A project equipment supply chain evaluation system and method based on big data

Abstract

The present invention discloses a project equipment supply chain evaluation system and method based on big data, which belongs to the field of abnormal positioning technology. The present invention analyzes all process data, classifies the supply process of project equipment to obtain different supply links; searches for process data reflecting the supply status of project equipment, calculates the searched process data, and uses the supply links to build a project equipment supply chain; searches for characteristic data of equipment abnormalities after analyzing the equipment data, and calculates the abnormal threshold; uses the calculated abnormal threshold to determine whether there is an abnormal risk in real-time project equipment and issue an early warning; calculates the correlation between process data and characteristic data, and constructs an abnormal inversion screening model; inverts the abnormalities of real-time early warnings, determines the supply chain link that causes the equipment to have an abnormal risk, marks it as a problem link, and transmits the problem link information to the project responsible person for problem elimination.

Description

Technical Field

[0001] The present invention relates to the field of anomaly location technology, and in particular to a project equipment supply chain evaluation system and method based on big data. Background Art

[0002] In many companies and enterprises, it is necessary to purchase project equipment. When science and technology were relatively backward, the purchase and supply of project equipment were mostly calculated and reviewed by manpower. With the development of science and technology and the advent of the digital age, the supervision and analysis of the project equipment supply process in enterprises no longer rely on manpower. Computers collect a large amount of data from various supply chain links (such as procurement, inventory, transportation, etc.) and integrate these data into a platform through data integration tools. Use statistical analysis, machine learning and artificial intelligence technology to analyze the data and identify patterns, trends and potential problems in the supply chain. These technologies can clearly complete the monitoring of the project equipment supply chain and are more accurate than manpower. However, when the computer investigates and detects the abnormality of the project equipment, it is impossible to investigate the supply chain process divided by human subjective consciousness. When the cause of the abnormality of the project equipment is in the supply chain, only manual labor can trace the supply process step by step to find the problem link. And due to manual reasons, the error in finding the problem link is large, which undoubtedly greatly increases the stability of the project equipment supply chain and has a huge impact on the normal work of the enterprise. Summary of the invention

[0003] The purpose of the present invention is to provide a project equipment supply chain evaluation system and method based on big data to solve the problems raised in the above background technology.

[0004] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0005] A project equipment supply chain evaluation method based on big data, the method comprising the following steps:

[0006] S100, collecting the process data of the project equipment supply in history, analyzing all the process data, and classifying the project equipment supply process into different supply links;

[0007] Furthermore, the specific steps of classifying the supply process of project equipment into different supply links are as follows:

[0008] S101, collect the process data of the project equipment supply in history, and extract the equipment data of the project equipment in the supply process. , It represents the 1st, 2nd, 3rd, ..., nth equipment data of the extracted project equipment in the supply process, where n is a positive integer; a curve graph is drawn using each equipment data, and the curve graphs of the n equipment data are observed, and the maximum and minimum values ​​of each equipment data are screened out to calculate the maximum amplitude of each equipment data. The formula is:

[0009] ;

[0010] In the formula, Am represents the maximum amplitude of each device data. Indicates the maximum value of each device data. Indicates the minimum value of each equipment data; obtains the maximum amplitude of each equipment data through calculation; selects the equipment data type corresponding to the maximum value among the maximum amplitudes of n types of equipment data as the effective data for distinguishing the project equipment supply process;

[0011] S102, calculating the difference between two adjacent valid data in the valid data curve, and using the difference to calculate the threshold for process classification, the formula is:

[0012] ;

[0013] In the formula, FY represents the threshold used to classify the equipment supply process of the project, and represents two adjacent data in the effective data curve, m-1 represents the number of adjacent effective data differences calculated, Represents the standard deviation of m-1 adjacent valid data differences;

[0014] S103, using the calculated threshold for classifying the project equipment supply process to judge the difference between each adjacent valid data, when When the supply process of the project equipment is judged to have changed, The supply process corresponding to the valid data on both sides is divided into different links; When it is determined that the supply process of the project equipment has not changed, The supply process corresponding to the valid data on both sides is divided into the same link; the difference between the calculated m-1 adjacent valid data is judged, and finally the supply process of the project equipment is divided into G links, specifically: , It represents the 1st, 2nd, 3rd, ..., Gth link in the supply of project equipment, where G is a positive integer.

[0015] By using historical data to classify the process of project equipment supply, instead of using human subjective consciousness to classify the supply process, and using the classification results of data to analyze the supply of project equipment, it can avoid inaccurate classification caused by human subjective errors, increase the workload of the system, and greatly increase work efficiency.

[0016] S200, screening the data of the project equipment supply process, searching for process data reflecting the project equipment supply status, calculating the searched process data, and building the project equipment supply chain using the supply link;

[0017] Furthermore, the specific steps of building a project equipment supply chain using the supply link are:

[0018] S201. Collect all data of each link in the historical project equipment supply process. Suppose the data in each link is , Indicates the 1st, 2nd, 3rd, ..., jth type of data in each link, where j is a positive integer; compare the data in each link to select the data types that exist in each link;

[0019] S202: Assume that the data types existing in each link are common data, and the types of common data screened are , Indicates the 1st, 2nd, 3rd, ..., kth type of data that exists in each stage of screening, where k is a positive integer. ; Extract each general data value of the project equipment when it is in use and the general data value at the initial supply, and calculate the general data difference of the project equipment after the supply is completed. The formula is:

[0020] ;

[0021] In the formula, Indicates the difference between the initial supply and the final supply of each common data in the calculated project equipment. Indicates the value of each common data of the project equipment after supply, Indicates the value of each common data of the project equipment at the beginning of supply; calculates the difference between each common data at the beginning and after supply, and obtains the difference of k common equipment;

[0022] S203, judge the difference sign of each common data, and use the difference sign to sort the supply links of the project equipment. When the corresponding type of common data value in each link is extracted, the supply links of the project equipment are sorted in ascending order according to the common data; when When extracting the common data values ​​of the corresponding types in each link, the supply links of the project equipment are sorted in descending order according to the common data;

[0023] S204, sorting the supply link sequence of the project equipment according to the sign of each general data difference in turn, when selecting the difference sign of a general equipment to sort the supply link sequence of the project equipment, judging each general data value and the difference sign after sorting, when the size sequence and the difference sign of the general data after sorting do not match, judging the corresponding general data as suspicious data; when the size sequence and the difference sign of the general data after sorting match, judging the corresponding general data as credible data;

[0024] Sort each common data by symbol and judge the remaining common data. After k sortings, the number of credible data judged in each sorting is , It indicates the number of credible data obtained when judging the 1st, 2nd, 3rd, ..., pth sorting, where p is a positive integer; the sorting result with the most credible data is selected as the final project equipment supply chain, and the corresponding general data type selected during the sorting is used as the process data RL for project equipment supply.

[0025] By analyzing the data of the classified links, we can find the common general data and use the general data to build the supply chain of the project equipment. The generated supply chain may not be the same as the supply stage in common sense. The accurate supply chain is beneficial to reduce the scope of troubleshooting and the span of the problem links when the project equipment is abnormal, so as to reduce the maintenance difficulty of the maintenance personnel and increase the work efficiency.

[0026] S300, collecting equipment data of abnormalities that occurred during the operation of project equipment in history, analyzing the equipment data to find feature data of equipment abnormalities, and calculating an abnormality threshold based on the feature data of equipment abnormalities that occurred in history;

[0027] Furthermore, the specific steps of calculating the abnormality threshold according to the characteristic data of the abnormality of the device in history are as follows:

[0028] S301. Collect the equipment data when the project equipment has abnormality in history, extract the data value of each equipment before and after the project equipment has abnormality, and calculate the change amount of each equipment data after the project equipment has abnormality. The formula is:

[0029] ;

[0030] In the formula, Indicates the calculated change in each device data after an abnormality occurs in the project equipment. Indicates the value of each device data before the abnormality of the project device occurs. Indicates the value of each device data after the project equipment has an abnormality; judges the change amount of all device data after the project equipment has an abnormality, and selects the device data type corresponding to the maximum change amount as the characteristic data of the project equipment abnormality;

[0031] S302, collect the characteristic data of the project equipment when abnormality occurs in the history , It represents the characteristic data collected when the project equipment is abnormal for the 1st, 2nd, 3rd, ..., bth time in history, where b is a positive integer. The abnormal threshold of the project equipment is calculated using the characteristic data collected when the project equipment is abnormal in history, and the formula is:

[0032] ;

[0033] In the formula, represents the calculated abnormal threshold of the project equipment, Ft represents the characteristic data collected in the history, b represents the number of characteristic data collected, Represents the standard deviation of the collected feature data.

[0034] S400, collecting feature data of project equipment in real time when it is working, using the calculated abnormal threshold to judge the real-time feature data, whether there is an abnormal risk of the real-time project equipment and issue an early warning;

[0035] Furthermore, the specific steps of using the calculated abnormal threshold to judge the real-time feature data are as follows:

[0036] S401, extract the characteristic data of the project equipment in real time , represents the feature data of the 1st, 2nd, 3rd, ..., dth project equipment extracted in real time, where d is a positive integer; the real-time feature data is judged using the abnormal threshold. When the project equipment is judged to have abnormal risks, an early warning is issued; When the project equipment is judged to have no abnormal risks, work can continue.

[0037] S500, after the risk warning is issued for the real-time project equipment, the correlation between the process data and the characteristic data is calculated, and an abnormal inversion screening model is constructed;

[0038] Furthermore, the specific steps of constructing the anomaly inversion screening model are as follows:

[0039] S501. Collect the characteristic data and process data of the project equipment in the supply chain in history, use the process data as the independent variable and the characteristic data as the variable to draw a scatter plot, calculate the linear regression equation in the scatter plot, and assume that the regression equation expression of the characteristic data and process data in the scatter plot is , in which Ft represents characteristic data, RL represents process data, A represents slope, and B represents intercept;

[0040] S502. Calculate the slope and intercept values ​​in the expression using the points in the scatter plot. The formula is:

[0041] ;

[0042] ;

[0043] In the formula, Ft represents the value of the variable characteristic data of each point in the three-point diagram, and RL represents the value of the independent variable process data of each point in the scatter plot. represents the average value of the variable in T points of the scatter plot, It represents the average value of the independent variable in T points in the scatter plot, and T represents the number of points in the scatter plot. After calculating the slope and intercept in the regression curve equation in the scatter plot, the correlation expression between the process data and the characteristic data is obtained as the regression curve equation in the scatter plot.

[0044] S503. Using the calculated correlation expression of the process data and the characteristic data, an inversion screening model for the project equipment is constructed.

[0045] S600. Use the constructed anomaly inversion screening model to invert the anomalies of real-time warnings, determine the supply chain links that cause abnormal risks of equipment, mark them as problem links, and transmit the problem link information to the project manager for problem troubleshooting.

[0046] Furthermore, the specific steps of using the constructed anomaly inversion screening model to invert the anomaly of real-time warning are as follows:

[0047] S601. When it is determined that the project equipment has abnormal risk and an early warning is issued, the characteristic data of the early warning project equipment is extracted as Ft_y; the supply link that causes the abnormal risk of the project equipment is located using the inverse screening model, and the formula is:

[0048] ;

[0049] In the formula, RL represents the project equipment process data with abnormal risks;

[0050] S602, after calculating the process data of the project equipment with abnormal risks, use Calculate the difference between the process data in each supply link of the project equipment, and select the link corresponding to the process data with the smallest difference as the problem link of the project equipment with abnormal risk; send the data of the problem link to the project person in charge to eliminate supply chain anomalies.

[0051] By using the calculated correlation expression between process data and characteristic data, the corresponding process data is calculated by determining the characteristic data of the warning project equipment, and the problematic links are found out through comparison, so the problems can be accurately eliminated, the maintenance time of maintenance personnel can be reduced, and work efficiency can be improved.

[0052] A project equipment supply chain evaluation system based on big data, the project equipment supply chain evaluation system includes a data collection module, a link classification module, a supply chain construction module, an abnormality judgment module, a model construction module and a link positioning module;

[0053] The data collection module is used to collect supply data, equipment data and abnormal data of historical project equipment;

[0054] The link classification module is used to classify the project equipment supply process using historical data and determine the specific supply links;

[0055] The supply chain construction module is used to analyze the data in the project equipment supply link, find the process data reflecting the project equipment supply, and build the project equipment supply chain;

[0056] The abnormality judgment module is used to find characteristic data reflecting abnormalities of project equipment according to historical data, calculate the abnormality threshold of the project equipment according to the characteristic data, and use the abnormality threshold to judge whether there is abnormal risk of real-time project equipment;

[0057] The model building module uses the characteristic data and process data in the history to build a scatter plot, calculates and analyzes the three-point plot to obtain the regression curve equation of the scatter plot, uses the regression curve equation in the scatter plot as the correlation expression of the process data and the characteristic data, and uses the expression to calculate the inversion screening model;

[0058] The link positioning module is used to, after issuing an early warning for project equipment with abnormal risks, locate the supply chain link that causes the abnormal risk of the early warning project equipment according to the inverse screening model and eliminate the problematic link.

[0059] The supply chain building modules include data analysis unit and link sorting unit;

[0060] The data analysis unit is used to search for common data in each link, calculate the difference of each common data, and sort the supply links of the project equipment using the signs of the difference;

[0061] The link sorting unit is used to analyze each sorting result after sorting the supply links of the project equipment using the difference symbol, and the best difference sorting result is the supply chain to determine the process data.

[0062] The abnormality judgment module includes a characteristic data search unit, a threshold calculation unit and a judgment unit;

[0063] The characteristic data unit is used to analyze all equipment data of abnormal project equipment in history, calculate the difference after abnormality, and find out the characteristic data reflecting the abnormality of project equipment;

[0064] The threshold value calculation unit is used to calculate the abnormal threshold value used to determine whether the real-time project equipment has an abnormal risk by using the characteristic data of the abnormal project equipment in the history;

[0065] The judgment unit is used to collect feature data of real-time project equipment, use abnormal thresholds to judge the real-time feature data of project equipment, determine whether there is an abnormal risk in the real-time project equipment, and issue an early warning.

[0066] Compared with the prior art, the beneficial effects achieved by the present invention are:

[0067] 1. The present invention collects and analyzes the data of the project equipment supply process in history, classifies the project equipment supply process, and obtains different supply links; analyzing the supply process can avoid inaccurate classification caused by human subjective errors, increase the workload of the system, and greatly increase work efficiency.

[0068] 2. The present invention constructs a new supply chain through the supply process of project equipment. When analyzing project equipment, an accurate supply chain is beneficial to reduce the scope of troubleshooting when project equipment is abnormal, reduce the span of problem links, reduce the maintenance difficulty of maintenance personnel, and increase work efficiency;

[0069] 3. The present invention uses historical data to calculate the correlation expression between process data and feature data and constructs an inversion screening model. When an early warning device appears, the correlation expression can be used to accurately locate the supply link that causes the project equipment early warning, thereby speeding up the work efficiency of maintenance personnel. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] 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:

[0071] Figure 1 It is a module distribution diagram of a project equipment supply chain evaluation system based on big data of the present invention;

[0072] Figure 2 It is a schematic diagram of the steps of a project equipment supply chain evaluation method based on big data of the present invention;

[0073] Figure 3It is an amplitude-time scatter plot of a project equipment supply chain evaluation method based on big data in the present invention. DETAILED DESCRIPTION

[0074] 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.

[0075] See also Figure 1-Figure 2 , the present invention provides a technical solution:

[0076] A project equipment supply chain evaluation method based on big data, the method comprising the following steps:

[0077] S100, collecting the process data of the project equipment supply in history, analyzing all the process data, and classifying the project equipment supply process into different supply links;

[0078] The specific steps of classifying the supply process of project equipment into different supply links are as follows:

[0079] S101, collect the process data of the project equipment supply in history, and extract the equipment data of the project equipment in the supply process. , It represents the 1st, 2nd, 3rd, ..., nth equipment data of the extracted project equipment in the supply process, where n is a positive integer; a curve graph is drawn using each equipment data, and the curve graphs of the n equipment data are observed, and the maximum and minimum values ​​of each equipment data are screened out to calculate the maximum amplitude of each equipment data. The formula is:

[0080] ;

[0081] In the formula, Am represents the maximum amplitude of each device data. Indicates the maximum value of each device data. Indicates the minimum value of each equipment data; obtains the maximum amplitude of each equipment data through calculation; selects the equipment data type corresponding to the maximum value among the maximum amplitudes of n types of equipment data as the effective data for distinguishing the project equipment supply process;

[0082] S102, calculating the difference between two adjacent valid data in the valid data curve, and using the difference to calculate the threshold for process classification, the formula is:

[0083] ;

[0084] In the formula, FY represents the threshold used to classify the equipment supply process of the project, and represents two adjacent data in the effective data curve, m-1 represents the number of adjacent effective data differences calculated, Represents the standard deviation of m-1 adjacent valid data differences;

[0085] S103, using the calculated threshold for classifying the project equipment supply process to judge the difference between each adjacent valid data, when When the supply process of the project equipment is judged to have changed, The supply process corresponding to the valid data on both sides is divided into different links; When it is determined that the supply process of the project equipment has not changed, The supply process corresponding to the valid data on both sides is divided into the same link; the difference between the calculated m-1 adjacent valid data is judged, and finally the supply process of the project equipment is divided into G links, specifically: , It represents the 1st, 2nd, 3rd, ..., Gth link in the supply of project equipment, where G is a positive integer.

[0086] By using historical data to classify the process of project equipment supply, instead of using human subjective consciousness to classify the supply process, and using the classification results of data to analyze the supply of project equipment, it can avoid inaccurate classification caused by human subjective errors, increase the workload of the system, and greatly increase work efficiency.

[0087] S200, screening the data of the project equipment supply process, searching for process data reflecting the project equipment supply status, calculating the searched process data, and building the project equipment supply chain using the supply link;

[0088] The specific steps to build a project equipment supply chain using the supply chain are:

[0089] S201. Collect all data of each link in the historical project equipment supply process. Suppose the data in each link is , Indicates the 1st, 2nd, 3rd, ..., jth type of data in each link, where j is a positive integer; compare the data in each link to select the data types that exist in each link;

[0090] S202: Assume that the data types existing in each link are common data, and the types of common data screened are , Indicates the 1st, 2nd, 3rd, ..., kth type of data that exists in each stage of screening, where k is a positive integer. ; Extract each general data value of the project equipment when it is in use and the general data value at the initial supply, and calculate the general data difference of the project equipment after the supply is completed. The formula is:

[0091] ;

[0092] In the formula, Indicates the difference between the initial supply and the final supply of each common data in the calculated project equipment. Indicates the value of each common data of the project equipment after supply, Indicates the value of each common data of the project equipment at the beginning of supply; calculates the difference between each common data at the beginning and after supply, and obtains the difference of k common equipment;

[0093] S203, judge the difference sign of each common data, and use the difference sign to sort the supply links of the project equipment. When the corresponding type of common data value in each link is extracted, the supply links of the project equipment are sorted in ascending order according to the common data; when When extracting the common data values ​​of the corresponding types in each link, the supply links of the project equipment are sorted in descending order according to the common data;

[0094] S204, sorting the supply link sequence of the project equipment according to the sign of each general data difference in turn, when selecting the difference sign of a general equipment to sort the supply link sequence of the project equipment, judging each general data value and the difference sign after sorting, when the size sequence and the difference sign of the general data after sorting do not match, judging the corresponding general data as suspicious data; when the size sequence and the difference sign of the general data after sorting match, judging the corresponding general data as credible data;

[0095] Sort each common data by symbol and judge the remaining common data. After k sortings, the number of credible data judged in each sorting is , It indicates the number of credible data obtained when judging the 1st, 2nd, 3rd, ..., pth sorting, where p is a positive integer; the sorting result with the most credible data is selected as the final project equipment supply chain, and the corresponding general data type selected during the sorting is used as the process data RL for project equipment supply.

[0096] By analyzing the data of the classified links, we can find the common general data and use the general data to build the supply chain of the project equipment. The generated supply chain may not be the same as the supply stage in common sense. The accurate supply chain is beneficial to reduce the scope of troubleshooting and the span of the problem links when the project equipment is abnormal, so as to reduce the maintenance difficulty of the maintenance personnel and increase the work efficiency.

[0097] S300, collecting equipment data of abnormalities that occurred during the operation of project equipment in history, analyzing the equipment data to find feature data of equipment abnormalities, and calculating an abnormality threshold based on the feature data of equipment abnormalities that occurred in history;

[0098] The specific steps to calculate the abnormality threshold based on the characteristic data of the device abnormality in history are:

[0099] S301. Collect the equipment data when the project equipment has abnormality in history, extract the data value of each equipment before and after the project equipment has abnormality, and calculate the change amount of each equipment data after the project equipment has abnormality. The formula is:

[0100] ;

[0101] In the formula, Indicates the calculated change in each device data after an abnormality occurs in the project equipment. Indicates the value of each device data before the abnormality of the project device occurs. Indicates the value of each device data after the project equipment has an abnormality; judges the change amount of all device data after the project equipment has an abnormality, and selects the device data type corresponding to the maximum change amount as the characteristic data of the project equipment abnormality;

[0102] S302, collect the characteristic data of the project equipment when abnormality occurs in the history , It represents the characteristic data collected when the project equipment is abnormal for the 1st, 2nd, 3rd, ..., bth time in history, where b is a positive integer. The abnormal threshold of the project equipment is calculated using the characteristic data collected when the project equipment is abnormal in history, and the formula is:

[0103] ;

[0104] In the formula, represents the calculated abnormal threshold of the project equipment, Ft represents the characteristic data collected in the history, b represents the number of characteristic data collected, Represents the standard deviation of the collected feature data.

[0105] S400, collecting feature data of project equipment in real time when it is working, using the calculated abnormal threshold to judge the real-time feature data, whether there is an abnormal risk of the real-time project equipment and issue an early warning;

[0106] The specific steps of using the calculated abnormal threshold to judge the real-time feature data are as follows:

[0107] S401, extract the characteristic data of the project equipment in real time , represents the feature data of the 1st, 2nd, 3rd, ..., dth project equipment extracted in real time, where d is a positive integer; the real-time feature data is judged using the abnormal threshold. When the project equipment is judged to have abnormal risks, an early warning is issued; When the project equipment is judged to have no abnormal risks, work can continue.

[0108] S500, after the risk warning is issued for the real-time project equipment, the correlation between the process data and the characteristic data is calculated, and an abnormal inversion screening model is constructed;

[0109] The specific steps to construct the anomaly inversion screening model are:

[0110] S501. Collect the characteristic data and process data of the project equipment in the supply chain in history, use the process data as the independent variable and the characteristic data as the variable to draw a scatter plot, calculate the linear regression equation in the scatter plot, and assume that the regression equation expression of the characteristic data and process data in the scatter plot is , in which Ft represents characteristic data, RL represents process data, A represents slope, and B represents intercept;

[0111] S502. Calculate the slope and intercept values ​​in the expression using the points in the scatter plot. The formula is:

[0112] ;

[0113] ;

[0114] In the formula, Ft represents the value of the variable characteristic data of each point in the three-point diagram, and RL represents the value of the independent variable process data of each point in the scatter plot. represents the average value of the variable in T points of the scatter plot, It represents the average value of the independent variable in T points in the scatter plot, and T represents the number of points in the scatter plot. After calculating the slope and intercept in the regression curve equation in the scatter plot, the correlation expression between the process data and the characteristic data is obtained as the regression curve equation in the scatter plot.

[0115] S503. Using the calculated correlation expression of the process data and the characteristic data, an inversion screening model for the project equipment is constructed.

[0116] S600. Use the constructed anomaly inversion screening model to invert the anomalies of real-time warnings, determine the supply chain links that cause abnormal risks of equipment, mark them as problem links, and transmit the problem link information to the project manager for problem troubleshooting.

[0117] The specific steps of using the constructed anomaly inversion screening model to invert the anomaly of real-time warning are as follows:

[0118] S601. When it is determined that the project equipment has abnormal risk and an early warning is issued, the characteristic data of the early warning project equipment is extracted as Ft_y; the supply link that causes the abnormal risk of the project equipment is located using the inverse screening model, and the formula is:

[0119] ;

[0120] In the formula, RL represents the project equipment process data with abnormal risks;

[0121] S602, after calculating the process data of the project equipment with abnormal risks, use Calculate the difference between the process data in each supply link of the project equipment, and select the link corresponding to the process data with the smallest difference as the problem link of the project equipment with abnormal risk; send the data of the problem link to the project person in charge to eliminate supply chain anomalies.

[0122] By using the calculated correlation expression between process data and characteristic data, the corresponding process data is calculated by determining the characteristic data of the warning project equipment, and the problematic links are found out through comparison, so the problems can be accurately eliminated, the maintenance time of maintenance personnel can be reduced, and work efficiency can be improved.

[0123] A project equipment supply chain evaluation system based on big data, the project equipment supply chain evaluation system includes a data collection module, a link classification module, a supply chain construction module, an abnormality judgment module, a model construction module and a link positioning module;

[0124] The data collection module is used to collect supply data, equipment data and abnormal data of historical project equipment;

[0125] The link classification module is used to classify the project equipment supply process using historical data and determine the specific supply links;

[0126] The supply chain construction module is used to analyze the data in the project equipment supply link, find the process data reflecting the project equipment supply, and build the project equipment supply chain;

[0127] The abnormality judgment module is used to find characteristic data reflecting abnormalities of project equipment according to historical data, calculate the abnormality threshold of the project equipment according to the characteristic data, and use the abnormality threshold to judge whether there is abnormal risk of real-time project equipment;

[0128] The model building module uses the characteristic data and process data in the history to build a scatter plot, calculates and analyzes the three-point plot to obtain the regression curve equation of the scatter plot, uses the regression curve equation in the scatter plot as the correlation expression of the process data and the characteristic data, and uses the expression to calculate the inversion screening model;

[0129] The link positioning module is used to, after issuing an early warning for project equipment with abnormal risks, locate the supply chain link that causes the abnormal risk of the early warning project equipment according to the inverse screening model and eliminate the problematic link.

[0130] The supply chain building modules include data analysis unit and link sorting unit;

[0131] The data analysis unit is used to search for common data in each link, calculate the difference of each common data, and sort the supply links of the project equipment using the signs of the difference;

[0132] The link sorting unit is used to analyze each sorting result after sorting the supply links of the project equipment using the difference symbol, and the best difference sorting result is the supply chain to determine the process data.

[0133] The abnormality judgment module includes a characteristic data search unit, a threshold calculation unit and a judgment unit;

[0134] The characteristic data unit is used to analyze all equipment data of abnormal project equipment in history, calculate the difference after abnormality, and find out the characteristic data reflecting the abnormality of project equipment;

[0135] The threshold value calculation unit is used to calculate the abnormal threshold value used to determine whether the real-time project equipment has an abnormal risk by using the characteristic data of the abnormal project equipment in the history;

[0136] The judgment unit is used to collect feature data of real-time project equipment, use abnormal thresholds to judge the real-time feature data of project equipment, determine whether there is an abnormal risk in the real-time project equipment, and issue an early warning.

[0137] Example 1: Collect data from a company's project equipment supply process, determine that the data with the largest amplitude is the vibration frequency, and use the formula The classification threshold is calculated to be 3; the supply process of project equipment is divided into four links: link 1, link 2, and link 3;

[0138] Collect common data that exist in each link, including time, temperature, humidity, and pressure; calculate the difference signs of the three common data, which are +, -, and - respectively; use the three common data to sort the links in turn; sort by time data as link 3-link 1-link 2; in the sub-link, the size relationship of temperature data in the three links is link 3>link 2>link 1, but the difference sign of temperature data is -; the correct sorting can only be from large to small link 3-link 2-link 1, so when sorting by time, temperature data is suspicious data, and after sorting humidity data, the credible data are humidity and pressure; use the same method to sort the rest of the common data as the standard, and compare and find that the most credible data is sorted by time, so the supply chain is link 3-link 1-link 2, and the process data is time;

[0139] The abnormal characteristic data collected by historical data is the amplitude, and the calculated abnormal threshold is 30; the real-time project equipment amplitude is 35, and it is judged that there is an abnormal risk and an early warning is issued;

[0140] Use the historical time data and amplitude data to construct a scatter plot such as Figure 3 As shown, the linear regression equation is calculated, and the correlation expression between time data and amplitude data is obtained as Ft = 0.76×RL - 4.8;

[0141] The amplitude of the real-time warning collected is 20, and the calculated time data is 32.6. This time data is compared with the time data in the supply chain, and the closest link is selected as link 1. Link 1 is judged to be the problem link, and the problem link information is sent to the project manager for problem troubleshooting.

[0142] 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.

[0143] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A project equipment supply chain evaluation method based on big data, characterized by: The method comprises the following steps: S100, collecting the process data of the project equipment supply in history, analyzing all the process data, and classifying the project equipment supply process into different supply links; The specific steps of classifying the supply process of project equipment into different supply links are as follows: S101, collect the process data of the project equipment supply in history, and extract the equipment data of the project equipment in the supply process. , It represents the 1st, 2nd, 3rd, ..., nth equipment data of the extracted project equipment in the supply process, where n is a positive integer; a curve graph is drawn using each equipment data, and the curve graphs of the n equipment data are observed, and the maximum and minimum values ​​of each equipment data are screened out to calculate the maximum amplitude of each equipment data. The formula is: ； In the formula, Am represents the maximum amplitude of each device data. Indicates the maximum value of each device data. Indicates the minimum value of each equipment data; obtains the maximum amplitude of each equipment data through calculation; selects the equipment data type corresponding to the maximum value among the maximum amplitudes of n types of equipment data as the effective data for distinguishing the project equipment supply process; S102, calculating the difference between two adjacent valid data in the valid data curve, and using the difference to calculate the threshold for process classification, the formula is: ； In the formula, FY represents the threshold used to classify the equipment supply process of the project, and represents two adjacent data in the effective data curve, m-1 represents the number of adjacent effective data differences calculated, Represents the standard deviation of m-1 adjacent valid data differences; S103, using the calculated threshold for classifying the project equipment supply process to judge the difference Sc of each adjacent valid data, when When the supply process of the project equipment is judged to have changed, The supply process corresponding to the valid data on both sides is divided into different links; When it is determined that the supply process of the project equipment has not changed, The supply process corresponding to the valid data on both sides is divided into the same link; the difference between the calculated m-1 adjacent valid data is judged, and finally the supply process of the project equipment is divided into G links, specifically: , Indicates the 1st, 2nd, 3rd, ..., Gth link in the supply of project equipment, where G is a positive integer; S200, screening the data of the project equipment supply process, searching for process data reflecting the project equipment supply status, calculating the searched process data, and building the project equipment supply chain using the supply link; The specific steps to build a project equipment supply chain using the supply chain are: S201. Collect all data of each link in the historical project equipment supply process. Suppose the data in each link is , Indicates the 1st, 2nd, 3rd, ..., jth type of data in each link, where j is a positive integer; compare the data in each link to select the data types that exist in each link; S202: Assume that the data types existing in each link are common data, and the types of common data screened are , Indicates the 1st, 2nd, 3rd, ..., kth type of data that exists in each stage of screening, where k is a positive integer. ; Extract each general data value of the project equipment when it is in use and the general data value at the initial supply, and calculate the general data difference of the project equipment after the supply is completed. The formula is: ； In the formula, Indicates the difference between the initial supply and the final supply of each common data in the calculated project equipment. Indicates the value of each common data of the project equipment after supply, Indicates the value of each general data of the project equipment at the beginning of supply; calculates the difference between each general data at the beginning and after supply, and obtains the difference of k general data; S203, judge the difference sign of each common data, and use the difference sign to sort the supply links of the project equipment. When the corresponding type of common data value in each link is extracted, the supply links of the project equipment are sorted in ascending order according to the common data; when When extracting the common data values ​​of the corresponding types in each link, the supply links of the project equipment are sorted in descending order according to the common data; S204, sorting the supply link sequence of the project equipment according to the sign of each general data difference in turn, when selecting a general data difference sign to sort the supply link sequence of the project equipment, judging each general data value and difference sign after sorting, when the size sequence and difference sign of the general data after sorting do not match, judging the corresponding general data as suspicious data; when the size sequence and difference sign of the general data after sorting match, judging the corresponding general data as credible data; Sort each common data by symbol and judge the remaining common data. After k sortings, the number of credible data judged in each sorting is , It indicates the number of credible data obtained when judging the 1st, 2nd, 3rd, ..., pth sorting, where p is a positive integer; the sorting result with the most credible data is selected as the final project equipment supply chain, and the corresponding general data type selected during sorting is used as the process data RL for project equipment supply; S300, collecting historical data of abnormal equipment when project equipment is working, analyzing the equipment data to find feature data of equipment abnormality, and calculating an abnormality threshold based on the feature data of equipment abnormality in history; S400, collecting feature data of project equipment in real time when it is working, using the calculated abnormal threshold to judge the real-time feature data, whether there is an abnormal risk of the real-time project equipment and issue an early warning; S500, after the risk warning is issued for the real-time project equipment, the correlation between the process data and the characteristic data is calculated, and an abnormal inversion screening model is constructed; S600. Use the constructed anomaly inversion screening model to invert the anomalies of real-time warnings, determine the supply chain links that cause abnormal risks of equipment, mark them as problem links, and transmit the problem link information to the project manager for problem troubleshooting.

2. According to the big data-based project equipment supply chain evaluation method of claim 1, it is characterized by: The specific steps of calculating the abnormality threshold value according to the characteristic data of the abnormality of the device in the history in S300 are: S301. Collect the equipment data when the project equipment has abnormality in history, extract the data value of each equipment before and after the project equipment has abnormality, and calculate the change amount of each equipment data after the project equipment has abnormality. The formula is: ； In the formula, Indicates the calculated change in each device data after an abnormality occurs in the project equipment. Indicates the value of each device data before the abnormality of the project device occurs. Indicates the value of each device data after the project equipment has an abnormality; judges the change amount of all device data after the project equipment has an abnormality, and selects the device data type corresponding to the maximum change amount as the characteristic data of the project equipment abnormality; S302, collect the characteristic data of the project equipment when abnormality occurs in the history , It represents the characteristic data collected when the project equipment is abnormal for the 1st, 2nd, 3rd, ..., bth time in history, where b is a positive integer. The abnormal threshold of the project equipment is calculated using the characteristic data collected when the project equipment is abnormal in history, and the formula is: ； In the formula, represents the calculated abnormal threshold of the project equipment, Ft represents the characteristic data collected in the history, b represents the number of characteristic data collected, Represents the standard deviation of the collected feature data.

3. According to the big data-based project equipment supply chain evaluation method of claim 2, it is characterized by: The specific steps of using the calculated abnormal threshold to judge the real-time feature data in S400 are: S401, extract the characteristic data of the project equipment in real time , represents the feature data of the 1st, 2nd, 3rd, ..., dth project equipment extracted in real time, where d is a positive integer; the real-time feature data is judged using the abnormal threshold. When the project equipment is judged to have abnormal risks, an early warning is issued; When the project equipment is judged to have no abnormal risks, work can continue.

4. The project equipment supply chain evaluation method based on big data according to claim 2 is characterized by: The specific steps of constructing the abnormal inversion screening model in S500 are: S501. Collect the characteristic data and process data of the project equipment in the supply chain in history, use the process data as the independent variable and the characteristic data as the variable to draw a scatter plot, calculate the linear regression equation in the scatter plot, and assume that the regression equation expression of the characteristic data and process data in the scatter plot is , in which Ft represents characteristic data, RL represents process data, A represents slope, and B represents intercept; S502. Calculate the slope and intercept values ​​in the expression using the points in the scatter plot. The formula is: ； ； In the formula, Ft represents the value of the variable characteristic data of each point in the scatter plot, and RL represents the value of the independent variable process data of each point in the scatter plot. represents the average value of the variable in T points of the scatter plot, It represents the average value of the independent variable in T points in the scatter plot, and T represents the number of points in the scatter plot. After calculating the slope and intercept in the regression curve equation in the scatter plot, the correlation expression between the process data and the characteristic data is obtained as the regression curve equation in the scatter plot. S503. Using the calculated correlation expression of the process data and the characteristic data, an inversion screening model for the project equipment is constructed.

5. The project equipment supply chain evaluation method based on big data according to claim 4 is characterized by: The specific steps of inverting the anomaly of the real-time warning using the constructed anomaly inversion screening model in S600 are as follows: S601. When it is determined that the project equipment has abnormal risk and an early warning is issued, the characteristic data of the early warning project equipment is extracted as Ft_y; the supply link that causes the abnormal risk of the project equipment is located using the inverse screening model, and the formula is: ； In the formula, RL_y represents the project equipment process data with abnormal risks; S602, after calculating the process data of the project equipment with abnormal risks, use Calculate the difference between the process data in each supply link of the project equipment, and select the link corresponding to the process data with the smallest difference as the problem link of the project equipment with abnormal risk; send the data of the problem link to the project person in charge to eliminate supply chain anomalies.

6. A project equipment supply chain evaluation system based on big data using the project equipment supply chain evaluation method based on big data as described in any one of claims 1 to 5, characterized in that: The project equipment supply chain evaluation system includes a data collection module, a link classification module, a supply chain construction module, an abnormality judgment module, a model construction module and a link positioning module; The data collection module is used to collect supply data, equipment data and abnormal data of historical project equipment; The link classification module is used to classify the project equipment supply process using historical data and determine the specific supply links; The supply chain construction module is used to analyze the data in the project equipment supply link, find the process data reflecting the project equipment supply, and build the project equipment supply chain; The abnormality judgment module is used to find characteristic data reflecting abnormalities of project equipment according to historical data, calculate the abnormality threshold of the project equipment according to the characteristic data, and use the abnormality threshold to judge whether there is abnormal risk of real-time project equipment; The model building module uses the characteristic data and process data in the history to build a scatter plot, performs calculation and analysis on the scatter plot to obtain a regression curve equation of the scatter plot, uses the regression curve equation in the scatter plot as a correlation expression between the process data and the characteristic data, and uses the expression to calculate the inversion screening model; The link positioning module is used to, after issuing an early warning for project equipment with abnormal risks, locate the supply chain link that causes the abnormal risk of the early warning project equipment according to the inverse screening model and eliminate the problematic link.

7. The project equipment supply chain evaluation system based on big data according to claim 6 is characterized by: The supply chain building module includes a data analysis unit and a link sorting unit; The data analysis unit is used to search for common data in each link, calculate the difference of each common data, and sort the supply links of the project equipment using the signs of the difference; The link sorting unit is used to analyze each sorting result after sorting the supply links of the project equipment using the difference symbol, and the best difference sorting result is the supply chain to determine the process data.

8. The project equipment supply chain evaluation system based on big data according to claim 6 is characterized by: The abnormality judgment module includes a characteristic data search unit, a threshold calculation unit and a judgment unit; The characteristic data unit is used to analyze all equipment data of abnormal project equipment in history, calculate the difference after abnormality, and find out the characteristic data reflecting the abnormality of project equipment; The threshold value calculation unit is used to calculate the abnormal threshold value used to determine whether the real-time project equipment has an abnormal risk by using the characteristic data of the abnormal project equipment in the history; The judgment unit is used to collect feature data of real-time project equipment, use abnormal thresholds to judge the real-time feature data of project equipment, determine whether there is an abnormal risk in the real-time project equipment, and issue an early warning.

Images