Data Preprocessing Method, System and Medium for Construction Machinery

Abstract

The present invention relates to the technical field of data preprocessing, and discloses a method, a system and a medium for preprocessing collected data of construction machinery. The method includes: establishing a database, dividing corresponding data groups for each target data collection unit of the construction machinery in the database, and establishing a data index linked list; storing the data collected by each target data collection unit into the corresponding data index linked list; performing a first check on the same type of data collected in chronological order in the same data group to determine the to-be-checked matters and the matter times generated by the data changes within the data group; performing a second check across data groups to verify whether the to-be-checked matters and the corresponding matter times within each data group are correct; if the to-be-checked matters and the corresponding matter times within the data group are incorrect, marking abnormal data in the attribute unit to identify the abnormal data. The present invention is beneficial to solving the technical problems that the collected data of construction machinery has a lot of data noise and outliers, and there are many data samples.

Description

Technical Field

[0001] The present invention relates to the technical field of data preprocessing, and in particular, to a method for preprocessing collected data of construction machinery, a data preprocessing system, and a readable storage medium. Background Art

[0002] Due to the complex working conditions and high construction difficulty of construction machinery, shutdown failures occur frequently. The shutdown of construction machinery will cause a series of losses, such as equipment restriction losses, project schedule delays, and high emergency repair costs and rush repair costs. Moreover, resuming work after emergency repair may cause further damage due to incomplete elimination of equipment failures.

[0003] Construction machinery (such as excavators, cranes, rollers, etc.) has a large number of original data collected due to the complexity of its structure, components, and construction environment. The data types include mechanical system data, hydraulic system data, electrical and control system data, operating condition data, and environmental data, etc.

[0004] By analyzing and monitoring the above data, the operation conditions of construction machinery and the health status of each component can be monitored, so that the manufacturer can timely track the status of the equipment and perform after-sales maintenance in a timely manner to reduce the shutdown failures of construction machinery.

[0005] However, there are multiple difficulties in data collection of construction machinery. For example, construction machinery often works under complex working conditions, and the harsh environment (such as high temperature, high humidity, and dust) makes sensors vulnerable to interference, and the multi-physical field coupling causes the mechanical, hydraulic, and electrical data to possibly affect each other (such as engine vibration interfering with the hydraulic pressure signal). Moreover, construction machinery often has the characteristics of data heterogeneity and multi-source data fusion, and it is necessary to process time series data, image data, and discrete events simultaneously.

[0006] At the same time, the data collected by construction machinery has high requirements for data real-time performance, and the on-vehicle hardware edge computing resources are limited. Construction machinery also has the characteristic of a large amount of collected data (for example, a full-sensor sampling of an excavator can generate dozens of GB of data per day), resulting in high long-term storage costs.

[0007] Therefore, the collected data of construction machinery has technical problems such as a large number of data noises and outliers, and a large number of data samples, which cause great difficulties to the analysis process of directly analyzing the original data, resulting in inaccurate data analysis results. Summary of the Invention

[0008] The main objective of the present invention is to provide a method, system, and medium for preprocessing the collected data of construction machinery, aiming to solve the problems in the prior art that there are many data noises and outliers in the collected data of construction machinery, and there are many data samples, which cause great difficulties in the analysis process of directly using the original data for data analysis, resulting in inaccurate data analysis results.

[0009] To achieve the above objective, a method for preprocessing the collected data of construction machinery provided by the present invention includes the following steps:

[0010] The steps are as follows:

[0011] Establish a database, divide corresponding data groups for each target data acquisition unit of the construction machinery in the database, and establish a data index linked list for each data group. Among them, the data index linked list includes a data unit for storing each original data, a timing unit for marking the timing of each original data, and an attribute unit for marking the attribute of each original data;

[0012] Obtain the data collected by each target data acquisition unit, and store the data collected by each target data acquisition unit into the corresponding data index linked list;

[0013] Perform a first verification on the data in the same data group through the same type of data collected in chronological order, so as to determine the verification matters to be generated by the data change in the data group according to the change situation of the same type of data in the same data group, and the matter time corresponding to the verification matters;

[0014] Perform a second verification across data groups through the verification matters and matter times within each data group of each data group, so as to verify whether the verification matters and corresponding matter times within each data group are correct;

[0015] If the verification matters and corresponding matter times within the data group are incorrect, mark the incorrect data corresponding to the verification matters and corresponding matter times within the data group as abnormal data in the attribute unit to identify abnormal data;

[0016] The cloud server obtains the abnormal data from the database for fault analysis of the construction machinery.

[0017] Optionally, the method further includes:

[0018] Mark the data that does not generate verification matters in the first verification as temporary data in the attribute unit;

[0019] If the verification matters and corresponding matter times within the data group are correct, mark the correct data corresponding to the verification matters and corresponding matter times within the data group as normal data in the attribute unit.

[0020] Optionally, before the step of performing a first verification on the data in the same data group by using the same type of data collected in chronological order in the same data group, so as to determine the matters to be verified generated by the data change in the data group and the matter time corresponding to the matters to be verified, the following steps are included:

[0021] According to the current working condition, divide multiple data groups with a set strong correlation relationship into the same association group; select one data group from the association group as the trusted group, and other data groups as the following groups;

[0022] Calculate the matching situation between the following groups and the trusted group, generate corresponding trust factors for the following groups whose matching situation with the trusted group reaches the preset condition, and generate corresponding penalty factors for the following groups whose matching situation with the trusted group reaches the preset deviation situation;

[0023] According to the penalty factor, correct the data of the data group corresponding to the penalty factor.

[0024] Optionally, the step of obtaining the data collected by each target data acquisition unit and storing the data collected by each target data acquisition unit into the corresponding data index linked list includes:

[0025] Obtain the newly collected data of each target data acquisition unit;

[0026] Generate a data unit, a time sequence unit and an attribute unit corresponding to the newly collected data in the data index linked list;

[0027] Store the newly collected data into the newly generated data unit, and store the time sequence corresponding to the newly collected data into the newly generated time sequence unit.

[0028] Optionally, the step of performing a first verification on the data in the same data group by using the same type of data collected in chronological order in the same data group, so as to determine the matters to be verified generated by the data change in the data group and the matter time corresponding to the matters to be verified, includes:

[0029] Obtain the preset interval set for the same data group, where each interval set includes at least one data interval, each data interval is used to represent different types of matters to be verified, and the data intervals included in the preset interval set of the same data group are different;

[0030] Verify the data in the same data group by using each data interval, so as to merge the data that conform to the same data interval within a continuous time period into the same matter to be verified within the data group;

[0031] Merge the acquisition times corresponding to the data of the same item to be verified within the data group to determine the item time corresponding to the item to be verified.

[0032] Optionally, the step of performing a second cross-data-group verification through the items to be verified and the item times within each data group to verify whether the items to be verified and the corresponding item times within each data group are correct includes:

[0033] Calculate the coincidence degree of the item types and item times across data groups for the items to be verified and the item times within each data group, and determine whether the coincidence degree is lower than a preset value;

[0034] If so, the items to be verified and the corresponding item times within the data group are incorrect;

[0035] If not, the items to be verified and the corresponding item times within the data group are correct.

[0036] Optionally, use the following method to determine the items to be verified generated by the data changes within the data group and the item times corresponding to the items to be verified:

[0037] Obtain the interval set i preset for the th data group ; where i represents the j th data interval in the interval set of the th data group, J and i is the number of data intervals in the interval set of the th data group;

[0038] Obtain the data sequence i formed by the continuous sampling of the th data group, where is the i th sampling data in the data sequence of the continuous sampling of the m th data group, and M is the number of data in the data sequence of the continuous sampling of the i th data group;

[0039] Calculate the label i of the data interval to which each sampling data in the data sequence of the continuous sampling of the th data group belongs, that is, represents the interval label corresponding to the mth data of the i th data group:

[0040] ;

[0041] Convert the data sequence formed by consecutive samplings of the i th data group into an interval label sequence ;

[0042] Scan the interval label sequence to find consecutive subsequences with the same label;

[0043] Obtain the preset matters to be verified corresponding to the data intervals of the consecutive subsequences with the same label within the data group, and obtain the data sampling time interval corresponding to the consecutive subsequences with the same label within the data group as the matter time corresponding to the matter to be verified.

[0044] Optionally, refer to the following method to verify whether the matters to be verified and the corresponding matter times within each data group are correct:

[0045] For matters to be verified of the same type across data groups, preset the same interval label;

[0046] Verify whether the matters to be verified and the corresponding matter times within each data group are correct according to the interval label coincidence degree in the interval label sequences of different data groups. Specifically:

[0047] ;

[0048] Among them, represents the coincidence degree of the interval label of the i th data group and the interval label of the k th data group; represents the k th interval label of the m th data in the th data group, i represents the m th interval label of the k th data group and the m th interval label of the th data group, and the result of the indicator function is 1 when holds, and the result of the indicator function is 0 when

[0049] ;

[0050] Among them, , and , , N is the number of data groups;

[0051] If , it means that the matters to be verified and the corresponding matter times within the data group are incorrect;

[0052] If , it indicates that the matters to be verified within the data group and the corresponding matter times are correct; among them, A is a preset coincidence degree parameter.

[0053] To achieve the above object, the present invention also proposes a data preprocessing system, and the data preprocessing system adopts the method for preprocessing the collected data of the construction machinery to preprocess the data collected by the construction machinery.

[0054] To achieve the above object, the present invention also proposes a readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the method for preprocessing the collected data of the construction machinery are implemented.

[0055] The technical solution of the present invention is beneficial to solving the problems in the prior art that there are many data noises and outliers in the collected data of construction machinery, and there are many data samples, which cause great difficulties to the analysis process of directly performing data analysis using the original data, resulting in inaccurate data analysis results. The specific analysis is as follows: A data group is established for each target data acquisition unit in the database, and a data index linked list is established for each data group. Among them, in each data index linked list, the newly collected real-time data of the corresponding target data acquisition unit is stored in the data unit, and the time sequence corresponding to the real-time data is recorded in the time sequence unit. Therefore, in the database structure, the time sequence and the original data of the real-time data collected by each target data acquisition unit are retained, so that the real-time data in the data group is recorded in an orderly manner. Further, by means of the first verification, the data change situation is verified from the unified data group, and it is determined whether there are matters to be verified according to the data change situation, and the time of the matters to be verified is obtained. At the same time, the second verification across data groups is also performed to judge whether the matters to be verified and the matter times existing within each data group are correct. Therefore, through the data changes in the same data group, the operation conditions and construction conditions of the construction machinery, as well as the corresponding times of the operation conditions and construction conditions, can be found. And through the second verification across groups, it can be found whether other data groups also feedback the same operation conditions and construction conditions of the construction machinery, and through the verification across data groups, the mutual verification of the operation conditions and construction conditions between different data groups is realized. And the data that cannot be verified with other data groups will be identified as incorrect data, and the attribute of the abnormal data will be marked in the data index linked list. Therefore, through the data group and the data index linked list, the original data of the construction machinery can be completely recorded, and the abnormal data can be marked, and the cloud server only needs to obtain the abnormal data for fault analysis, which can not only ensure the storage of complete time sequence data within a short time, but also ensure that only the abnormal data is analyzed separately during data analysis. The original data is stored according to different functions. Description of the Drawings

[0056] Figure 1 Schematic flowchart of the method for preprocessing the collected data of construction machinery in the first embodiment of the present invention;

[0057] Figure 2 Schematic diagram of establishing a data index linked list for each data group in the database in the present invention;

[0058] Figure 3 In the present invention, the i Schematic diagram of converting the data sequence formed by consecutive sampling of the

[0059] Figure 4 Schematic diagram of calculating the overlap degree of interval labels in the interval label sequences of different data groups in the present invention;

[0060] Figure 5 Schematic diagram of the target data acquisition unit of the construction machinery in the present invention adding the collected data to the database.

[0061] The implementation, functional features and advantages of the present invention will be further described with reference to the embodiments and the accompanying drawings. Specific Embodiments

[0062] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0063] In the following description, suffixes such as "unit", "component" or "element" used to represent elements are only for the convenience of describing the present invention, and they have no specific meaning themselves. Therefore, "unit", "component" or "element" can be used interchangeably.

[0064] Please refer to Figures 1 to 5 , in the first embodiment of the present invention, a method for preprocessing the collected data of construction machinery is provided, including the following steps:

[0065] Step S10: Establish a database, divide corresponding data groups for each target data acquisition unit of the construction machinery in the database, and establish a data index linked list for each data group, where the data index linked list includes a data unit for storing each original data, a timing unit for marking the timing of each original data, and an attribute unit for marking the attribute of each original data;

[0066] Step S20: Obtain the data collected by each target data acquisition unit, and store the data collected by each target data acquisition unit into the corresponding data index linked list;

[0067] Step S30: Perform a first verification on the data in the same data group by using the same-type data collected in chronological order in the same data group, so as to determine the matters to be verified generated by the data changes within the data group and the matter times corresponding to the matters to be verified according to the changes of the same-type data in the same data group.

[0068] Step S40: Perform a second cross-data-group verification by using the matters to be verified and the matter times within each data group to verify whether the matters to be verified and the corresponding matter times within each data group are correct.

[0069] Step S50: If the matters to be verified and the corresponding matter times within the data group are incorrect, mark the error data corresponding to the matters to be verified and the corresponding matter times within the data group as abnormal data in the attribute unit to identify the abnormal data.

[0070] Step S60: The cloud server obtains the abnormal data from the database for fault analysis of the construction machinery.

[0071] The technical solution of the present invention is beneficial to solving the problems in the prior art that there are many data noises and outliers in the collected data of construction machinery, and there are many data samples, which cause great difficulties in the analysis process of directly analyzing the original data, resulting in inaccurate data analysis results. The specific analysis is as follows: A data group is established for each target data acquisition unit in the database, and a data index linked list is established for each data group. Among them, in each data index linked list, the real-time data newly collected by the corresponding target data acquisition unit is stored in the data unit, and the time sequence corresponding to the real-time data is recorded in the time sequence unit. Therefore, in the database structure, the time sequence and the original data of the real-time data collected by each target data acquisition unit are retained, so that the real-time data in the data group is recorded in an orderly manner. Further, through the first verification method, the data change situation is verified from the unified data group, and it is determined whether there are matters to be verified according to the data change situation, and the time of the matters to be verified is obtained. At the same time, through the second verification across data groups, it is judged whether the matters to be verified and the matter times existing in each data group are correct. Therefore, through the data changes in the same data group, the operation situation and construction situation of the construction machinery, as well as the corresponding times of the operation situation and construction situation, can be found. And through the second cross-group verification, it can be found whether other data groups also reflect the same operation situation and construction situation of the construction machinery, and through the cross-data group verification, the mutual verification of the operation situation and construction situation between different data groups is realized. The data that cannot be verified with other data groups will be identified as incorrect data, and the attribute of the abnormal data will be marked in the data index linked list. Therefore, through the data group and the data index linked list, the original data of the construction machinery can be completely recorded, and the abnormal data can be marked. The cloud server only needs to obtain the abnormal data for fault analysis, which can not only ensure the storage of complete time sequence data within a short time, but also ensure that only the abnormal data is analyzed separately during data analysis. The original data is stored according to different functions.

[0072] The data collected in real time by construction machinery (such as excavators, cranes, loaders, etc.), especially the data related to fault monitoring, usually covers the key parameters of mechanical, hydraulic, electrical, thermal and other systems.

[0073] Therefore, the target data acquisition unit in this application refers to the component used to collect the key working parameters of construction machinery.

[0074] For example: The target data acquisition unit can be an acceleration sensor for collecting vibration speed or acceleration; the target data acquisition unit can also be a pressure sensor for detecting the pressure of hydraulic components; or, the target data acquisition unit can be a flow meter for detecting the oil flow; again, the target data acquisition unit can be a temperature sensor for detecting the motor temperature, etc.

[0075] Meanwhile, the target data acquisition unit can be a component for detecting environmental and operating data. For example, it can be a detection component for GPS data, attitude data, handle signals, and pedal signals.

[0076] In the real-time monitoring data of construction machinery, different types of working data are strongly correlated with its working state and the operations being performed. Through multi-sensor data fusion and pattern recognition, the real-time state of the machinery (such as normal operation, no-load, overload, fault, etc.) and specific operations (such as excavation, lifting, rotation, etc.) can be accurately determined.

[0077] Moreover, corresponding work items can also be identified based on the data changes in the same data group.

[0078] For example, when the construction machinery is an excavator and one of the target data acquisition units is a pressure sensor for monitoring the change in the main pump pressure (here, the main pump pressure is taken as the outlet pressure), when storing the real-time data of the main pump pressure into the data index linked list of the corresponding data group, the operating state of the excavator can be determined through the change in the main pump pressure.

[0079] For example, when the main pump pressure is in the range of [0MPa, 5 MPa], the corresponding item to be verified may be: no-load standby operation;

[0080] When the main pump pressure is in the range of (5MPa, 15 MPa], the corresponding item to be verified may be: light-load operation;

[0081] When the main pump pressure is in the range of (15MPa, 25 MPa], the corresponding item to be verified may be: normal operating load;

[0082] When the main pump pressure is in the range of (25MPa, 30MPa], the corresponding item to be verified may be: heavy-load operation;

[0083] When the main pump pressure exceeds 30MPa, the corresponding item to be verified may be: overpressure state;

[0084] When the fluctuation rate of the main pump pressure reaches the set rate, the corresponding item to be verified may be: load mutation or pump failure.

[0085] Another example is when the construction machinery is an excavator and another target data acquisition unit is a flow meter for monitoring the change in the main pump flow rate. When storing the real-time data of the main pump flow rate into the data index linked list of the corresponding data group, the operating state of the excavator can also be determined through the change in the main pump flow rate.

[0086] For example, when the main pump flow rate is in the range of (20L / min, 50 L / min], the corresponding item to be verified may be: no-load standby operation;

[0087] When the main pump flow rate is in the range of (50 L / min, 120 L / min], the corresponding items to be verified may be: light load operation;

[0088] When the main pump flow rate is in the range of (120 L / min, 180 L / min], the corresponding items to be verified may be: normal operation load;

[0089] When the main pump flow rate is in the range of (180 L / min, 200 L / min], the corresponding items to be verified may be: heavy load operation;

[0090] When the main pump flow rate is in the range of (0 L / min, 20 L / min], the corresponding items to be verified may be: system blockage;

[0091] When the fluctuation rate of the main pump flow rate reaches the set rate, the corresponding items to be verified may be: sudden load change or pump failure.

[0092] The above data are only examples. Specifically, the corresponding relationship between the parameter range and the operation status during the actual operation of each construction machinery can be measured, and each data range of each data group can be determined according to the measured results.

[0093] Therefore, through the first verification, according to the data change situation in the same data group, the items to be verified generated by the data change in the data group and the corresponding event time can be determined.

[0094] Furthermore, the second verification is a cross-data group verification. That is, each item to be verified and the event time obtained within each data group are matched with each item to be verified and the event time obtained within the remaining other data groups to determine whether each item to be verified and the event time obtained within this data group are correct. If correct, it usually means the system is operating normally. If incorrect, it indicates that the corresponding target data acquisition unit fails, or the target component monitored by the target data acquisition unit fails, and the error data needs to be analyzed for faults.

[0095] Based on the first embodiment of the method for preprocessing the collected data of the construction machinery of the present invention, in the second embodiment of the method for preprocessing the collected data of the construction machinery of the present invention, the method further includes:

[0096] Step S70, temporarily mark the data that does not generate items to be verified in the first verification in the attribute unit;

[0097] Step S80, if the items to be verified and the corresponding event time in the data group are correct, mark the correct data corresponding to the items to be verified and the corresponding event time in the data group in the attribute unit as normal data.

[0098] In the first embodiment, various data for generating items to be verified are listed. In actual engineering applications, that is, in data analysis, it is not necessary to set corresponding items to be verified for the monitoring data of each interval (for example, light load operation can be excluded from the items to be verified), thus reducing the data processing pressure on the system.

[0099] For example, when one of the data groups is the main pump pressure, only the following can be set as corresponding items to be verified respectively: the main pump pressure is 25 - 30 MPa, the main pump pressure exceeds 30 MPa, and the main pump pressure fluctuation rate reaches the set rate.

[0100] Therefore, data not within the above intervals are data that do not generate items to be verified, and temporary data marking is performed in the attribute units corresponding to the data that do not generate items to be verified.

[0101] The temporary data marking indicates that these data are unimportant data set by after-sales personnel or the manufacturer, and the data can be cleared according to the set temporary data cleaning cycle to retain the storage capacity of the system.

[0102] Meanwhile, each item to be verified and the event time obtained within each data group are matched with the items to be verified and the event times obtained within the remaining other data groups. After determining that each item to be verified and the event time obtained within this data group are correct, it usually indicates that the system operates normally during these data collection cycles, or that the monitoring object corresponding to this data group works normally. At this time, these data are marked as normal data in the corresponding attribute units. Normal data is convenient for after-sales personnel to retrieve data in a timely manner and have a real-time understanding of the operating status of construction machinery equipment. Similarly, the data can also be cleared according to the set normal data cleaning cycle to retain the storage capacity of the system.

[0103] Meanwhile, according to whether the attribute in each data group is marked as normal or abnormal, the normal operation time period and abnormal operation time period of the equipment can also be understood. In addition, the items to be verified and the event times, as well as the normal operation cycle and abnormal operation cycle, can be used to generate an analysis result of the data on which items to be verified the equipment is prone to abnormal operation status, so as to facilitate the analysis of the cause of equipment failures and the tracking of equipment failures.

[0104] Based on the first embodiment of the method for preprocessing collected data of a construction machinery according to the present invention, in the third embodiment of the method for preprocessing collected data of a construction machinery according to the present invention, before step S30, the following steps are included:

[0105] Step S90, according to the current working condition, divide multiple data groups with a set strong correlation relationship into the same association group; select one data group from the association group as the trust group, and the other data groups as the following groups;

[0106] Step S100, calculate the matching situation between the following groups and the trusted groups, generate corresponding trust factors for the following groups whose matching situation with the trusted groups reaches the preset conditions, and generate corresponding penalty factors for the following groups whose matching situation with the trusted groups reaches the preset deviation situation;

[0107] Step S110, correct the data of the data group corresponding to the penalty factor according to the penalty factor.

[0108] Specifically, multiple data groups with a set strong correlation relationship refer to a strong correlation where the physical parameters have a calculation relationship.

[0109] For example, pump power = pressure difference between the inlet and outlet of the main pump × main pump flow rate, that is , P is the pump power, is the pressure difference between the inlet and outlet of the main pump, is the main pump flow rate.

[0110] At this time, the main pump inlet pressure data group and the main pump outlet pressure data group can be used as a group of trusted groups (of course, a group of data groups can be at least one data group, here it is two data groups), and the pressure difference data between the inlet and outlet of the main pump is calculated. Because it directly reflects the load and there is a theoretical calculation formula with the main pump flow rate.

[0111] Specifically, the calculation methods of the trust factor and the penalty factor are as follows:

[0112] (1) Take the main pump inlet pressure data group and the main pump outlet pressure data group as the trusted groups, and take the main pump flow rate Q as the following group; the constraint condition of the theoretical strong correlation relationship is: × Q ≤ rated power.

[0113] (2) Calculate the real-time theoretical main pump flow rate : ;

[0114] (3) Calculate the matching degree of the actual main pump flow rate and the theoretical main pump flow rate :

[0115] ;

[0116] Among them, the trusted group and the following group respectively contain M sampling data, m represents the serial number of the sampling data, , is the m th actual main pump flow rate in the following group, is the m th theoretical main pump flow rate in the following group calculated based on the pressure difference between the inlet and outlet of the m th main pump in the trust group.

[0117] When it reaches the preset condition for matching with the trust group, a mapping relationship table between the preset matching degree and the trust factor is used to determine the value of the trust factor according to the specific value of the matching degree;

[0118] When it does not reach the preset condition for matching with the trust group, a mapping relationship table between the preset matching degree and the penalty factor is used to determine the value of the penalty factor according to the specific value of the matching degree.

[0119] Specifically, when the penalty factor belongs to the set numerical interval, the corresponding attribute unit of the following group data can be marked as abnormal data. At this time, the first check and the second check do not need to be performed on this data group.

[0120] Based on the first embodiment of the method for preprocessing acquisition data of construction machinery according to the present invention, in the fourth embodiment of the method for preprocessing acquisition data of construction machinery according to the present invention, the step S20 includes:

[0121] Step S21, obtaining the newly acquired data of each target data acquisition unit;

[0122] Step S22, generating a data unit, a timing unit, and an attribute unit corresponding to the newly acquired data in the data index linked list;

[0123] Step S23, storing the newly acquired data into the newly generated data unit, and storing the timing corresponding to the newly acquired data into the newly generated timing unit.

[0124] Specifically, when the data index linked list generates newly acquired data, it generates a data unit, a timing unit, and an attribute unit for the newly acquired data, thereby realizing the automatic matching of the length of the data index linked list with the number of acquisition data.

[0125] The timing unit is used to ensure the correct sequential recording of data. The attribute unit is used to mark the data type to achieve automatic sorting and automatic classification marking of data. Thus, the cloud server can call the required type of data for analysis, and it is also convenient for subsequent data classification storage.

[0126] Based on the first embodiment of the method for preprocessing acquisition data of construction machinery according to the present invention, in the fifth embodiment of the method for preprocessing acquisition data of construction machinery according to the present invention, the step S30 includes:

[0127] Step S31: Obtain the preset interval set for the same data group. Each interval set includes at least one data interval, and each data interval is used to represent different types of matters to be verified. The data intervals included in the interval set preset for the same data group are different;

[0128] Step S32: For the data in the same data group, perform verification using each data interval to merge the data that conforms to the same data interval within a continuous time period into the same matter to be verified within the data group;

[0129] Step S33: Merge the acquisition times of the data corresponding to the same matter to be verified within the data group to determine the matter time corresponding to the matter to be verified.

[0130] Specifically, for the same data group, each data interval in the interval set corresponds to an operating state of the construction machinery. The interval set of the same data group can include one or more data intervals, and the number of data intervals in the interval set of the same data group is related to the preset monitored working states. For example, when the background only needs to obtain the real-time data of heavy-load operations, the interval set may only include one data interval, and this data interval only needs to correspond to the data interval of heavy-load operations. Another example is that when the background needs to obtain the real-time data of no-load standby operations and heavy-load operations, the interval set includes two data intervals, one of which corresponds to the data interval of no-load standby operations and the other corresponds to the data interval of heavy-load operations.

[0131] Based on the fifth embodiment of the method for preprocessing the collected data of the construction machinery of the present invention, in the sixth embodiment of the method for preprocessing the collected data of the construction machinery of the present invention, the step S40 includes:

[0132] Step S41: Calculate the coincidence degree of the type of matter and the matter time across data groups for the matters to be verified and the matter times within each data group, and determine whether the coincidence degree is lower than the preset value;

[0133] If so, execute step S42: The matter to be verified and the corresponding matter time within the data group are incorrect;

[0134] If not, execute step S43: The matter to be verified and the corresponding matter time within the data group are correct.

[0135] Based on the sixth embodiment of the method for preprocessing the collected data of the construction machinery of the present invention, in the seventh embodiment of the method for preprocessing the collected data of the construction machinery of the present invention, the following method is used to determine the matters to be verified generated by the data change within the data group and the matter times corresponding to the matters to be verified:

[0136] Obtain for the iThe preset interval set of each data group ; among them, represents the i th data interval in the interval set of the j th data group, , J is the number of data intervals in the interval set of the i th data group, ;

[0137] Obtain the data sequence formed by continuous sampling of the i th data group , among which, is the i th sampling data in the data sequence of continuous sampling of the m th data group, , M is the number of data in the data sequence of continuous sampling of the i th data group;

[0138] Calculate the label of the data interval to which each sampling data i in the data sequence of continuous sampling of the th data group belongs , that is represents the interval label corresponding to the mth data of the i th data group:

[0139] ;

[0140] Convert the data sequence formed by continuous sampling of the i th data group into an interval label sequence ;

[0141] Scan the interval label sequence to find consecutive subsequences with the same label;

[0142] Obtain the preset matters to be verified corresponding to the data intervals of the consecutive subsequences with the same label within the data group, and obtain the data sampling time interval corresponding to the consecutive subsequences with the same label within the data group as the matter time corresponding to the matter to be verified.

[0143] Based on the seventh embodiment of the acquisition data preprocessing method of the construction machinery of the present invention, in the eighth embodiment of the acquisition data preprocessing method of the construction machinery of the present invention, verify whether the matters to be verified and the corresponding matter times within each data group are correct in the following manner:

[0144] For the same type of matters to be verified across data groups, preset the same interval label;

[0145] According to the overlap of interval labels in the interval label sequences of different data groups, verify whether the items to be verified and the corresponding item time in each data group are correct, specifically:

[0146] ;

[0147] in, Indicates i The interval label and the k The overlap of the interval labels of the data groups; Indicates k The first m The interval label corresponding to the data is Indicates i The first m The interval number and k The data set m The indicator function of the interval labels, When the indicator function is established, the result is 1. When it is not true, the result of the indicator function is 0;

[0148] ;

[0149] in, ,and , , N is the number of data sets;

[0150] like , it means that the items to be verified in the data group and the corresponding item time are wrong;

[0151] like , it means that the items to be verified and the corresponding item time in the data group are correct; among them, A is the preset coincidence parameter.

[0152] It should be noted that A Represents the minimum allowed overlap. If it is equal to or lower than the minimum overlap, it is determined that the data changes of this data group cannot be mutually verified with the data changes of other data groups. When the minimum overlap can be reached, it is within the overlap range allowed by the system.

[0153] Furthermore, as another extended embodiment, the normal data may be further marked:

[0154] Specifically, set another standard overlap C , standard overlap C Greater than A ;

[0155] , then it meansi The coincidence degree of one data group with other data groups is good, and good data marking is further carried out in the corresponding attribute units.

[0156] , which indicates that the i coincidence degree of the data group with other data groups is normal, and general data marking is further carried out in the corresponding attribute units.

[0157] Thus, good data and general data can be distinguished and marked.

[0158] To achieve the above object, the present invention further provides a data preprocessing system, which adopts the method for preprocessing the collected data of the construction machinery to preprocess the data collected by the construction machinery.

[0159] To achieve the above object, the present invention further provides a readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the method for preprocessing the collected data of the construction machinery are implemented.

[0160] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-described embodiment methods can be implemented by means of software plus a necessary general hardware platform, or by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, in essence, or the part that makes a contribution to the prior art, can be embodied in the form of a software product, which is stored in a readable storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions for causing a terminal device to enter the methods described in the various embodiments of the present invention.

[0161] In the description of this specification, the descriptions with reference to terms such as "one embodiment", "another embodiment", "other embodiments", or "the first embodiment to the Xth embodiment" etc. mean that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, method steps or characteristics described can be combined in a suitable manner in any one or more embodiments or examples.

[0162] It should be noted that in this document, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, such that a process, method, article or system comprising a series of elements not only includes those elements but also includes other elements not explicitly listed, or further includes elements inherent to such process, method, article or system. Without further limitation, an element defined by the statement "comprising one..." does not exclude the presence of another identical element in the process, method, article or system comprising that element.

[0163] The serial numbers of the embodiments of the present invention above are only for description and do not represent the superiority or inferiority of the embodiments.

[0164] The above are only the preferred embodiments of the present invention, and do not limit the patent scope of the present invention accordingly. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present invention, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present invention.

Claims

1. A method for preprocessing collected data of construction machinery, characterized in that It includes the following steps: Establish a database. Divide corresponding data groups for each target data acquisition unit of construction machinery in the database, and establish a data index linked list for each data group. The data index linked list includes data units for storing each piece of original data, timing units for marking the timing of each piece of original data, and attribute units for marking the attributes of each piece of original data; Obtain the data collected by each target data acquisition unit, and store the data collected by each target data acquisition unit into the corresponding data index linked list; Perform a first verification on the data in the same data group through the same type of data collected in sequence in the same data group, so as to determine the verification items to be verified generated by the data change in the data group and the corresponding item time according to the change situation of the same type of data in the same data group; Perform a second cross-data-group verification through the verification items to be verified and the item time within each data group of each data group, so as to verify whether the verification items to be verified and the corresponding item time within each data group are correct; If the verification items to be verified and the corresponding item time within the data group are incorrect, mark the incorrect data corresponding to the verification items to be verified and the corresponding item time within the data group as abnormal data in the attribute unit to identify abnormal data; The cloud server obtains the abnormal data from the database for fault analysis of construction machinery; Verify whether the verification items to be verified and the corresponding item time within each data group are correct in the following manner: Set the same interval label for the verification items to be verified of the same type across data groups; Verify whether the verification items to be verified and the corresponding item time within each data group are correct according to the overlap degree of the interval labels in the interval label sequences of different data groups. Specifically: ； Among them, represents the coincidence degree of the interval label of the i th data group and the interval label of the k th data group; represents the interval label corresponding to the k th data of the m th data group, represents the indicator function of the i th interval label of the m th data group and the k th interval label of the m th data group. When holds, the result of the indicator function is 1, and when does not hold, the result of the indicator function is 0; , M is the number of data in the continuous sampling data sequence of the i th data group;​​ ； Among them, and , , N is the number of data groups; If , it indicates that the matters to be verified within the data group and the corresponding matter times are incorrect; If , it means that the items to be verified in the data group and the corresponding item times are correct; where A is a preset coincidence degree parameter.

2. The method for preprocessing the collected data of the construction machinery according to claim 1, wherein, The method further includes: Mark the data that does not generate verification items to be verified in the first verification as temporary data in the attribute unit; If the verification items to be verified and the corresponding item time within the data group are correct, mark the correct data corresponding to the verification items to be verified and the corresponding item time within the data group as normal data in the attribute unit.

3. The data acquisition preprocessing method for construction machinery according to claim 1, characterized in that Before the step of performing a first verification on the data in the same data group through the same type of data collected in sequence in the same data group, so as to determine the verification items to be verified generated by the data change in the data group and the corresponding item time, the following steps are included: According to the current working condition, divide multiple data groups with a set strong correlation relationship into the same association group; select one group of data groups from the association group as the trust group, and other data groups as the following groups; Calculate the matching situation between the following groups and the trust group, generate corresponding trust factors for the following groups whose matching situation with the trust group reaches the preset condition, and generate corresponding penalty factors for the following groups whose matching situation with the trust group reaches the preset deviation situation; Correct the data of the data group corresponding to the penalty factor according to the penalty factor.

4. The method for preprocessing the collected data of the construction machinery according to claim 1, characterized in that, The step of obtaining the data collected by each target data acquisition unit and storing the data collected by each target data acquisition unit into the corresponding data index linked list includes: Obtain the newly collected data of each target data acquisition unit; Generate a data unit, a timing unit, and an attribute unit corresponding to the newly collected data in the data index linked list; Store the newly collected data into the newly generated data unit, and store the timing corresponding to the newly collected data into the newly generated timing unit.

5. The method for preprocessing the collected data of the construction machinery according to claim 1, characterized in that, The step of performing a first verification on the data in the same data group by using the same type of data collected in chronological order in the same data group, so as to determine the matters to be verified generated by the data change in the data group and the matter time corresponding to the matters to be verified includes: Obtain the preset interval set for the same data group, where each interval set includes at least one data interval, and each data interval is used to represent different types of matters to be verified, and the data intervals included in the preset interval set for the same data group are different; Verify the data in the same data group by using each data interval, so as to merge the data that conforms to the same data interval within a continuous time period into the same matter to be verified within the data group; Merge the collection times of the data merged into the same matter to be verified within the data group, so as to determine the matter time corresponding to the matter to be verified.

6. The method for preprocessing the collected data of the construction machinery according to claim 5, characterized in that, The step of performing a second verification across data groups by using the matters to be verified and the matter times within each data group of each data group, so as to verify whether the matters to be verified and the corresponding matter times within each data group are correct includes: Calculate the coincidence degree of the matter types and the matter times across data groups for the matters to be verified and the matter times within each data group of each data group, and determine whether the coincidence degree is lower than the preset value; If so, the matters to be verified and the corresponding matter times within the data group are incorrect; If not, the matters to be verified and the corresponding matter times within the data group are correct.

7. The method for preprocessing the collected data of the construction machinery according to claim 6, wherein, Determine the matters to be verified generated by the data change in the data group and the matter time corresponding to the matters to be verified in the following manner: Obtain the interval set preset for the i th data group ; Among them, represents the i th data interval in the interval set of the j th data group, , J is the i number of data intervals in the interval set of the th data group; Obtain the i data sequence formed by continuous sampling of the -th data set, where is the i -th sampling data in the data sequence of continuous sampling of the m -th data set; Calculate the i label of the data interval to which each sampled data in the continuously sampled data sequence of the th data group belongs, that is, it represents the interval label corresponding to the mth data of the th data group: i ​ ； Convert the data sequence formed by consecutive samplings of the i th data set into an interval label sequence ; Scan the interval label sequence to find continuous subsequences with the same label; Obtain the matters to be verified preset for the data intervals corresponding to the continuous subsequences with the same label within the data group, and obtain the data sampling time interval corresponding to the continuous subsequences with the same label within the data group as the matter time corresponding to the matters to be verified.

8. A data preprocessing system, characterized in that, The data preprocessing system uses the method for preprocessing the collected data of the construction machinery according to any one of claims 1 to 7 to preprocess the collected data of the construction machinery.

9. A readable storage medium, characterized in that, The computer program is stored on the readable storage medium, and when the computer program is executed by the processor, the steps of the method for preprocessing the collected data of the construction machinery according to any one of claims 1 to 7 are implemented.

Images