Bus duct operation environment monitoring and early warning system based on Internet of Things

Abstract

The invention relates to the technical field of data processing, in particular to a bus duct operation environment monitoring and early warning system based on the Internet of Things, which comprises a monitoring record integration module, an access sequence analysis module, an abnormal record capture module and a real-time record analysis module, the monitoring record integration module is used for dividing each historical monitoring record and carrying out information integration; the access sequence analysis module is used for analyzing to obtain an effective value of each historical monitoring record and setting an access sequence; the exception record analysis module is used for capturing exception monitoring records with exception data; determining an access duration threshold and a reference monitoring record for updating the abnormal monitoring record; and the real-time record analysis module is used for acquiring a currently generated real-time monitoring record, and if the real-time monitoring record contains abnormal data, the real-time monitoring record is subjected to record updating or secondary monitoring reminding.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a bus duct operation environment monitoring and early warning system based on the Internet of Things. Background Art

[0002] Bus duct is a device used for power transmission and distribution, and is widely used in industrial, commercial and civil buildings. It is mainly made of conductive materials and can effectively transmit electrical energy from one place to another; bus duct transmits electrical energy from the power source to the load through its conductors; when the current passes through the conductors, the conductors effectively transfer the electrical energy to the connected equipment. Because the bus duct is designed to have low resistance and high conductivity, it is able to support the transmission of large currents.

[0003] The operating environment monitoring of bus duct plays an important role in the power system. A large amount of data will be generated during the monitoring process, including data that has been stored for a long time and is not needed. This situation will affect the efficiency of users accessing target data. At the same time, some data abnormalities will appear during the monitoring process. Users can repair them based on previous data, but because the amount of stored data is too large, when users process abnormal data, they need to spend a lot of time to traverse all the data, which seriously affects the timeliness and efficiency of data processing. Summary of the invention

[0004] The purpose of the present invention is to provide a bus duct operating environment monitoring and early warning system based on the Internet of Things to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: a bus duct operation environment monitoring and early warning system based on the Internet of Things, the monitoring and early warning system includes a monitoring record integration module, an access sequence analysis module, an abnormal record capture module and a real-time record analysis module;

[0006] The monitoring record integration module is used to generate a historical monitoring record for the data generated during each historical monitoring process of the bus duct, obtain the environmental information contained in each historical monitoring record, and classify each historical monitoring record; and integrate the information of the historical monitoring records that are in the same category after classification;

[0007] The access sequence analysis module is used to record the user's historical access to each historical monitoring record, analyze the user's access to each historical monitoring record, obtain the valid value of each historical monitoring record, and determine whether to mark the historical monitoring record as invalid data; set the access sequence for the historical monitoring record that does not have an invalid data mark;

[0008] The abnormal record analysis module is used to obtain the access footprints of any two adjacent historical monitoring records and capture the abnormal monitoring records with abnormal data; if there is a monitoring record update behavior in the access footprint of the abnormal monitoring record, analyze the access time from the abnormal monitoring record to the next historical monitoring record, determine the access time threshold and the reference monitoring record for updating the abnormal monitoring record; reset the access order of the historical monitoring records, and delete the historical monitoring records with invalid data marks;

[0009] The real-time record analysis module is used to obtain the real-time monitoring record currently generated. If the real-time monitoring record contains abnormal data, the historical monitoring record is accessed and compared through the environmental information contained in the real-time monitoring record to obtain the reference monitoring record corresponding to the real-time monitoring record, and the real-time monitoring record is updated; if the access time to the historical monitoring record exceeds the access time threshold, a secondary monitoring reminder is performed on the real-time monitoring record.

[0010] Further, the monitoring record integration module includes a monitoring record division unit and a record data integration unit;

[0011] The monitoring record classification unit is used to obtain environmental information in each historical monitoring record, perform feature extraction on the environmental information, obtain a number of environmental features, and generate an environmental feature set; classify all historical monitoring records according to the environmental feature set;

[0012] The monitoring record division unit is used to obtain the environmental information contained in any historical monitoring record, perform feature extraction on the environmental information, and generate an environmental feature set of the historical monitoring record; extract the environmental feature sets of any two historical monitoring records respectively, extract an environmental feature from one set of environmental feature sets, and compare it with any environmental feature in the other set of environmental feature sets; if the two compared environmental features are the same, set the two environmental features as common environmental features; perform quantitative statistics on the common environmental features between the two sets of environmental feature sets, and obtain the number of environmental features in the two sets of environmental feature sets respectively; if the number of common environmental features is equal to the number of environmental features in the two sets of environmental feature sets, the two historical monitoring records are divided into the same category to generate a monitoring record set;

[0013] The record data integration unit is used to arbitrarily select a set of monitoring record sets, obtain the change in the temperature of the bus duct in each historical monitoring record in a unit cycle, analyze the degree of difference between any two historical monitoring records, and integrate several historical monitoring records in the monitoring record set by comparing the degree of difference with a set difference threshold.

[0014] Further, the record data integration unit includes:

[0015] Get a set of monitoring records at random, get the temperature change of the bus duct in a unit period in the i-th historical monitoring record in the monitoring record set, divide the unit period into several time points, get the temperature at any time point, and get the average temperature of the i-th historical monitoring record as (T ave ) i , set the highest temperature of the i-th historical monitoring record to (T max ) i and the minimum temperature is (T min ) i , the fluctuation range of the i-th historical monitoring record is

[0016] F i =[(T max ) i -(T min ) i ] / (T ave ) i ;

[0017] Obtain the fluctuation range of each historical monitoring record in the monitoring record set, sort the fluctuation ranges from large to small according to the values, and select a fluctuation range according to the sorted order, obtain the number of historical monitoring records with values ​​less than the fluctuation range as N, and obtain the proportion of the number of records less than the fluctuation range as α=N / N m , where N m is the number of historical monitoring records in the monitoring record set; set the number ratio threshold α max , if α<α max , then select the next fluctuation range difference from the sorted order and recalculate until α>α is satisfied max Until; it will satisfy α>α max The fluctuation range is taken as the maximum allowable fluctuation range F of each historical monitoring record in the monitoring record set max ;

[0018] If the fluctuation range of the i-th historical monitoring record is F i >F max , then get the average temperature (T ave ) i , the normal temperature range of the i-th historical monitoring record is T i =((T ave ) i ×(1-F max ),(T ave ) i ×(1+F max)); if there is a temperature at a certain time point in a certain historical monitoring record that is not within the normal temperature range, then the certain historical monitoring record is removed from the monitoring record set; after obtaining and removing several historical monitoring records, the average value of the j-th time point of all historical monitoring records in the monitoring record set is calculated to obtain the average temperature at the j-th time point: Obtaining the average temperature at each time point as the temperature change process of the monitoring record set;

[0019] Analyze the temperature change process of each historical monitoring record under the same set of environmental characteristics, integrate the historical monitoring records with similar fluctuation ranges, and merge the records under the same environment, which can effectively reduce the amount of data storage and ensure that the subsequent use of related data will not be affected after data integration, thereby improving data utilization efficiency;

[0020] The removed historical monitoring records are merged to generate a new monitoring record set, the temperature fluctuation range of the historical monitoring records in the new monitoring record set is recalculated, and the historical monitoring records are re-divided into a number of monitoring record sets to obtain the temperature change process of each monitoring record set;

[0021] Separating historical monitoring records with large differences in temperature change processes under the same environment can not only distinguish records with abnormal data, but also distinguish data differences caused by different values ​​under the same environmental characteristics, making historical detection records more accurate, and also facilitating subsequent detection and repair of abnormal monitoring records; it can improve work efficiency;

[0022] Each monitoring record set is presented in the form of a new historical monitoring record, and the temperature change process of the monitoring record set is the temperature change process of the corresponding new historical monitoring record.

[0023] Further, the access sequence analysis module includes a valid value calculation unit and an access sequence setting unit;

[0024] The effective value calculation unit is used to obtain the number of times a user visits a certain historical monitoring record through the user's access footprint; obtain the number of times the remaining historical monitoring records in the monitoring record set where the certain historical monitoring record is located; analyze the record generation time interval between any two adjacent historical monitoring records in the monitoring record set, and calculate the effective value of the monitoring record set where the certain historical monitoring record is located; and mark invalid data for new historical monitoring records corresponding to some monitoring record sets;

[0025] The access sequence setting unit is used to sort the valid values ​​from large to small to generate an access sequence for the user to subsequently access each new historical monitoring record.

[0026] Furthermore, the effective value calculation unit includes:

[0027] Set the number of times a user accesses the i-th historical monitoring record to P i ; Get the monitoring record set where the i-th historical monitoring record is located, set the monitoring record set where it is located as the a-th monitoring record set, count the number of visits to each historical monitoring record in the a-th monitoring record set, and get the total number of visits to the a-th monitoring record set by the user as Q a ; Get the time interval between each user's access to the i-th historical monitoring record and the current time point; select the access time with the shortest time interval, and set the shortest access time to (Δt min ) i ;

[0028] Get the record generation time interval of any two adjacent historical monitoring records in the a-th monitoring record set, sort them according to the record generation time, select the record generation time interval with the largest value, and set it as the access time threshold (Δt max ) a ; According to the formula:

[0029]

[0030] Among them, IF() is a judgment function. If (Δt min ) i <(Δt max ) a , then IF((Δt min ) i ≤(Δt max ) a )=1, otherwise, IF((Δt min ) i ≤(Δt max ) a =0; calculate the effective value Zi of the i-th historical monitoring record;

[0031] The number of visits can reflect the user's historical visit frequency and the possible visit frequency in the future; IF((Δt min ) i ≤(Δt max ) aReflects the length of time that the current monitoring record has not been used. If it has not been used for a long time recently, it means that the monitoring record is invalid and should be removed to ease data storage pressure and improve data processing efficiency;

[0032] Get the effective value of each historical monitoring record in the a-th monitoring record set, calculate the average value to get the effective value Z of the a-th new historical monitoring record corresponding to the a-th monitoring record set a ;

[0033] By calculating the effective value of each monitoring record, the access frequency and subsequent access possibility of each monitoring record can be reflected to a certain extent; sorting the access order of each monitoring record by effective value can help users access the target monitoring record as quickly as possible when they access the monitoring data next time.

[0034] Further, the abnormal record analysis module includes an abnormal record capturing unit, a reference data acquiring unit and an access sequence adjusting unit;

[0035] The abnormal record capture unit is used to extract the environmental feature sets of two adjacent historical monitoring records respectively, and if the two sets of environmental feature sets are the same, obtain the temperature difference at each time point in the two historical monitoring records; select the time point of one of the historical monitoring records as the reference time point, and obtain the temperature difference degree at each time point of the two historical monitoring records; set a temperature difference degree threshold, count the number of time points at which the temperature difference degree is lower than the temperature difference degree threshold, and obtain the proportion of the number of time points at which the temperature difference degree is lower than the temperature difference degree threshold; if the proportion of the number of time points is higher than the set proportion threshold, set the previous historical monitoring record of the two adjacent historical monitoring records as an abnormal monitoring record;

[0036] The reference data acquisition unit is used to analyze the access time from the abnormal monitoring record to the next historical monitoring record, determine the access time threshold and the reference monitoring record for updating the abnormal monitoring record;

[0037] The access sequence adjustment unit is used to reset the access sequence of historical monitoring records and to remind the deletion of historical monitoring records with invalid data marks.

[0038] Further, the reference data acquisition unit includes:

[0039] The time interval between the abnormal monitoring record and the next historical monitoring record generation time is T ’ , comparing the environmental feature set of the abnormal monitoring record with the environmental feature set of each new historical monitoring record to obtain a number of new historical monitoring records containing the same environmental feature set;

[0040] Obtain the time points at which the temperature difference is higher than the temperature difference threshold value between the abnormal monitoring record and the next historical monitoring record, and set them as target time points; obtain the temperature of the next historical monitoring record at each target time point, and compare it with the temperature at the corresponding time point in the new historical monitoring record containing the same set of environmental features; if there is a new historical monitoring record whose temperature at the corresponding time point is the same as that of the next historical monitoring record, set the new historical monitoring record as the reference monitoring record;

[0041] Determine the position of the reference monitoring record in the access sequence of all new historical monitoring records as W, and calculate the average duration of a user accessing a new historical monitoring record as

[0042] The total number of new historical monitoring records obtained is N new , the access time threshold of abnormal monitoring records accessing reference monitoring records is calculated as

[0043] Furthermore, the real-time recording and analysis module includes a real-time data analysis unit and an abnormal data processing unit;

[0044] The real-time record analysis module is used to obtain the currently generated real-time monitoring record. If the real-time monitoring record contains abnormal data, the historical monitoring record is accessed and compared through the environmental information contained in the real-time monitoring record to obtain the reference monitoring record corresponding to the real-time monitoring record, and the real-time monitoring record is updated; if the access time to the historical monitoring record exceeds the access time threshold, the real-time monitoring record is monitored again.

[0045] The real-time data analysis unit is used to obtain the currently generated real-time monitoring record, and the average temperature of the real-time monitoring record is obtained as follows: Extract the environmental feature set of the real-time monitoring record, access each new historical monitoring record and calculate the access time (T search ) now Perform statistics; obtain the average temperature range of the reference monitoring record of the real-time monitoring record as follows: And the environmental feature set is the same as the real-time monitoring record; if (T search ) now >(T search ) max , then an abnormal reminder is given for the real-time monitoring record;

[0046] The abnormal data processing unit is used to obtain and compare the environmental feature set of each new historical monitoring record when an abnormal reminder is issued for the real-time monitoring record, obtain a number of new historical monitoring records with the same environmental feature set as the real-time monitoring record, and set them as target monitoring records; obtain the average temperature of each target monitoring record, and calculate the degree of temperature difference between the real-time monitoring record and each target monitoring record in, is the average temperature of the x-th target monitoring record; if the temperature difference between the real-time monitoring record and the x-th target monitoring record is less than the set difference threshold, the temperature change process of the x-th target monitoring record is adjusted to the temperature change process of the real-time monitoring record; if the temperature difference between the real-time monitoring record and the x-th target monitoring record is greater than the set difference threshold, a secondary monitoring reminder is performed on the real-time monitoring record.

[0047] The operating environment monitoring of bus duct plays an important role in the power system. A large amount of data will be generated during the monitoring process, including data that has been stored for a long time and is not needed. This situation will affect the efficiency of users accessing the target data. At the same time, some data abnormalities will appear during the monitoring process. Users can make repairs based on previous data, but because the amount of stored data is too large, when users process abnormal data, they need to spend a lot of time to traverse all data, which seriously affects the timeliness and efficiency of data processing.

[0048] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: (1) the present invention can alleviate the pressure of data storage and improve the efficiency of user access to target data by reasonably integrating the stored monitoring data and clearing the data that has not been used for a long time; (2) the present invention can sort the effective monitoring records by importance and store the data with a higher probability of being accessed in front, so that the user can find the target data as quickly as possible, improve the efficiency of user access to target data, and also improve the timeliness of data processing; (3) the present invention divides the stored monitoring data and repairs the abnormal data according to the same type of monitoring data; when the abnormal data is subsequently monitored in real time, the abnormal data can be automatically adjusted, the manual repair operation is abandoned, human resources are liberated, and work efficiency is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0050] Figure 1It is a structural diagram of the bus duct operation environment monitoring and early warning system based on the Internet of Things. DETAILED DESCRIPTION

[0051] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0052] See also Figure 1 , the present invention provides a technical solution: a bus duct operation environment monitoring and early warning system based on the Internet of Things, the monitoring and early warning system includes a monitoring record integration module, an access sequence analysis module, an abnormal record capture module and a real-time record analysis module;

[0053] The monitoring record integration module is used to generate a historical monitoring record for the data generated during each historical monitoring process of the bus duct, obtain the environmental information contained in each historical monitoring record, and classify each historical monitoring record; and integrate the information of the historical monitoring records that are in the same category after classification;

[0054] The access sequence analysis module is used to record the user's historical access to each historical monitoring record, analyze the user's access to each historical monitoring record, obtain the valid value of each historical monitoring record, and determine whether to mark the historical monitoring record as invalid data; set the access sequence for the historical monitoring record that does not have an invalid data mark;

[0055] The abnormal record analysis module is used to obtain the access footprints of any two adjacent historical monitoring records and capture the abnormal monitoring records with abnormal data; if there is a monitoring record update behavior in the access footprint of the abnormal monitoring record, analyze the access time from the abnormal monitoring record to the next historical monitoring record, determine the access time threshold and the reference monitoring record for updating the abnormal monitoring record; reset the access order of the historical monitoring records, and delete the historical monitoring records with invalid data marks;

[0056] The real-time record analysis module is used to obtain the real-time monitoring record currently generated. If the real-time monitoring record contains abnormal data, the historical monitoring record is accessed and compared through the environmental information contained in the real-time monitoring record to obtain the reference monitoring record corresponding to the real-time monitoring record, and the real-time monitoring record is updated; if the access time to the historical monitoring record exceeds the access time threshold, a secondary monitoring reminder is performed on the real-time monitoring record.

[0057] Among them, the monitoring record integration module includes a monitoring record division unit and a record data integration unit;

[0058] The monitoring record classification unit is used to obtain environmental information in each historical monitoring record, perform feature extraction on the environmental information, obtain a number of environmental features, and generate an environmental feature set; classify all historical monitoring records according to the environmental feature set;

[0059] The monitoring record division unit is used to obtain the environmental information contained in any historical monitoring record, perform feature extraction on the environmental information, and generate an environmental feature set of the historical monitoring record; extract the environmental feature sets of any two historical monitoring records respectively, extract an environmental feature from one set of environmental feature sets, and compare it with any environmental feature in the other set of environmental feature sets; if the two compared environmental features are the same, set the two environmental features as common environmental features; perform quantitative statistics on the common environmental features between the two sets of environmental feature sets, and obtain the number of environmental features in the two sets of environmental feature sets respectively; if the number of common environmental features is equal to the number of environmental features in the two sets of environmental feature sets, the two historical monitoring records are divided into the same category to generate a monitoring record set;

[0060] The record data integration unit is used to arbitrarily select a set of monitoring record sets, obtain the change in the temperature of the bus duct in each historical monitoring record in a unit cycle, analyze the degree of difference between any two historical monitoring records, and integrate several historical monitoring records in the monitoring record set by comparing the degree of difference with a set difference threshold.

[0061] The recording data integration unit includes:

[0062] Get a set of monitoring records at random, get the temperature change of the bus duct in a unit period in the i-th historical monitoring record in the monitoring record set, divide the unit period into several time points, get the temperature at any time point, and get the average temperature of the i-th historical monitoring record as (T ave ) i , set the highest temperature of the i-th historical monitoring record to (T max ) i and the minimum temperature is (T min ) i , the fluctuation range of the i-th historical monitoring record is

[0063] F i =[(T max ) i -(T min ) i ] / (Tave ) i ;

[0064] For example, if a unit cycle is set to 60 minutes, it is evenly divided into 60 time points. The average temperature in 60 minutes is 30°C. The highest temperature detected is 40°C and the lowest temperature is 20°C. The fluctuation range is calculated to be (40-20) / 30=66.7%.

[0065] Obtain the fluctuation range of each historical monitoring record in the monitoring record set, sort the fluctuation ranges from large to small according to the values, and select a fluctuation range according to the sorted order, obtain the number of historical monitoring records with values ​​less than the fluctuation range as N, and obtain the proportion of the number of records less than the fluctuation range as α=N / N m , where N m is the number of historical monitoring records in the monitoring record set; set the number ratio threshold α max , if α<α max , then select the next fluctuation range difference from the sorted order and recalculate until α>α is satisfied max Until; it will satisfy α>α max The fluctuation range is taken as the maximum allowable fluctuation range F of each historical monitoring record in the monitoring record set max ;

[0066] If the fluctuation range of the i-th historical monitoring record is F i >F max , then get the average temperature (T ave ) i , the normal temperature range of the i-th historical monitoring record is T i =((T ave ) i ×(1-F max ),(T ave ) i ×(1+F max )); if there is a temperature at a certain time point in a certain historical monitoring record that is not within the normal temperature range, then the certain historical monitoring record is removed from the monitoring record set; after obtaining and removing several historical monitoring records, the average value of the j-th time point of all historical monitoring records in the monitoring record set is calculated to obtain the average temperature at the j-th time point: Obtaining the average temperature at each time point as the temperature change process of the monitoring record set;

[0067] The removed historical monitoring records are merged to generate a new monitoring record set, the temperature fluctuation range of the historical monitoring records in the new monitoring record set is recalculated, and the historical monitoring records are re-divided into a number of monitoring record sets to obtain the temperature change process of each monitoring record set;

[0068] Each monitoring record set is presented in the form of a new historical monitoring record, and the temperature change process of the monitoring record set is the temperature change process of the corresponding new historical monitoring record.

[0069] Wherein, the access sequence analysis module includes an effective value calculation unit and an access sequence setting unit;

[0070] The effective value calculation unit is used to obtain the number of times a user visits a certain historical monitoring record through the user's access footprint; obtain the number of times the remaining historical monitoring records in the monitoring record set where the certain historical monitoring record is located; analyze the record generation time interval between any two adjacent historical monitoring records in the monitoring record set, and calculate the effective value of the monitoring record set where the certain historical monitoring record is located; and mark invalid data for new historical monitoring records corresponding to some monitoring record sets;

[0071] The access sequence setting unit is used to sort the valid values ​​from large to small to generate an access sequence for the user to subsequently access each new historical monitoring record.

[0072] The effective value calculation unit includes:

[0073] Set the number of times a user accesses the i-th historical monitoring record to P i ; Get the monitoring record set where the i-th historical monitoring record is located, set the monitoring record set where it is located as the a-th monitoring record set, count the number of visits to each historical monitoring record in the a-th monitoring record set, and get the total number of visits to the a-th monitoring record set by the user as Q a ; Get the time interval between each user's access to the i-th historical monitoring record and the current time point; select the access time with the shortest time interval, and set the shortest access time to (Δt min ) i ;

[0074] Get the record generation time interval of any two adjacent historical monitoring records in the a-th monitoring record set, sort them according to the record generation time, select the record generation time interval with the largest value, and set it as the access time threshold (Δt max ) a ; According to the formula:

[0075]

[0076] Among them, IF() is a judgment function. If (Δt min ) i <(Δt max ) a , then IF((Δt min ) i ≤(Δt max ) a )=1, otherwise, IF((Δt min ) i ≤(Δt max ) a =0; calculate the effective value Z of the i-th historical monitoring record i ;

[0077] For example, if the shortest access time to each historical monitoring record in the monitoring record set where the first historical monitoring record is located is 24 hours, but in the monitoring record set, the maximum record generation time interval between two adjacent historical monitoring records is 12 hours, because 24 hours>12 hours, we get IF((Δt min ) i ≤(Δt max ) a =0, so no matter how many times the history accesses the first historical monitoring record, the effective value of the first historical monitoring record is 0;

[0078] Get the effective value of each historical monitoring record in the a-th monitoring record set, calculate the average value to get the effective value Z of the a-th new historical monitoring record corresponding to the a-th monitoring record set a .

[0079] Among them, the abnormal record analysis module includes an abnormal record capture unit, a reference data acquisition unit and an access sequence adjustment unit;

[0080] The abnormal record capture unit is used to extract the environmental feature sets of two adjacent historical monitoring records respectively, and if the two sets of environmental feature sets are the same, obtain the temperature difference at each time point in the two historical monitoring records; select the time point of one of the historical monitoring records as the reference time point, and obtain the temperature difference degree at each time point of the two historical monitoring records; set a temperature difference degree threshold, count the number of time points at which the temperature difference degree is lower than the temperature difference degree threshold, and obtain the proportion of the number of time points at which the temperature difference degree is lower than the temperature difference degree threshold; if the proportion of the number of time points is higher than the set proportion threshold, set the previous historical monitoring record of the two adjacent historical monitoring records as an abnormal monitoring record;

[0081] The reference data acquisition unit is used to analyze the access time from the abnormal monitoring record to the next historical monitoring record, determine the access time threshold and the reference monitoring record for updating the abnormal monitoring record;

[0082] The access sequence adjustment unit is used to reset the access sequence of historical monitoring records and to remind the deletion of historical monitoring records with invalid data marks.

[0083] Wherein, the reference data acquisition unit includes:

[0084] The time interval between the abnormal monitoring record and the next historical monitoring record generation time is T ’ , comparing the environmental feature set of the abnormal monitoring record with the environmental feature set of each new historical monitoring record to obtain a number of new historical monitoring records containing the same environmental feature set;

[0085] Obtain the time points at which the temperature difference is higher than the temperature difference threshold value between the abnormal monitoring record and the next historical monitoring record, and set them as target time points; obtain the temperature of the next historical monitoring record at each target time point, and compare it with the temperature at the corresponding time point in the new historical monitoring record containing the same set of environmental features; if there is a new historical monitoring record whose temperature at the corresponding time point is the same as that of the next historical monitoring record, set the new historical monitoring record as the reference monitoring record;

[0086] Determine the position of the reference monitoring record in the access sequence of all new historical monitoring records as W, and calculate the average duration of a user accessing a new historical monitoring record as

[0087] The total number of new historical monitoring records obtained is N new , the access time threshold of abnormal monitoring records accessing reference monitoring records is calculated as

[0088] Among them, the real-time record analysis module includes a real-time data analysis unit and an abnormal data processing unit;

[0089] The real-time record analysis module is used to obtain the currently generated real-time monitoring record. If the real-time monitoring record contains abnormal data, the historical monitoring record is accessed and compared through the environmental information contained in the real-time monitoring record to obtain the reference monitoring record corresponding to the real-time monitoring record, and the real-time monitoring record is updated; if the access time to the historical monitoring record exceeds the access time threshold, the real-time monitoring record is monitored again.

[0090] The real-time data analysis unit is used to obtain the currently generated real-time monitoring record, and the average temperature of the real-time monitoring record is obtained as follows: Extract the environmental feature set of the real-time monitoring record, access each new historical monitoring record and calculate the access time (T search ) now Perform statistics; obtain the average temperature range of the reference monitoring record of the real-time monitoring record as follows: And the environmental feature set is the same as the real-time monitoring record; if (T search ) now >(T search ) max , then an abnormal reminder is given for the real-time monitoring record;

[0091] The abnormal data processing unit is used to obtain and compare the environmental feature set of each new historical monitoring record when an abnormal reminder is issued for the real-time monitoring record, obtain a number of new historical monitoring records with the same environmental feature set as the real-time monitoring record, and set them as target monitoring records; obtain the average temperature of each target monitoring record, and calculate the degree of temperature difference between the real-time monitoring record and each target monitoring record in, is the average temperature of the x-th target monitoring record; if the temperature difference between the real-time monitoring record and the x-th target monitoring record is less than the set difference threshold, the temperature change process of the x-th target monitoring record is adjusted to the temperature change process of the real-time monitoring record; if the temperature difference between the real-time monitoring record and the x-th target monitoring record is greater than the set difference threshold, a secondary monitoring reminder is performed on the real-time monitoring record.

[0092] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0093] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. The bus duct operation environment monitoring and early warning system based on the Internet of Things is characterized by: The monitoring and early warning system includes a monitoring record integration module, an access sequence analysis module, an abnormal record capture module and a real-time record analysis module; The monitoring record integration module is used to generate a historical monitoring record for the data generated during each historical monitoring process of the bus duct, obtain the environmental information contained in each historical monitoring record, and classify each historical monitoring record; and integrate the information of the historical monitoring records that are in the same category after classification; The access sequence analysis module is used to record the user's historical access to each historical monitoring record, analyze the user's access to each historical monitoring record, obtain the valid value of each historical monitoring record, and determine whether to mark the historical monitoring record as invalid data; Setting the access order for historical monitoring records that do not contain invalid data marks; The abnormal record analysis module is used to obtain the access footprints of any two adjacent historical monitoring records and capture the abnormal monitoring records with abnormal data; if there is a monitoring record update behavior in the access footprint of the abnormal monitoring record, analyze the access time from the abnormal monitoring record to the next historical monitoring record, determine the access time threshold and the reference monitoring record for updating the abnormal monitoring record; reset the access order of the historical monitoring records, and delete the historical monitoring records with invalid data marks; The real-time record analysis module is used to obtain the real-time monitoring record currently generated. If the real-time monitoring record contains abnormal data, the historical monitoring record is accessed and compared through the environmental information contained in the real-time monitoring record to obtain the reference monitoring record corresponding to the real-time monitoring record, and the real-time monitoring record is updated; if the access time to the historical monitoring record exceeds the access time threshold, a secondary monitoring reminder is performed on the real-time monitoring record.

2. The bus duct operation environment monitoring and early warning system based on the Internet of Things according to claim 1 is characterized in that: The monitoring record integration module includes a monitoring record division unit and a record data integration unit; The monitoring record classification unit is used to obtain the environmental information in each historical monitoring record, perform feature extraction on the environmental information, obtain a number of environmental features, and generate an environmental feature set; classify all historical monitoring records according to the environmental feature set; The monitoring record division unit is used to obtain the environmental information contained in any historical monitoring record, perform feature extraction on the environmental information, and generate an environmental feature set of the historical monitoring record; extract the environmental feature sets of any two historical monitoring records respectively, extract an environmental feature from one set of environmental feature sets, and compare it with any environmental feature in the other set of environmental feature sets; if the two compared environmental features are the same, set the two environmental features as common environmental features; perform quantitative statistics on the common environmental features between the two sets of environmental feature sets, and obtain the number of environmental features in the two sets of environmental feature sets respectively; if the number of common environmental features is equal to the number of environmental features in the two sets of environmental feature sets, the two historical monitoring records are divided into the same category to generate a monitoring record set; The record data integration unit is used to arbitrarily select a set of monitoring record sets, obtain the change in the temperature of the bus duct in each historical monitoring record in a unit cycle, analyze the degree of difference between any two historical monitoring records, and integrate several historical monitoring records in the monitoring record set by comparing the degree of difference with a set difference threshold.

3. The bus duct operation environment monitoring and early warning system based on the Internet of Things according to claim 2 is characterized in that: The record data integration unit comprises: Get a set of monitoring records at random, get the temperature change of the bus duct in a unit period in the i-th historical monitoring record in the monitoring record set, divide the unit period into several time points, get the temperature at any time point, and get the average temperature of the i-th historical monitoring record as (T ave ) i , set the highest temperature of the i-th historical monitoring record to (T max ) i and the minimum temperature is (T min ) i , the fluctuation range of the i-th historical monitoring record is F i =[(T max ) i -(T min ) i ] / (T ave ) i ; Obtain the fluctuation range of each historical monitoring record in the monitoring record set, sort the fluctuation ranges from large to small according to the values, and select a fluctuation range according to the sorted order, obtain the number of historical monitoring records with values ​​less than the fluctuation range as N, and obtain the proportion of the number of records less than the fluctuation range as α=N / N m , where N m is the number of historical monitoring records in the monitoring record set; set the number ratio threshold α max , if α<α max , then select the next fluctuation range difference from the sorted order and recalculate until α>α is satisfied max Until; it will satisfy α>α max The fluctuation range is taken as the maximum allowable fluctuation range F of each historical monitoring record in the monitoring record set max ; If the fluctuation range of the i-th historical monitoring record is F i >F max , then get the average temperature (T ave ) i , the normal temperature range of the i-th historical monitoring record is T i =((T ave ) i ×(1-F max ),(T ave ) i × (1+F max )); if there is a temperature at a certain time point in a certain historical monitoring record that is not within the normal temperature range, then the certain historical monitoring record is removed from the monitoring record set; after obtaining and removing several historical monitoring records, the average value of the j-th time point of all historical monitoring records in the monitoring record set is calculated to obtain the average temperature at the j-th time point: Obtaining the average temperature at each time point as the temperature change process of the monitoring record set; The removed historical monitoring records are merged to generate a new monitoring record set, the temperature fluctuation range of the historical monitoring records in the new monitoring record set is recalculated, and the historical monitoring records are re-divided into a number of monitoring record sets to obtain the temperature change process of each monitoring record set; Each monitoring record set is presented in the form of a new historical monitoring record, and the temperature change process of the monitoring record set is the temperature change process of the corresponding new historical monitoring record.

4. The bus duct operation environment monitoring and early warning system based on the Internet of Things according to claim 3 is characterized in that: The access sequence analysis module includes a valid value calculation unit and an access sequence setting unit; The effective value calculation unit is used to obtain the number of times a user visits a certain historical monitoring record through the user's access footprint; obtain the number of times the remaining historical monitoring records in the monitoring record set where the certain historical monitoring record is located; analyze the record generation time interval between any two adjacent historical monitoring records in the monitoring record set, and calculate the effective value of the monitoring record set where the certain historical monitoring record is located; and mark invalid data for new historical monitoring records corresponding to some monitoring record sets; The access sequence setting unit is used to sort the valid values ​​from large to small to generate an access sequence for the user to subsequently access each new historical monitoring record.

5. The bus duct operation environment monitoring and early warning system based on the Internet of Things according to claim 4 is characterized in that: The effective value calculation unit comprises: Set the number of times a user accesses the i-th historical monitoring record to P i ; Get the monitoring record set where the i-th historical monitoring record is located, set the monitoring record set where it is located as the a-th monitoring record set, count the number of visits to each historical monitoring record in the a-th monitoring record set, and get the total number of visits to the a-th monitoring record set by the user as Q a ; Get the time interval between the user's access time and the current time point each time he accesses the i-th historical monitoring record; select the access time with the shortest time interval, and set the shortest access time to (Δt min ) i ; Get the record generation time interval of any two adjacent historical monitoring records in the a-th monitoring record set, sort them according to the record generation time, select the record generation time interval with the largest value, and set it as the access time threshold (Δt max ) a ; According to the formula: Among them, IF() is a judgment function. If (Δt min ) i <(Δt max ) a , then IF((Δt min ) i ≤(Δt max ) a )=1, otherwise, IF((Δt min ) i ≤(Δt max ) a =0; calculate the effective value Z of the i-th historical monitoring record i ; Get the effective value of each historical monitoring record in the a-th monitoring record set, calculate the average value to get the effective value Z of the a-th new historical monitoring record corresponding to the a-th monitoring record set a .

6. The bus duct operation environment monitoring and early warning system based on the Internet of Things according to claim 5 is characterized in that: The abnormal record analysis module includes an abnormal record capturing unit, a reference data acquiring unit and an access sequence adjusting unit; The abnormal record capturing unit is used to extract the environmental feature sets of two adjacent historical monitoring records respectively, and if the two sets of environmental feature sets are the same, obtain the temperature difference at each time point in the two historical monitoring records; Select the time point of one of the historical monitoring records as the reference time point, and obtain the temperature difference degree at each time point of the two historical monitoring records; set a temperature difference degree threshold, count the number of time points at which the temperature difference degree is lower than the temperature difference degree threshold, and obtain the proportion of the number of time points at which the temperature difference degree is lower than the temperature difference degree threshold; if the proportion of the number of time points is higher than the set proportion threshold, set the previous historical monitoring record of the two adjacent historical monitoring records as an abnormal monitoring record; The reference data acquisition unit is used to analyze the access time from the abnormal monitoring record to the next historical monitoring record, determine the access time threshold and the reference monitoring record for updating the abnormal monitoring record; The access sequence adjustment unit is used to reset the access sequence of historical monitoring records and to remind the deletion of historical monitoring records with invalid data marks.

7. The bus duct operation environment monitoring and early warning system based on the Internet of Things according to claim 6 is characterized in that: The reference data acquisition unit comprises: The time interval between the abnormal monitoring record and the generation time of the next historical monitoring record is T. ’ , comparing the environmental feature set of the abnormal monitoring record with the environmental feature set of each new historical monitoring record to obtain a number of new historical monitoring records containing the same environmental feature set; Obtain the time points at which the temperature difference is higher than the temperature difference threshold value between the abnormal monitoring record and the next historical monitoring record, and set them as target time points; obtain the temperature of the next historical monitoring record at each target time point, and compare it with the temperature at the corresponding time point in the new historical monitoring record containing the same set of environmental features; if there is a new historical monitoring record whose temperature at the corresponding time point is the same as that of the next historical monitoring record, set the new historical monitoring record as the reference monitoring record; Determine the position of the reference monitoring record in the access sequence of all new historical monitoring records as W, and calculate the average duration of a user accessing a new historical monitoring record as The total number of new historical monitoring records obtained is N new , the access time threshold of abnormal monitoring records accessing reference monitoring records is calculated as 8. The bus duct operation environment monitoring and early warning system based on the Internet of Things according to claim 7 is characterized in that: The real-time record analysis module includes a real-time data analysis unit and an abnormal data processing unit; The real-time record analysis module is used to obtain the currently generated real-time monitoring record. If the real-time monitoring record contains abnormal data, the historical monitoring record is accessed and compared through the environmental information contained in the real-time monitoring record to obtain the reference monitoring record corresponding to the real-time monitoring record, and the real-time monitoring record is updated; if the access time to the historical monitoring record exceeds the access time threshold, the real-time monitoring record is monitored again. The real-time data analysis unit is used to obtain the currently generated real-time monitoring record, and the average temperature of the real-time monitoring record is obtained as follows: Extract the environmental feature set of the real-time monitoring record, access each new historical monitoring record and calculate the access time (T search ) now Perform statistics; obtain the average temperature range of the reference monitoring record of the real-time monitoring record as follows: And the environmental feature set is the same as the real-time monitoring record; if (T search ) now >(T search ) max , then an abnormal reminder is given for the real-time monitoring record; The abnormal data processing unit is used to obtain and compare the environmental feature set of each new historical monitoring record when an abnormal reminder is issued for the real-time monitoring record, obtain a number of new historical monitoring records with the same environmental feature set as the real-time monitoring record, and set them as target monitoring records; obtain the average temperature of each target monitoring record, and calculate the degree of temperature difference between the real-time monitoring record and each target monitoring record in, is the average temperature of the x-th target monitoring record; if the temperature difference between the real-time monitoring record and the x-th target monitoring record is less than the set difference threshold, the temperature change process of the x-th target monitoring record is adjusted to the temperature change process of the real-time monitoring record; if the temperature difference between the real-time monitoring record and the x-th target monitoring record is greater than the set difference threshold, a secondary monitoring reminder is performed on the real-time monitoring record.

Images