, and collecting vibration amplitude information of various components of the mechanical equipment in real time during operation through sensors and monitoring software; S200, establishing sampling points by analyzing the fault records in the historical log, sorting the sampling points and dividing them into different combination areas, calculating the first coefficient according to the standard deviation of the interval time of the sampling points in different combination areas and defining the abnormal object; S300, analyzing the conduction relationship between components according to the structure diagram and defining the conduction object, associating the abnormal object with the conduction object, calculating the second coefficient and the third index, and identifying the abnormal components and the potential safety hazard area through the third index; S400, display the potential safety hazard areas in the mechanical equipment through a visual screen, update the potential safety hazard areas in real time according to the vibration amplitude information, record the information of each component in the mechanical equipment and store it in a historical log.

2. The method for managing mechanical equipment operation data based on big data according to claim 1, characterized in that: In S100, the history log includes the fault record and operation record of each component of the mechanical equipment; each fault record includes the component code and the fault time, and each operation record includes the component code and the vibration change diagram. The vibration change diagram represents the change in vibration amplitude of the component during each operation time. The vibration information is collected in real time by the sensor and handed over to the monitoring software to be drawn as a vibration change diagram; the structure diagram represents the various components in the mechanical equipment and the conduction relationship between them. Conduction refers to the transmission of force between the components inside the mechanical equipment through contact and connection.

3. The method for managing mechanical equipment operation data based on big data according to claim 2, characterized in that: In S200, the specific steps are as follows: S201, obtain all fault records of component BN1 in the history log and count the total number h, sort the h fault records in order from earliest to latest according to the fault time; establish a sampling point for every two adjacent fault records according to the arrangement order, calculate the difference dt and the average te of the fault time in the two adjacent fault records respectively, and use dt and te as the interval duration and sampling time of the corresponding sampling point respectively; establish L-1 sampling points according to the number L of fault records of each component, and calculate the interval duration and sampling time of each sampling point; S202: Create a sampling set for each component, count the number of sampling points e for the same component, and put them into the corresponding sampling set in order from early to late in sampling time to obtain {n1, n2, n3, ..., n e }; Set the gap threshold Q thr , calculate the standard deviation of the interval between sampling points n1 and n2 and determine whether it is less than Q thr ; if it is less than, create a combined area and add n1 and n2, and calculate n1, n2 and n again e If it is not less than Q, calculate the standard deviation of the interval between sampling points n2 and n3 and judge it; and so on, according to the judgment of the standard deviation, put two or more adjacent sampling points into the same combination area, the sampling points in different combination areas are different, and the standard deviation of the interval between all sampling points in each combination area is less than Q thr ; S203, analyzing the earliest fault time T in the fault records corresponding to all sampling points in the combined area early and the latest failure time T late ; T early to T late As the fault time period of the corresponding combination area; obtain the sampling set of component BN2, and select the last combination area Z according to the arrangement order of the sampling points in the sampling set last , analyze the vibration change diagram in the operation record of component BN2 and calculate the average vibration amplitude zfd ave and Z last The average amplitude of vibration during the fault period fd ave ; Substitute into the formula to calculate the first coefficient XS for each component one , set the coefficient threshold XS thr , the first coefficient greater than XS thr The parts are taken as abnormal objects; the first coefficient calculation formula is as follows: In the formula, α is a constant, k is the number of combination zones in the sampling set, and BZ i is the standard deviation of the interval time of all sampling points in the i-th combined area.

4. The method for managing mechanical equipment operation data based on big data according to claim 3 is characterized in that: In S300, the specific steps are as follows: S301, analyzing the conduction relationship between the components in the structure diagram, selecting the components that have a conduction relationship with the abnormal object DX1 as the conduction object of DX1; associating the abnormal object with each of its conduction objects respectively, obtaining the sampling time of each sampling point under each pair of associated objects and the fault time period of each combination area; setting the impact time s, associating the two sampling points in each pair of associated objects whose sampling time difference is less than s and do not belong to the same object, and associating the two combination areas whose fault time difference is less than s and do not belong to the same object; S302: Divide the interval time difference of each pair of associated sampling points by the sampling time difference to obtain a sampling coefficient, and divide the standard deviation difference of each pair of associated combination areas by the fault time difference to obtain a gap coefficient. Substitute the sampling coefficient and the gap coefficient into the formula to calculate the second coefficient XS of each pair of associated objects. two , the formula is as follows: Where v is the logarithm of the associated sampling points, JS c is the sampling coefficient of the cth pair of associated sampling points, JS ave is the average sampling coefficient of all associated sampling points, f is the logarithm of the associated combination area, CJ g is the gap coefficient of the g-th pair of associated combination areas, CJ ave is the average value of the gap coefficients of all associated combination areas; S303, obtaining the second coefficient of each pair of associated objects and the first coefficient of each object therein, and substituting them into a formula to calculate the third index of each pair of associated objects; Set the index threshold ZS thr , marking the third index greater than ZS thr The associated object of the mark is used, and the two parts corresponding to the associated object are regarded as abnormal parts, and the connection between the abnormal parts is regarded as the safety hazard area; wherein, the calculation formula of the third index is as follows: In the formula, ZS is the third index, β is a constant, is the first coefficient of one of the objects in the associated object, The first coefficient of another object in the associated object.

5. The method for managing mechanical equipment operation data based on big data according to claim 4 is characterized in that: In S400, each safety hazard area is displayed in real time through the visual screen on the mechanical equipment, and the vibration change diagram of the corresponding components in the safety hazard area is displayed; the safety hazard area is updated in real time according to the change of vibration amplitude, and the vibration change diagram is drawn in real time through the amplitude change of each component of the mechanical equipment and the failure time of each component is recorded. After the fault record and operation record are generated, they are stored in the history log.

6. A mechanical equipment operation data management system based on big data, characterized by: The system includes a data acquisition module, an abnormality analysis module, an operation management module and a visualization module; The data acquisition module is used to collect historical logs and structural diagrams of mechanical equipment, as well as the vibration amplitude of each component during the operation of the mechanical equipment; The abnormal analysis module is used to analyze the fault records in the historical log and establish sampling points, sort the sampling points and divide them into different combination areas, calculate the first coefficient according to the standard deviation of the interval time of the sampling points in different combination areas, and define the abnormal object; The operation management module analyzes the conduction relationship between components according to the structure diagram and defines the conduction object, associates the abnormal object with the conduction object, calculates the second coefficient and the third index, and identifies the abnormal components and safety hazard areas through the third index; The visualization module is used to display the potential safety hazards in mechanical equipment, record the information of each component and store it in the historical log.

7. The mechanical equipment operation data management system based on big data according to claim 6 is characterized by: The data collection module includes a history log collection unit, a structure information collection unit and an operation status collection unit; The historical log collection unit is used to collect the fault records and operation records of each component of the mechanical equipment; Each fault record includes the component code and fault time, and each operation record includes the component code and vibration change diagram. The vibration change diagram shows the change in vibration amplitude of the component during each operation time. The structural information acquisition unit is used to acquire the structural diagram of the mechanical equipment; The structural diagram shows the various components in the mechanical equipment and the conduction relationship between them. Conduction refers to the transmission of forces between the components inside the mechanical equipment through contact and connection; The operation status acquisition unit is used to collect the vibration amplitude of each component during the operation of the mechanical equipment.

8. The mechanical equipment operation data management system based on big data according to claim 7 is characterized in that: The abnormality analysis module includes a region division unit and an abnormality analysis unit; The regional division unit is used to establish sampling points and divide them into different combination areas; First, retrieve all fault records under the same component in the historical log, and sort these fault records in order of fault time; establish a sampling point for every two adjacent fault records, calculate the difference dt and average te of the fault time in the two adjacent fault records as the interval length and sampling time of the corresponding sampling point respectively; Then, a sampling set is established for each component, and the number of sampling points under the component is counted, and they are put into the corresponding sampling set in order from early to late according to the sampling time, and {n1, n2, n3, ..., n e }; Set the gap threshold Q thr , calculate the standard deviation of the interval between sampling points n1 and n2 and determine whether it is less than Q thr ; if it is less than, create a combined area and add n1 and n2, and calculate n1, n2 and n again e If it is not less than Q, calculate the standard deviation of the interval between sampling points n2 and n3 and judge it; and so on, according to the judgment of the standard deviation, put two or more adjacent sampling points into the same combination area, the sampling points in different combination areas are different, and the standard deviation of the interval between all sampling points in each combination area is less than Q thr ; The abnormality analysis unit is used to calculate the first coefficient of each component and define abnormal objects; First, analyze the earliest fault time T in the fault records corresponding to all sampling points in the combined area Early and the latest failure time T late ; T early to T late As the fault time period of the corresponding combination area; Secondly, obtain the sampling set of parts and select the last combination area Z according to the order of sampling points in the sampling set. last , analyze the vibration change diagram in the component operation record and calculate the average vibration amplitude zfd ave and Z last The average amplitude of vibration during the fault period fd ave ; Finally, according to the formula Calculate the first coefficient XS for each component one , set the coefficient threshold XS thr , the first coefficient greater than XS thr The parts are taken as abnormal objects; where α is a constant, k is the number of combination zones in the sampling set, BZ i is the standard deviation of the interval time of all sampling points in the i-th combined area.

9. The mechanical equipment operation data management system based on big data according to claim 8 is characterized in that: The operation management module includes a relationship analysis unit and a hidden danger identification unit; The relationship analysis unit is used to establish the relationship between parts; First, the conduction relationship between the components in the structure diagram is analyzed, and the components that have a conduction relationship with the abnormal object DX1 are selected as the conduction objects of DX1; Secondly, associate the abnormal object with each of its conductive objects, and obtain the sampling time of each sampling point under each pair of associated objects and the fault time period of each combination area; Finally, the impact duration s is set, and the two sampling points in each pair of associated objects whose sampling time difference is less than s and do not belong to the same object are associated, and the two combined areas whose fault time period difference is less than s and do not belong to the same object are associated; The hidden danger identification unit is used to identify abnormal parts and safety hazard areas; First, divide the interval time difference of each pair of associated sampling points by the sampling time difference to obtain the sampling coefficient, and divide the standard deviation difference of each pair of associated combination areas by the fault time difference to obtain the gap coefficient. Substitute the sampling coefficient and gap coefficient into the formula In the above example, the second coefficient XS of each pair of associated objects is calculated separately. two ; where v is the logarithm of the associated sampling points, JS c is the sampling coefficient of the cth pair of associated sampling points, JS ave is the average sampling coefficient of all associated sampling points, f is the logarithm of the associated combination area, CJ g is the gap coefficient of the g-th pair of associated combination areas, CJ ave is the average value of the gap coefficients of all associated combination areas; Then set the index threshold ZS thr , and obtain the second coefficient of each pair of associated objects and the first coefficient of each object in it, according to the formula Calculate the third index of each pair of associated objects; mark the third index greater than ZS thr The associated object of the mark is used to mark the two parts corresponding to the associated object as abnormal parts, and the connection between the abnormal parts is used as the safety hazard area; where β is a constant, is the first coefficient of one of the objects in the associated object, The first coefficient of another object in the associated object.

10. The mechanical equipment operation data management system based on big data according to claim 9 is characterized in that: The visualization module displays various safety hazard areas through the visualization screen on the mechanical equipment, and updates the safety hazard areas in real time according to the changes in vibration amplitude. It draws a vibration change graph in real time and records the failure time of each component each time. It generates fault records and operation records and stores them in the history log.

Images