Collection tank operation data abnormity early warning method

Abstract

The invention provides a collection tank operation data abnormity early warning method, which comprises the steps of determining a liquid level change trend according to liquid level change quantities of a to-be-detected collection tank in a first time period, a second time period and a target time period; if the liquid level change trend tends to be stable, the operation data in the first time period, the second time period, the target time period and the historical time period are compared to determine the operation safety state in the third time period; if the liquid level change trend is that the liquid level change exists, the operation safety state in the third time period is determined according to the motion states of the multiple pieces of operation data in the first time period, the second time period and the target time period in the operation data track diagram; and if the operation safety state in the third time period is an abnormal state, an emergency braking instruction is sent to a control module of the to-be-detected collection tank, so that the monitoring computing power of the operation data of the to-be-detected collection tank is reduced, and the purpose of abnormal early warning is achieved.

Description

Background Art

[0002] The collection tank is used to carry liquid media. Since different media have different storage or transportation conditions, the operating data of the collection tank's operation safety monitoring when carrying different media will also be different, and the monitoring thresholds of the set operation data will also be different. Therefore, when the collection tank stores or transports the medium, it is necessary to monitor the operation safety of the collection tank in real time. When the operating data of the collection tank is in an abnormal state, an abnormal alarm will be sent to the control center in time.

[0003] The current safe operation monitoring of the collecting tank is achieved by real-time monitoring of all operating data of the collecting tank (such as pressure values, temperature values, etc.), but this monitoring method will result in too much processing of the monitored operating data, and cannot adaptively adjust the monitoring thresholds of the operating data for different media. Therefore, it will cause errors in the safe operation monitoring results of the collecting tank. Moreover, since this method of monitoring the safe operation of the collecting tank is real-time monitoring, it will only issue an abnormal alarm when an abnormality is detected in the operating data at the current moment. However, since an abnormal failure has occurred in the collecting tank when the abnormal alarm is issued, even if the staff promptly closes the collecting tank or takes other emergency measures, it may cause economic losses to the collecting tank. Therefore, the current method of monitoring the safe operation of the collecting tank cannot issue abnormal warnings for the collecting tank, and the data processing volume is large, which will occupy a large computing power of the monitoring system, and there are still certain errors in the monitoring results. Summary of the invention

[0004] In view of the above technical problems, the technical solution adopted by the present invention is: According to one aspect of the present application, a method for early warning of abnormal operation data of a collection tank is provided, which is applied to an early warning system for abnormal operation data of a collection tank, wherein the early warning system for abnormal operation data of a collection tank is connected to a collection tank to be detected; The abnormal early warning method for the collection tank operation data includes the following steps: Step S100, determining a liquid level change trend of the collection tank to be detected according to the liquid level change of the collection tank to be detected in the first time period, the liquid level change of the collection tank to be detected in the second time period, and the liquid level change of the collection tank to be detected in the target time period; The first time period, the second time period and the target time period have the same length, and the end time of the first time period is the start time of the second time period, the end time of the second time period is the start time of the target time period, and the end time of the target time period is the current time; Step S200: If the liquid level change trend of the collection tank to be detected is stable, execute step S300; otherwise, execute step S400; Step S300, by comparing a number of operating data of the collection tank to be detected in the first time period, a number of operating data in the second time period, a number of operating data in the target time period, and a number of operating data in the historical time period, to determine the operating safety state of the collection tank to be detected in the third time period, and executing step S500; The end time of the historical time period is the start time of the first time period; the length of the third time period is the same as the length of the target time period, and the start time of the third time period is the end time of the target time period; Step S400, determining the operating safety state of the collection tank to be detected in the third time period according to the motion state in the operating data trajectory diagram corresponding to the collection tank to be detected in the first time period, the second time period and the target time period, and executing step S500; The operation data trajectory diagram is obtained by training a number of operation data of the collection tank to be detected in the historical time period; Step S500: If the operating safety state of the collection tank to be detected is an abnormal state within the third time period, an emergency braking instruction is sent to the control module of the collection tank to be detected.

[0005] According to one aspect of the present application, a non-transitory computer-readable storage medium is provided, in which at least one instruction or at least one program is stored. The at least one instruction or the at least one program is loaded and executed by a processor to implement the aforementioned collection tank operation data abnormality warning method.

[0006] According to one aspect of the present application, an electronic device is provided, including a processor and the aforementioned non-transitory computer-readable storage medium.

[0007] The present invention has at least the following beneficial effects: The method for warning abnormal operation data of a collecting tank of the present invention first determines the liquid level change trend corresponding to the collecting tank to be detected according to the liquid level change amount of the collecting tank to be detected in the first time period, the liquid level change amount of the collecting tank to be detected in the second time period, and the liquid level change amount of the collecting tank to be detected in the target time period. If the liquid level change trend corresponding to the collecting tank to be detected is stable, a plurality of operation data of the collecting tank to be detected in the first time period, a plurality of operation data in the second time period, a plurality of operation data in the target time period, and a plurality of operation data in the historical time period are compared to determine the operation safety state of the collecting tank to be detected in the third time period. Conversely, if the liquid level change trend is that there is a liquid level change, the operation safety state of the collecting tank to be detected in the third time period is determined according to the movement state of the plurality of operation data of the collecting tank to be detected in the first time period, the second time period and the target time period in the operation data trajectory diagram corresponding to the collecting tank to be detected. Finally, if the operation safety state of the collecting tank to be detected in the third time period is an abnormal state, an emergency braking command is sent to the control module of the collecting tank to be detected. By judging the amount of change in the liquid level of the collection tank to be detected, the liquid level change trend of the collection tank to be detected is determined, as well as a method for determining the operation data of the collection tank to be detected. Then, the operation data in the first time period, the second time period, and the target time period are processed by different judgment methods to reduce the monitoring computing power of the operation data of the collection tank to be detected. By judging the operation data in the first time period, the second time period, and the target time period, the operation safety status of the collection tank to be detected in the third time period is predicted to achieve the purpose of abnormal warning. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0009] Figure 1 A flowchart of a method for early warning of abnormal operation data of a collection tank provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0010] 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 those skilled in the art without creative work are within the scope of protection of the present invention.

[0011] The present application proposes a method for warning of abnormal operation data of a collecting tank, which is applied to a warning system for abnormal operation data of a collecting tank. The warning system for abnormal operation data of a collecting tank is connected to a collecting tank to be detected, and the warning system for abnormal operation data of a collecting tank is used to perform abnormal detection on the collecting tank to be detected. A plurality of detection mechanisms (such as temperature sensors, pressure sensors, ultrasonic sensors, etc.) are arranged in the collecting tank to be detected, and each detection mechanism corresponds to a detection type (such as for temperature detection, for pressure detection, for collection tank wall thickness detection, etc.), and the detection mechanism is used to perform data detection on the collection tank to be detected (such as a temperature sensor performs temperature detection on a medium in the collection tank to be detected, an ultrasonic sensor performs wall thickness detection on the collection tank to be detected, etc.).

[0012] Among them, Figure 1 As shown, the abnormal early warning method for the collection tank operation data proposed in this application includes the following steps: Step S100, determining a liquid level change trend of the collection tank to be detected according to the liquid level change of the collection tank to be detected in the first time period, the liquid level change of the collection tank to be detected in the second time period, and the liquid level change of the collection tank to be detected in the target time period; The first time period, the second time period, and the target time period have the same length, and the end time of the first time period is the start time of the second time period, the end time of the second time period is the start time of the target time period, and the end time of the target time period is the current time.

[0013] The specific abnormality detection method of the collection tank to be detected is determined by determining the liquid level change trend of the medium carried by the collection tank to be detected during the time period between the start time of the first time period and the current time (ie, step S300 and step S400).

[0014] Further, step S100 includes steps S110 to S170: Step S110: Obtain the liquid level value corresponding to each detection time of the collection tank to be detected in the first time period to obtain a first liquid level value list A1=(A 11 ,A 21 ,...,A i1 ,...,A n1 ), where i=1,2,...,n, and n is the number of detection moments in the first time period; A i1 is the liquid level value corresponding to the i-th detection moment of the collection tank to be detected in the first time period; the time period between every two adjacent detection moments is the same; Step S120: According to the first liquid level value list A1, determine the liquid level change B1 of the collection tank to be detected in the first time period = (∑ n i=1 A i1) / n; Step S130: Obtain the liquid level value corresponding to each detection time of the collection tank to be detected in the second time period to obtain a second liquid level value list A2=(A 12 ,A 22 ,...,A i2 ,...,A n2 ), where A i2 is the liquid level value corresponding to the i-th detection moment of the collection tank to be detected in the second time period; the length of the time period between each adjacent detection moment in the second time period is the same as the length of the time period between each adjacent detection moment in the first time period; Step S140: According to the second liquid level value list A2, determine the liquid level change B2 of the collection tank to be detected in the second time period = (∑ n i=1 A i2 ) / n; Step S150: Obtain the liquid level value corresponding to each detection time of the collection tank to be detected within the target time period to obtain a target liquid level value list A3=(A 13 ,A 23 ,...,A i3 ,...,A n3 ), where A i3 is the liquid level value corresponding to the i-th detection moment of the collection tank to be detected within the target time period; the time period length between each adjacent detection moment within the target time period is the same as the time period length between each adjacent detection moment within the first time period; Step S160: According to the target liquid level value list A3, determine the liquid level change B3 of the collection tank to be detected within the target time period = (∑ n i=1 A i3 ) / n; Step S170, if |B1-B2|≤B0, and |B2-B3|≤B0, it is determined that the liquid level change trend corresponding to the collection tank to be detected is tending to be stable; otherwise, it is determined that the liquid level change trend corresponding to the collection tank to be detected is that there is a liquid level change; wherein B0 is a preset liquid level change difference threshold.

[0015] If the corresponding liquid level change trend of the collection tank to be detected from the first time period to the target time period is tending to be stable, it means that the liquid level of the medium in the collection tank to be detected has not changed significantly from the first time period to the target time period, which can be explained that the collection tank to be detected is in a medium storage state from the first time period to the target time period; conversely, if the corresponding liquid level change trend of the collection tank to be detected from the first time period to the target time period is that there is a liquid level change, it means that the liquid level of the medium in the collection tank to be detected has changed significantly from the first time period to the target time period, which can be explained that the collection tank to be detected is in a medium transfer state from the first time period to the target time period.

[0016] Step S200: If the liquid level change trend of the collection tank to be detected is stable, execute step S300; otherwise, execute step S400; If the liquid level change trend corresponding to the collection tank to be detected tends to be stable, it means that the state of the medium carried in the collection tank to be detected is relatively stable, and the possibility of abnormal failure is small. Therefore, the abnormal detection method of data vector comparison described in step S300 is adopted. This method only needs to perform vector comparison on several operating data in each time period and the historical operating data. Compared with the method of real-time comparison of operating data in the prior art, the amount of data processing is reduced.

[0017] If the liquid level change trend corresponding to the collection tank to be detected shows that there is a liquid level change, it means that the state of the medium carried in the collection tank to be detected fluctuates relatively greatly, and the possibility of abnormal failure is relatively high. Therefore, the method of performing abnormality detection by checking the trend of the trajectory points in the operation data trajectory diagram described in step S400 is adopted to improve the accuracy of abnormal detection and early warning of the collection tank to be detected, and the horizontal and vertical coordinates of the trajectory points in the operation data trajectory diagram use the principal component analysis method to determine the operation data for abnormal detection, which further reduces the data processing volume compared with the method of detecting all operation data in the prior art.

[0018] Step S300, by comparing a number of operating data of the collection tank to be detected in the first time period, a number of operating data in the second time period, a number of operating data in the target time period, and a number of operating data in the historical time period, to determine the operating safety state of the collection tank to be detected in the third time period, and executing step S500; The end time of the historical time period is the start time of the first time period; the length of the third time period is the same as the length of the target time period, and the start time of the third time period is the end time of the target time period, that is, the third time period is a future period.

[0019] Further, step S300 includes steps S310 to S360: Step S310: Obtain the mean value of each operation data of the collection tank to be detected in the first time period to obtain a first operation data vector C1=(C 11 ,C 21 ,...,C j1 ,...,C k1 ), where j=1,2,...,k; k is the number of running data of the collection tank to be tested; C j1 is the mean value of the j-th operating data of the collection tank to be tested in the first time period; Step S320: Obtain the mean value of each operation data of the collection tank to be detected in the second time period to obtain a second operation data vector C2=(C 12 ,C 22 ,...,C j2 ,...,C k2 ), where C j2 is the mean value of the j-th operating data of the collection tank to be tested in the second time period; Step S330: Obtain the mean value of each operation data of the collection tank to be detected within the target time period to obtain the target operation data vector C3=(C 13 ,C 23 ,...,C j3 ,...,C k3 ), where C j3 is the mean value of the j-th operating data of the collection tank to be tested within the target time period; Step S340: Obtain each historical operation data vector corresponding to the collection tank to be detected to obtain a historical operation data vector list D=(D1, D2, ..., D h ,...,D m ), where h = 1, 2, ..., m; m is the number of historical sub-time periods within the historical time period; D h is the historical operation data vector corresponding to the hth historical sub-time period of the collection tank to be detected within the historical time period; D h =(D 1h ,D 2h ,...,D jh ,...,D kh );D jh is the mean value of the j-th operating data of the collection tank to be tested in the h-th historical sub-time period; The length of each historical sub-time period is equal to the length of the target time period, and the start time of the hth historical sub-time period is the end time of the h-1th historical sub-time period, the end time of the hth historical sub-time period is the start time of the h+1th historical sub-time period; the end time of the mth historical sub-time period is the start time of the first time period.

[0020] Step S350: determining a plurality of target historical operation data vectors from a plurality of historical operation data vectors according to the medium carried by the collection tank to be detected at the current moment; Since the media carried in the collection tank to be detected are different, the detection thresholds of the operation data of the collection tank to be detected will be different (for example, the detection temperature threshold when the medium is water is different from the detection temperature threshold when the medium is oil). Therefore, in order to improve the accuracy of anomaly detection, it is necessary to filter out the target historical operation data vector corresponding to the medium carried by the collection tank to be detected at the current moment from the historical operation data vector, and then perform vector comparison. This targeted operation data comparison can improve the accuracy of anomaly detection of the collection tank to be detected.

[0021] Further, step S350 includes steps S351 to S355: Step S351, obtaining the medium identifier E0 corresponding to the medium carried in the collection tank to be detected at the current moment; Step S352: Obtain the medium identification corresponding to each historical operation data vector in the historical operation data vector list D to obtain a medium identification list E=(E1, E2, ..., E h ,...,E m ), where E h is the medium identifier corresponding to the medium carried by the collection tank to be detected at the end time of the hth historical sub-time period; Step S353, traverse each medium identification in the medium identification list E in turn, if E h =E0, then D h Determine the intermediate historical operation data vector to obtain the intermediate historical operation data vector list F=(F1, F2, ..., F a ,...,F b ), where a=1,2,...,b, b is the number of intermediate historical operation data vectors determined; F a is the determined a-th intermediate historical running data vector; Step S354: If F c-2 The corresponding historical sub-time period, F c-1 The corresponding historical sub-time period, F c The corresponding historical sub-time period, F c+1 If the corresponding historical sub-time periods are consecutive and adjacent historical sub-time periods within the historical time period, then F c Determine the target historical operation data vector; where c=3,...,b-1; The continuous intermediate historical operation data vectors of the historical sub-time periods are determined as the target historical operation data vectors, so that the time period corresponding to the determined target historical operation data vectors and the time period corresponding to the target operation data vectors are both continuous and adjacent time periods, so as to further improve the matching accuracy of the vector comparison.

[0022] Step S355: If the number of target historical operation data vectors in the intermediate historical operation data vector list F is less than a preset target vector number threshold, execute step S400.

[0023] If in the intermediate historical operation data vector list F, the number of target historical operation data vectors is less than the target vector number threshold, it means that the number of determined target historical operation data vectors is small. If these target historical operation data vectors are used for vector comparison, the comparison results will be too rough due to the small number of comparison groups. Therefore, accurate detection is performed using the detection method described in step S400.

[0024] Step S360: Compare the first operation data vector C1, the second operation data vector C2, the target operation data vector C3 and the target historical operation data vector to determine the operation safety status of the collection tank to be detected within the third time period.

[0025] Further, step S360 includes steps S361 to S364: Step S361: Obtain each target historical operation data vector to obtain a target historical operation data vector list G=(G1, G2, ..., G d ,...,G e ), where d = 1, 2, ..., e, and e is the number of the determined target historical operation data vectors; G d The historical operation data vector of the determined dth target; Step S362: traverse each target historical operation data vector in the target historical operation data vector list G, and if it is in the intermediate historical operation data vector list F, it is located in G d The matching degree between the second intermediate historical operation data vector and the first operation data vector C1 is greater than the preset matching degree threshold and is located at G d The matching degree between the first intermediate historical operation data vector and the second operation data vector C2 is greater than the preset matching degree threshold, and G d If the matching degree with the target operation data vector C3 is greater than the preset matching degree threshold, the target operation data vector C3 will be placed in the intermediate historical operation data vector list F at G d The first intermediate historical operation data vector thereafter is determined as the key historical operation data vector; Step S363, obtaining the operation safety status identifier corresponding to each key historical operation data vector; The operation safety status identifier represents the operation safety status of the collection tank to be detected in the historical sub-time period corresponding to the key historical operation data vector corresponding to the operation safety status identifier.

[0026] For example, when the operation safety status identifier is 1, it means that the operation safety status of the collection tank to be tested in the historical sub-time period corresponding to the key historical operation data vector corresponding to the operation safety status identifier is a safe state; when the operation safety status identifier is 0, it means that the operation safety status of the collection tank to be tested in the historical sub-time period corresponding to the key historical operation data vector corresponding to the operation safety status identifier is an abnormal state.

[0027] Step S364: If, among all the operation safety status identifications, the ratio of the number of operation safety status identifications indicating that the operation safety status is an abnormal state to the total number of operation safety status identifications is greater than a preset abnormal ratio threshold, it is determined that the operation safety status of the collection tank to be detected in the third time period is an abnormal state.

[0028] Step S400, determining the operating safety state of the collection tank to be detected in the third time period according to the motion state in the operating data trajectory diagram corresponding to the collection tank to be detected in the first time period, the second time period and the target time period, and executing step S500; The operation data trajectory diagram is obtained by training a number of operation data of the collection tank to be detected in the historical time period. Specifically, the operation data trajectory diagram is obtained through steps S401 and S402: Step S401, determining first target operating data and second target operating data corresponding to the collection tank to be detected according to each operating data of the collection tank to be detected; Further, step S401 includes steps S4011 to S4016: Step S4011, obtain the operation data identifier corresponding to each operation data of the collection tank to be detected, so as to obtain an operation data identifier list H=(H1, H2, ..., H j ,...,H k ), where H j is the operating data identifier corresponding to the j-th operating data of the collection tank to be detected; Step S4012: H1, H2, ..., H j ,...,H k Conduct principal component analysis to obtain several operational data groups; Several corresponding operation data in the same operation data group are correlated with each other.

[0029] The principal component analysis algorithm is used to reduce the detection dimension of the operating data. All the operating data are processed through principal component analysis to obtain several operating data groups to represent the influence of different operating data groups on the abnormal detection results of the collection tank to be detected. The principal component analysis algorithm (PCA) is an existing data processing algorithm, so it will not be described here.

[0030] Step S4013, obtaining the impact values ​​of the detection items corresponding to the corresponding operating data in each operating data group on the safe operation result of the collection tank to be detected, so as to obtain the operating data impact value corresponding to each operating data group, and determine the operating data impact value list I=(I1, I2, ..., I p ,...,I q ), where p = 1, 2, ..., q, q is the number of running data sets, I p is the operating data impact value corresponding to the pth operating data group; I p The sum of the impact values ​​of the detection items corresponding to the several operation data in the pth operation data group on the safe operation result of the collection tank to be detected; The impact value of the detection items corresponding to the operating data (i.e., the detection categories, such as the operating data of the pressure detection value is a group, the operating data of the temperature detection value is a group, etc.) on the safe operation result of the collection tank to be detected is the value preset by the staff, and can be obtained by the staff through statistics of the historical detection results.

[0031] Step S4014, determining the operation data group corresponding to MAX(I) as the first operation data group, and the operation data in the first operation data group as the first initial operation data; wherein MAX() is a preset maximum value determination function; The first operating data group is represented by the operating data included therein having the greatest influence on the safe operating result of the collecting tank to be inspected among all the operating data.

[0032] Step S4015: determining the operation data group corresponding to only the operation data influence values ​​less than MAX(I) in the operation data influence value list I as the second operation data group, and determining some operation data in the second operation data group as the second initial operation data; Step S4016: perform data integration processing on the plurality of first initial operation data and the plurality of second initial operation data respectively to obtain first target operation data and second target operation data.

[0033] The method of performing data integration processing on the plurality of first initial operation data and the plurality of second initial operation data respectively may be average value processing, logarithmic processing, or other data integration methods.

[0034] Step S402: input the first target operation data and the second target operation data into a preset data detection model to obtain an operation data trajectory diagram output by the data detection model; The data detection model is trained based on a number of operating data of the collection tank to be detected within a historical time period.

[0035] Among them, the horizontal coordinate of the trajectory point of the operation data trajectory diagram represents the first target operation data corresponding to the collection tank to be detected; the vertical coordinate of the trajectory point of the operation data trajectory diagram represents the second target operation data corresponding to the collection tank to be detected.

[0036] By performing principal component analysis on all operating data, we can obtain the first target operating data that has the greatest impact on the abnormal detection result and the second target operating data that has the second highest impact on the abnormal detection result after the first target operating data. Only these two groups of operating data are monitored for abnormalities, so as to reduce the monitoring processing volume of operating data while ensuring the accuracy of abnormality detection.

[0037] Further, step S402 includes steps S4021 to S4027: Step S4021, obtaining a parameter value of each operating data corresponding to the first operating data group in each historical sub-time period and a parameter value of each operating data corresponding to the second operating data group in each historical sub-time period; Step S4022: Determine the sum of the parameter values ​​of a plurality of operation data corresponding to the first operation data group in the same historical sub-time period as the first historical operation data parameter value; Step S4023: Determine the sum of the parameter values ​​of a plurality of operation data corresponding to the second operation data group in the same historical sub-time period as the second historical operation data parameter value; Step S4024, obtaining the operating safety status identifier of the collection tank to be detected in each historical sub-time period; Step S4025: input the first historical operation data parameter value, the second historical operation data parameter value, and the operation safety status identifier corresponding to each historical sub-time period into a preset data detection model for training, so as to obtain an operation data trajectory diagram; the abscissa of each trajectory point in the operation data trajectory diagram is the first historical operation data parameter value, and the ordinate of each trajectory point in the operation data trajectory diagram is the second historical operation data parameter value; The data detection model can adopt the existing mathematical model, and the training method can also be the existing data model training method.

[0038] Step S4026, in the initial data trajectory diagram, a trajectory point whose operation safety status indicator indicates that the operation safety status of the collection tank to be detected is a normal state is determined as an operation safety trajectory point; Step S4027: determine the area enclosed by a number of operation safety trajectory points as the operation safety area.

[0039] Further, step S400 includes steps S410 to S470: Step S410: determining the sum of the parameter values ​​of the plurality of operating data corresponding to the first operating data group within the first time period as the first target operating data parameter value, and determining the sum of the parameter values ​​of the plurality of operating data corresponding to the second operating data group as the second target operating data parameter value; Step S420: determining the sum of the parameter values ​​of the plurality of operating data corresponding to the first operating data group within the second time period as the third target operating data parameter value, and determining the sum of the parameter values ​​of the plurality of operating data corresponding to the second operating data group as the fourth target operating data parameter value; Step S430: determining the sum of the parameter values ​​of the plurality of operation data corresponding to the first operation data group within the target time period as the fifth target operation data parameter value, and determining the sum of the parameter values ​​of the plurality of operation data corresponding to the second operation data group as the sixth target operation data parameter value; Step S440, inputting the first target operating data parameter value and the second target operating data parameter value into the data detection model to obtain a first trajectory point of the collection tank to be detected in the operating data trajectory diagram within the first time period; Step S450, inputting the third target operating data parameter value and the fourth target operating data parameter value into the data detection model to obtain a second trajectory point of the collection tank to be detected in the operating data trajectory diagram within the second time period; Step S460: input the fifth target operating data parameter value and the sixth target operating data parameter value into the data detection model to obtain a third trajectory point of the collection tank to be detected in the operating data trajectory diagram within the target time period; Step S470: If the first trajectory point, the second trajectory point, and the third trajectory point are all within the operation safety area, and the length between the third trajectory point and the nearest boundary point of the operation safety area is greater than a preset safety distance threshold, then it is determined that the operation safety status of the collection tank to be detected during the third time period is a normal state; otherwise, it is determined that the operation safety status of the collection tank to be detected during the third time period is an abnormal state.

[0040] If the first trajectory point, the second trajectory point, and the third trajectory point are all within the operational safety area, and the length between the third trajectory point and the nearest boundary point of the operational safety area is greater than the preset safety distance threshold, it means that the collection tank to be detected is in a safe state within the target time period and has no tendency to extend outside the operational safety area. It can be determined that the operational safety state of the collection tank to be detected in the third time period in the future time period is also normal.

[0041] On the contrary, if the length between the third trajectory point and the nearest boundary point of the operating safety area is less than or equal to the preset safety distance threshold, it means that although the collection tank to be inspected is in a safe state during the target time period, it has a tendency to extend outside the operating safety area. In order to ensure the operational safety of the collection tank to be inspected, the operational safety state of the collection tank to be inspected during the third time period is determined as an abnormal state to notify the staff to inspect the collection tank to be inspected.

[0042] Step S500: If the operating safety state of the collection tank to be detected is an abnormal state within the third time period, an emergency braking instruction is sent to the control module of the collection tank to be detected.

[0043] If the operating safety status of the collection tank to be inspected within the third time period is an abnormal state, it means that the collection tank to be inspected may have an abnormal failure within the third time period in the future period, and an emergency braking command is sent to the control module of the collection tank to be inspected, or an alarm signal is sent to the control system of the staff to remind the staff to check the collection tank to be inspected to achieve the purpose of abnormal warning.

[0044] The method for warning abnormal operation data of a collecting tank of the present invention first determines the liquid level change trend corresponding to the collecting tank to be detected according to the liquid level change amount of the collecting tank to be detected in the first time period, the liquid level change amount of the collecting tank to be detected in the second time period, and the liquid level change amount of the collecting tank to be detected in the target time period. If the liquid level change trend corresponding to the collecting tank to be detected is stable, a plurality of operation data of the collecting tank to be detected in the first time period, a plurality of operation data in the second time period, a plurality of operation data in the target time period, and a plurality of operation data in the historical time period are compared to determine the operation safety state of the collecting tank to be detected in the third time period. Conversely, if the liquid level change trend is that there is a liquid level change, the operation safety state of the collecting tank to be detected in the third time period is determined according to the movement state of the plurality of operation data of the collecting tank to be detected in the first time period, the second time period and the target time period in the operation data trajectory diagram corresponding to the collecting tank to be detected. Finally, if the operation safety state of the collecting tank to be detected in the third time period is an abnormal state, an emergency braking command is sent to the control module of the collecting tank to be detected. By judging the amount of change in the liquid level of the collection tank to be detected, the liquid level change trend of the collection tank to be detected is determined, as well as a method for determining the operation data of the collection tank to be detected. Then, the operation data in the first time period, the second time period, and the target time period are processed by different judgment methods to reduce the monitoring computing power of the operation data of the collection tank to be detected. By judging the operation data in the first time period, the second time period, and the target time period, the operation safety status of the collection tank to be detected in the third time period is predicted to achieve the purpose of abnormal warning.

[0045] An embodiment of the present invention further provides a computer program product, which includes program code. When the program product is run on an electronic device, the program code is used to enable the electronic device to execute the steps of the method according to various exemplary embodiments of the present invention described above in this specification.

[0046] In addition, although the steps of the method in the present disclosure are described in a specific order in the drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps, etc.

[0047] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by combining software with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0048] In an exemplary embodiment of the present disclosure, an electronic device capable of implementing the above method is also provided.

[0049] It will be appreciated by those skilled in the art that various aspects of the present invention may be implemented as a system, method or program product. Therefore, various aspects of the present invention may be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software, which may be collectively referred to herein as a "circuit", "module" or "system".

[0050] The electronic device according to this embodiment of the present invention is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0051] The electronic device is presented in the form of a general-purpose computing device. The components of the electronic device may include, but are not limited to: the at least one processor mentioned above, the at least one storage device mentioned above, and a bus connecting different system components (including storage devices and processors).

[0052] The storage stores program codes, which can be executed by the processor, so that the processor executes the steps according to various exemplary embodiments of the present invention described in the above “Exemplary Method” section of this specification.

[0053] The memory may include readable media in the form of volatile memory, such as random access memory (RAM) and / or cache memory, and may further include read only memory (ROM).

[0054] The storage may also include a program / utility having a set (at least one) of program modules, such program modules including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0055] The bus may represent one or more of several types of bus structures including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures.

[0056] The electronic device may also communicate with one or more external devices (e.g., keyboards, pointing devices, Bluetooth devices, etc.), one or more devices that enable a user to interact with the electronic device, and / or any device that enables the electronic device to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface. Furthermore, the electronic device may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter.

[0057] In an exemplary embodiment of the present disclosure, a computer-readable storage medium is also provided, on which a program product capable of implementing the above method of the present specification is stored. In some possible implementations, various aspects of the present invention can also be implemented in the form of a program product, which includes a program code, and when the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps according to various exemplary embodiments of the present invention described in the above "Exemplary Method" section of the present specification.

[0058] In addition, the above-mentioned figures are only schematic illustrations of the processes included in the method according to an exemplary embodiment of the present invention, and are not intended to be limiting. It is easy to understand that the processes shown in the above-mentioned figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be performed synchronously or asynchronously, for example, in multiple modules.

[0059] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.

[0060] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A method for early warning of abnormal operation data of a collection tank, characterized in that: Applied to a collection tank operation data abnormality early warning system, the collection tank operation data abnormality early warning system is connected to a collection tank to be detected; The abnormal early warning method for the collection tank operation data comprises the following steps: Step S100, determining a liquid level change trend of the to-be-detected collection tank according to the liquid level change of the to-be-detected collection tank in the first time period, the liquid level change of the to-be-detected collection tank in the second time period, and the liquid level change of the to-be-detected collection tank in the target time period; The first time period, the second time period and the target time period have the same length, and the end time of the first time period is the start time of the second time period, the end time of the second time period is the start time of the target time period, and the end time of the target time period is the current time; Step S200: If the liquid level change trend of the collection tank to be detected is stable, execute step S300; otherwise, execute step S400; Step S300, by comparing a number of operating data of the collection tank to be detected in the first time period, a number of operating data in the second time period, a number of operating data in the target time period, and a number of operating data in the historical time period, to determine the operating safety state of the collection tank to be detected in a third time period, and executing step S500; The end time of the historical time period is the start time of the first time period; the length of the third time period is the same as the length of the target time period, and the start time of the third time period is the end time of the target time period; Step S400, according to the several operation data of the collection tank to be detected in the first time period, the second time period and the target time period, the movement state in the operation data trajectory diagram corresponding to the collection tank to be detected is determined to determine the operation safety state of the collection tank to be detected in the third time period, and execute step S500; the operation data trajectory diagram is obtained by training the several operation data of the collection tank to be detected in the historical time period; Step S500: If the operating safety state of the collection tank to be detected is an abnormal state within the third time period, an emergency braking instruction is sent to the control module of the collection tank to be detected.

2. The method according to claim 1, characterized in that The step S100 includes: Step S110: Obtain the liquid level value corresponding to each detection time of the collection tank to be detected in the first time period to obtain a first liquid level value list A1=(A 11 ,A 21 ,...,A i1 ,...,A n1 ); wherein i=1,2,...,n; n is the number of detection moments in the first time period; A i1 is the liquid level value corresponding to the i-th detection moment of the collection tank to be detected in the first time period; the time period between every two adjacent detection moments is the same in length; Step S120: According to the first liquid level value list A1, determine the liquid level change B1 of the to-be-detected collection tank in the first time period = (∑ n i=1 A i1 ) / n; Step S130: Obtain the liquid level value corresponding to each detection time of the collection tank to be detected in the second time period to obtain a second liquid level value list A2=(A 12 ,A 22 ,...,A i2 ,...,A n2 ), where A i2 is the liquid level value corresponding to the i-th detection moment of the collection tank to be detected in the second time period; the length of the period between each adjacent two detection moments in the second time period is the same as the length of the period between each adjacent two detection moments in the first time period; Step S140: According to the second liquid level value list A2, determine the liquid level change B2 of the collection tank to be detected in the second time period = (∑ n i=1 A i2 ) / n; Step S150: Obtain the liquid level value corresponding to each detection time of the collection tank to be detected within the target time period to obtain a target liquid level value list A3=(A 13 ,A 23 ,...,A i3 ,...,A n3 ), where A i3 is the liquid level value corresponding to the i-th detection moment of the collection tank to be detected within the target time period; the time period length between each adjacent detection moment within the target time period is the same as the time period length between each adjacent detection moment within the first time period; Step S160: According to the target liquid level value list A3, determine the liquid level change B3 of the collection tank to be detected within the target time period = (∑ n i=1 A i3 ) / n; Step S170, if |B1-B2|≤B0, and |B2-B3|≤B0, determine that the liquid level change trend corresponding to the collection tank to be detected is tending to be stable; otherwise, determine that the liquid level change trend corresponding to the collection tank to be detected is that there is a liquid level change; wherein B0 is a preset liquid level change difference threshold.

3. The method according to claim 2, characterized in that The step S300 includes: Step S310: Obtain the mean value of each operation data of the collection tank to be detected in the first time period to obtain a first operation data vector C1=(C 11 ,C 21 ,...,C j1 ,...,C k1 ); wherein j=1,2,...,k; k is the number of operation data of the collection tank to be detected; C j1 is the mean value of the j-th operating data of the collection tank to be detected in the first time period; Step S320: Obtain the mean value of each operation data of the collection tank to be detected in the second time period to obtain a second operation data vector C2=(C 12 ,C 22 ,...,C j2 ,...,C k2 ), where C j2 is the mean value of the j-th operating data of the collection tank to be detected in the second time period; Step S330: Obtain the mean value of each operation data of the collection tank to be detected within the target time period to obtain a target operation data vector C3=(C 13 ,C 23 ,...,C j3 ,...,C k3 ), where C j3 is the mean value of the j-th operating data of the collection tank to be detected within the target time period; Step S340: Obtain each historical operation data vector corresponding to the collection tank to be detected to obtain a historical operation data vector list D=(D1, D2, ..., D h ,...,D m ), where h = 1, 2, ..., m; m is the number of historical sub-time periods within the historical time period; D h is the historical operation data vector corresponding to the hth historical sub-time period of the collection tank to be detected within the historical time period; the length of each of the historical sub-time periods is equal to the length of the target time period, and the start time of the hth historical sub-time period is the end time of the h-1th historical sub-time period, and the end time of the hth historical sub-time period is the start time of the h+1th historical sub-time period; the end time of the mth historical sub-time period is the start time of the first time period; D h =(D 1h ,D 2h ,...,D jh ,...,D kh );D jh is the average value of the j-th operating data of the collection tank to be detected in the h-th historical sub-time period; Step S350: determining a plurality of target historical operation data vectors from the plurality of historical operation data vectors according to the medium carried by the collection tank to be detected at the current moment; Step S360: Compare the first operation data vector C1, the second operation data vector C2, the target operation data vector C3 and the target historical operation data vector to determine the operation safety status of the collection tank to be detected within a third time period.

4. The method according to claim 3, characterized in that The step S350 includes: Step S351, obtaining a medium identifier E0 corresponding to the medium carried in the collection tank to be detected at the current moment; Step S352: Obtain the medium identification corresponding to each historical operation data vector in the historical operation data vector list D to obtain a medium identification list E=(E1, E2, ..., E h ,...,E m ), where E h is a medium identifier corresponding to the medium carried by the collection tank to be detected at the end time of the hth historical sub-time period; Step S353, traverse each medium identification in the medium identification list E in turn, if E h =E0, then D h Determine the intermediate historical operation data vector to obtain the intermediate historical operation data vector list F=(F1, F2, ..., F a ,...,F b ), where a=1,2,...,b, b is the number of intermediate historical operation data vectors determined; F a is the determined a-th intermediate historical running data vector; Step S354: If F c-2 The corresponding historical sub-time period, F c-1 The corresponding historical sub-time period, F c The corresponding historical sub-time period, F c+1 If the corresponding historical sub-time periods are consecutive and adjacent historical sub-time periods within the historical time period, then F c Determine the target historical running data vector; where c=3,...,b-1.

5. The method according to claim 4, characterized in that The step S354 includes: Step S355: If the number of target historical operation data vectors in the intermediate historical operation data vector list F is less than a preset target vector number threshold, execute step S400.

6. The method according to claim 5, characterized in that The step S360 includes: Step S361: Obtain each of the target historical operation data vectors to obtain a target historical operation data vector list G=(G1, G2, ..., G d ,...,G e ), where d = 1, 2, ..., e, and e is the number of the determined target historical operation data vectors; G d The historical operation data vector of the determined dth target; Step S362: traverse each target historical operation data vector in the target historical operation data vector list G, and if in the intermediate historical operation data vector list F, the target historical operation data vector in G d The matching degree between the second intermediate historical operation data vector and the first operation data vector C1 is greater than the preset matching degree threshold, and is located at G d The matching degree between the first intermediate historical operation data vector and the second operation data vector C2 is greater than a preset matching degree threshold, and G d If the matching degree with the target operation data vector C3 is greater than the preset matching degree threshold, the target operation data vector C3 is located at G in the intermediate historical operation data vector list F. d The first intermediate historical operation data vector thereafter is determined as the key historical operation data vector; Step S363, obtaining an operation safety status identifier corresponding to each of the key historical operation data vectors; the operation safety status identifier represents the operation safety status of the collection tank to be detected in the historical sub-time period corresponding to the key historical operation data vector corresponding to the operation safety status identifier; Step S364: If, among all the operation safety status identifications, the ratio of the number of operation safety status identifications indicating that the operation safety status is an abnormal state to the total number of the operation safety status identifications is greater than a preset abnormal ratio threshold, it is determined that the operation safety status of the collection tank to be detected in the third time period is an abnormal state.

7. The method according to claim 6, characterized in that The operation data trajectory diagram is obtained by the following steps: Step S401, determining first target operating data and second target operating data corresponding to the collection tank to be detected according to each operating data of the collection tank to be detected; Step S402: input the first target operation data and the second target operation data into a preset data detection model to obtain an operation data trajectory diagram output by the data detection model; The data detection model is obtained by training a number of operation data of the collection tank to be detected in a historical time period; The horizontal coordinate of the track point of the operation data track diagram represents the first target operation data corresponding to the collection tank to be detected; the vertical coordinate of the track point of the operation data track diagram represents the second target operation data corresponding to the collection tank to be detected.

8. The method according to claim 7, characterized in that The step S401 includes: Step S4011, obtain the operation data identifier corresponding to each operation data of the collection tank to be detected, so as to obtain an operation data identifier list H=(H1, H2, ..., H j ,...,H k ), where H j is the operating data identifier corresponding to the j-th operating data of the collection tank to be detected; Step S4012: H1, H2, ..., H j ,...,H k Performing principal component analysis to obtain a plurality of operation data groups; a plurality of corresponding operation data in the same operation data group are correlated with each other; Step S4013, obtaining the impact values ​​of the detection items corresponding to the corresponding several operation data in each operation data group on the safe operation result of the collection tank to be detected, so as to obtain the operation data impact value corresponding to each operation data group, and determine the operation data impact value list I=(I1, I2, ..., I p ,...,I q ); wherein p=1,2,...,q; q is the number of the operation data sets; I p is the operating data impact value corresponding to the pth operating data group; p is the sum of the impact values ​​of the detection items corresponding to the operation data in the pth operation data group on the safe operation result of the collection tank to be detected; Step S4014: determine the operation data group corresponding to MAX(I) as the first operation data group, and the operation data in the first operation data group are the first initial operation data; wherein MAX() is a preset maximum value determination function; Step S4015: Determine the operation data group corresponding to only the operation data influence values ​​less than MAX(I) in the operation data influence value list I as the second operation data group, and the operation data in the second operation data group as the second initial operation data; Step S4016: perform data integration processing on a plurality of the first initial operation data and a plurality of the second initial operation data respectively to obtain first target operation data and second target operation data.

9. The method according to claim 8, characterized in that The step S402 includes: Step S4021, obtaining a parameter value of each operating data corresponding to the first operating data group in each historical sub-time period and a parameter value of each operating data corresponding to the second operating data group in each historical sub-time period; Step S4022: Determine the sum of the parameter values ​​of a plurality of operation data corresponding to the first operation data group in the same historical sub-time period as the first historical operation data parameter value; Step S4023: Determine the sum of the parameter values ​​of a plurality of operation data corresponding to the second operation data group in the same historical sub-time period as the second historical operation data parameter value; Step S4024, obtaining the operating safety status identifier of the collection tank to be detected in each historical sub-time period; Step S4025: input the first historical operating data parameter value, the second historical operating data parameter value, and the operating safety status identifier corresponding to each historical sub-time period into a preset data detection model for training, so as to obtain an operating data trajectory diagram; the abscissa of each trajectory point in the operating data trajectory diagram is the first historical operating data parameter value, and the ordinate of each trajectory point in the operating data trajectory diagram is the second historical operating data parameter value; Step S4026, determining the trajectory point in the initial data trajectory diagram, whose operation safety status mark indicates that the operation safety status of the collection tank to be detected is a normal state, as an operation safety trajectory point; Step S4027: determine the area enclosed by a number of operation safety trajectory points as the operation safety area.

10. The method according to claim 9, characterized in that The step S400 includes: Step S410: determining the sum of the parameter values ​​of the plurality of operating data corresponding to the first operating data group within the first time period as a first target operating data parameter value, and determining the sum of the parameter values ​​of the plurality of operating data corresponding to the second operating data group as a second target operating data parameter value; Step S420: determining the sum of the parameter values ​​of the plurality of operation data corresponding to the first operation data group within the second time period as a third target operation data parameter value, and determining the sum of the parameter values ​​of the plurality of operation data corresponding to the second operation data group as a fourth target operation data parameter value; Step S430: determining the sum of the parameter values ​​of the plurality of operation data corresponding to the first operation data group within the target time period as a fifth target operation data parameter value, and determining the sum of the parameter values ​​of the plurality of operation data corresponding to the second operation data group as a sixth target operation data parameter value; Step S440, inputting the first target operating data parameter value and the second target operating data parameter value into the data detection model to obtain a first trajectory point of the to-be-detected collection tank in the operating data trajectory diagram within the first time period; Step S450, inputting the third target operating data parameter value and the fourth target operating data parameter value into the data detection model to obtain a second trajectory point of the collection tank to be detected in the operating data trajectory diagram within the second time period; Step S460, inputting the fifth target operating data parameter value and the sixth target operating data parameter value into the data detection model to obtain a third trajectory point of the collection tank to be detected in the operating data trajectory diagram within the target time period; Step S470: If the first trajectory point, the second trajectory point, and the third trajectory point are all within the operation safety area, and the length between the third trajectory point and the nearest boundary point of the operation safety area is greater than a preset safety distance threshold, then it is determined that the operation safety status of the collection tank to be detected during the third time period is a normal state; otherwise, it is determined that the operation safety status of the collection tank to be detected during the third time period is an abnormal state.

Images