A supervision and management method and system for coal construction projects based on big data

Abstract

The present invention relates to the technical field of coal engineering data monitoring, and particularly relates to a supervision and management method and system for coal construction projects based on big data. The method includes: during the construction process of a coal construction project, forming data points from the consumed materials and project progress, setting a first neighborhood range of the data points, determining the neighborhood anomaly degree according to the fluctuation of the first neighborhood range of the data points, and adjusting the first neighborhood range to obtain a second neighborhood range. Evaluating the adaptation degree of the second neighborhood range and calculating a third neighborhood range. Determining the robust weight of the data points according to the third neighborhood range, performing least squares fitting based on the robust weights of all data points to obtain an overall fitting curve. Analyzing the slope change of the overall fitting curve to determine whether the data points on the current date are abnormal, so as to achieve real-time supervision and management. This method can effectively identify the abnormal relationship between the consumed materials and project progress during the construction process, and improve the timeliness and accuracy of construction supervision and management.

Description

Technical Field

[0001] The present invention relates to the technical field of coal engineering data monitoring. Specifically, it relates to a supervision and management method and system for coal construction projects based on big data. Background Art

[0002] In the field of coal construction projects, the project scale is huge and the construction period is long. For the abnormal monitoring of project progress and material consumption, it is possible to achieve refined control of the project construction process.

[0003] The robust weighted least squares method is a common technical means. Its specific implementation method is as follows: Based on historical construction data and multi-source information obtained from real-time monitoring, an association model between material consumption and project progress is constructed. First, for each data point, other relevant data points are collected within its preset fixed neighborhood range. Then, according to the influence degree of each data point in the neighborhood on the robust weight of the current data point, the robust weight of the current data point is determined. The least squares method is used to fit these weighted data points to generate a fitting curve reflecting the relationship between material consumption and project progress. During the project progress, abnormal monitoring is carried out according to the change of the fitting curve.

[0004] However, in the complex and changeable actual scenario of coal construction projects, the traditional robust weighted least squares method has obvious defects. The construction environment of coal construction projects is complex, and the construction process is affected by various factors such as geological conditions, climate factors, and technical process adjustments. In such a background, it is difficult for the fixed neighborhood range to flexibly respond to the local characteristic changes of different data points. If the neighborhood range is too small, the model can only capture limited local data changes, over-focusing on local features, which will lead to misjudgment of the overall trend of material consumption and project progress and cannot accurately reflect the actual situation of the project. If the neighborhood range is set too large, the calculation efficiency will be seriously reduced, delaying the best time to solve the problem.

[0005] In short, when using the traditional robust weighted least squares method to conduct abnormal monitoring of project progress and material consumption in coal construction projects, the fixed neighborhood range will affect the accuracy of the abnormal monitoring results, leading to misjudgment of project progress and material consumption and unable to meet the accurate supervision and management of coal construction projects. Summary of the Invention

[0006] To solve the problem that when using the traditional robust weighted least squares method to conduct abnormal monitoring of project progress and material consumption, the fixed neighborhood range will affect the accuracy of the abnormal monitoring results and cannot meet the accurate supervision and management requirements, the present invention proposes a supervision and management method and system for coal construction projects based on big data.

[0007] In a first aspect, the present invention provides a supervision and management method for coal construction projects based on big data, including:

[0008] During the construction process of coal construction projects, the total amount of materials consumed each day and the project progress form a data point. All data points from the start of construction to the current date are obtained, and a two-dimensional coordinate system of all data points is constructed with the total amount of materials consumed as the horizontal axis and the project progress as the vertical axis;

[0009] Preset the first neighborhood range of all data points; determine the neighborhood anomaly degree of each data point according to the fluctuation degree of the first neighborhood range of each data point, and adjust the first neighborhood range of each data point to the second neighborhood range by using the neighborhood anomaly degree of each data point;

[0010] Evaluate the adaptation degree of the second neighborhood range of each data point and calculate the third neighborhood range of each data point: , in the formula, is the third neighborhood range of the th data point, is the adaptation degree of the second neighborhood range of the th data point, is the preset first neighborhood range, is the second neighborhood range of the th data point;

[0011] Determine the robust weight of each data point according to the third neighborhood range of each data point, perform least squares fitting based on the robust weights of all data points to obtain the overall fitting curve, and conduct real-time supervision and management of the material consumption and project progress on the current date according to the slope change of the overall fitting curve.

[0012] This technical solution first combines the total amount of consumed materials per day and the project progress into a data point, constructs a basic data unit reflecting the relationship between project progress and material consumption, and obtains comprehensive data points with time series characteristics. These data can intuitively reflect the associated changes between material consumption and project progress as the project progresses, enabling a more accurate grasp of the actual progress of the project. Next, the first neighborhood range is dynamically adjusted according to the neighborhood abnormality degree of each data point, enabling the second neighborhood range to adapt to the local characteristics of different data points and avoiding the limitations of a fixed first neighborhood range. Then, an adaptation degree index is introduced to measure the quality of the second neighborhood range, and multiple factors are comprehensively considered to further optimize the second neighborhood range. The third neighborhood range for each data point is obtained. The third neighborhood range can better balance the local characteristics and overall trend of the data points, making subsequent analysis based on the third neighborhood range more accurate and reliable, and improving the modeling accuracy of the relationship between project progress and material consumption. Finally, robust weights are determined according to the third neighborhood range, enabling the calculation of robust weights to more accurately reflect the importance of data points. The overall fitting curve obtained from accurate calculation of robust weights and least squares fitting can more precisely describe the relationship between material consumption and project progress. By monitoring the slope change of the overall fitting curve to judge abnormalities, abnormal changes in project progress and material consumption can be detected in a timely manner, realizing real-time supervision and management of coal construction projects, so as to take timely measures for adjustment, ensure the smooth progress of the project, and improve the efficiency and quality of project management.

[0013] Further, curve fitting is performed on all data points within the third neighborhood range of each data point to obtain the local curve of each data point, and the coordinate value corresponding to this data point on the local curve and the original coordinate value of this data point are calculated, and the reciprocal of the absolute value of the difference between them is used as the robust weight of this data point.

[0014] The robust weights of each data point determined by this technical solution are such that the robust weights of those data points with a change trend similar to that of surrounding data points are relatively large. When fitting the overall fitting curve of the relationship between material consumption and project progress, these data points with large robust weights play a dominant role in the fitting process of the overall curve, so that the finally obtained overall fitting curve can more accurately reflect the true relationship between material consumption and project progress, providing a reliable basis for accurately judging whether project progress and material consumption are abnormal subsequently.

[0015] Further, the adaptation degree of the second neighborhood range of each data point satisfies the following relational expression:

[0016] , . is the The adaptation degree of the second neighborhood range of the data points and the total number of data points within the second neighborhood range and is the local fitting error of the th data point, the th data point within the second neighborhood range of the th data point and is the neighborhood anomaly degree of the th data point, the th data point within the second neighborhood range of the th data point and are the standard deviation of the local fitting errors and the standard deviation of the neighborhood anomaly degrees of all data points within the second neighborhood range of the th data point and are the mean value of the local fitting errors and the mean value of the neighborhood anomaly degrees of all data points within the second neighborhood range of the th data point is the natural exponential function is the absolute value symbol

[0017] This technical solution comprehensively considers multi-dimensional data features to determine the adaptation degree of the second neighborhood range, comprehensively weighs the local fitting errors, neighborhood anomaly degrees and their discrete characteristics of each data point within the second neighborhood range, can accurately measure the quality of the second neighborhood range, and provides a reliable analysis index for determining a more accurate third neighborhood range subsequently

[0018] Furthermore, the method for real-time supervision and management of the material consumption and project progress on the current date according to the slope change of the overall fitting curve is as follows

[0019] Obtain the slope at each data point on the overall fitting curve, and use the box plot method to perform anomaly detection on all slopes; if the slope at the data point on the current date has an anomaly, it is determined that the material consumption and project progress on the current date have an anomaly, a warning notice is issued, and the consumed materials and project progress on the current date are inspected and analyzed; if the slope at the data point on the current date does not have an anomaly, it is determined that the material consumption and project progress on the current date do not have an anomaly, and no warning notice is issued

[0020] Furthermore, the first neighborhood range, the second neighborhood range, and the third neighborhood range of each data point are all length values, starting from each data point, and intercepting forward according to the length value to obtain the neighborhood range corresponding to the data point

[0021] Furthermore, the neighborhood anomaly degree of each data point is calculated based on the following formula

[0022] ;

[0023] In the formula, For the The degree of abnormality of the neighborhood of a data point, For the The fluctuation degree of the first neighborhood range of the data point, For the The total number of data points within the first neighborhood of a data point, For the The first neighborhood of the data point The original data point Coordinate values, For the The first neighborhood of the data point The original data point Coordinate values, For the The original data points of all data points in the first neighborhood of the data point The mean of the coordinate values, is the preset first neighborhood range, is the absolute value symbol, is a natural exponential function.

[0024] This technical solution calculates the neighborhood anomaly degree of each data point and can accurately reflect the abnormal situation of the data point within its neighborhood range. The accurate anomaly degree assessment provides a reliable basis for the subsequent adjustment of the first neighborhood range, so that the adjusted second neighborhood range can better adapt to the local characteristics of the data point, thereby improving the accuracy of data analysis.

[0025] Furthermore, the local fitting error is determined based on the following method: curve fitting is performed on all data points within the second neighborhood of each data point to obtain a local curve for each data point; the corresponding error of the data point on the local curve is calculated. The coordinate value and the original The absolute value of the difference in coordinate values ​​is taken as the local fitting error of the data point.

[0026] Furthermore, the fluctuation degree of the first neighborhood range of each data point is determined based on the following method: calculating the fluctuation degree of all data points within the first neighborhood range of each data point Variance of coordinate values , and all data points in the coordinate system Variance of coordinate values ;Will and The ratio of is taken as the fluctuation degree of the first neighborhood range of the data point.

[0027] This technical solution quantifies the degree of dispersion of all data points within the first neighborhood range of each data point by calculating the variance of all data points within the first neighborhood range. It can intuitively reflect the fluctuation of all data points within the first neighborhood range, and through this quantization method, the stability of the data points within the neighborhood range of each data point can be understood more accurately.

[0028] Furthermore, the method for adjusting the first neighborhood range of each data point to the second neighborhood range by using the neighborhood anomaly degree of each data point is as follows: preset a neighborhood anomaly degree threshold ; calculate the second neighborhood range of each data point: , where is the second neighborhood range of the th data point, is the preset first neighborhood range, is the neighborhood anomaly degree of the th data point, is the ceiling symbol.

[0029] This technical solution establishes a clear correlation between the neighborhood anomaly degree and the first neighborhood range. The neighborhood anomaly degree of each data point accurately reflects the abnormal situation around the data point. Compared with the traditional method of a fixed neighborhood range, this solution can flexibly adjust the first neighborhood range to a more appropriate second neighborhood range according to the actual abnormal situation of the first neighborhood range of each data point.

[0030] In a second aspect, the present invention provides a supervision and management system for coal construction projects based on big data. The supervision and management system includes a memory and a processor. A computer program is stored on the memory, and the processor executes the computer program to implement the steps of any one of the supervision and management methods.

[0031] The present invention has the following effects:

[0032] This solution obtains data points covering the entire construction process and having time series characteristics. First, it initially adjusts the neighborhood range according to the data distribution characteristics of the data points within the neighborhood range, and then introduces an adaptation degree index to adjust and optimize the neighborhood range again, balancing the local details and overall trends of the data points. Based on the robust weights determined by the optimized neighborhood range, the least squares method is used to generate an overall fitting curve that accurately reflects the material consumption and project progress, improving the fitting effect. Based on the accurate overall fitting curve, accurate anomaly monitoring can be performed, realizing real-time and efficient supervision and management of coal construction projects. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 is a schematic flow chart of the method of the present invention;

[0034] Figure 2 is the overall fitting curve graph of the present invention;

[0035] Figure 3 is the schematic flow chart of the real-time supervision and management of the material consumption and project progress based on the overall fitting curve of the present invention;

[0036] Figure 4 is the box plot anomaly detection result graph of the present invention. Specific embodiments

[0037] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention.

[0038] Referring to Figure 1 , a method for supervising and managing coal construction projects based on big data provided by the present invention includes steps S1 - S7:

[0039] S1: Collect material consumption and project progress, and construct a two-dimensional coordinate system.

[0040] During the construction process of coal construction projects, the daily material consumption is huge. Among them, concrete, as a key building material, its consumption plays an important role in the project progress. In the supervision and management system involved in the present invention, the consumed materials mentioned specifically refer to the total consumed amount of concrete.

[0041] To accurately grasp the project dynamics, data collection work is carried out regularly every day. Specifically, the total amount of consumed materials and project progress data are collected once a day. For example, when collecting data on the 10th day, the total amount of consumed materials obtained is the cumulative consumption of concrete from the start date of the project (the 1st day) to the 10th day; and the project progress data collected on the 10th day reflects the actual progress of the project as of the 10th day. Similarly, the total amount of consumed materials collected on the 11th day is the total consumption of concrete from the 1st day to the 11th day since the start of the project, and the project progress collected on the 11th day represents the progress status of the project on the 11th day.

[0042] Collect the total amount of consumed materials and project progress every day from the start of construction until the current date. Use the total amount of consumed materials as the horizontal axis and the project progress as the vertical axis to construct a two-dimensional coordinate system covering all data points. In this way, the total amount of consumed materials and project progress collected every day together constitute a data point in this two-dimensional coordinate system.

[0043] In the two-dimensional coordinate system, the abscissa of the th data point , represents the The total amount of consumed materials corresponding to a data point is for the date of that day. The ordinate of the th data point represents the project progress for the date corresponding to the

[0044] th data point. In summary, by constructing a two-dimensional coordinate system with the total amount of consumed materials as the horizontal axis and the project progress as the vertical axis, the complex project progress and material consumption situation can be visually presented. Each data point represents the construction status of one day. The distribution and change trend of the overall data points can enable managers to clearly understand the progress track of the project from the start to the current, providing a solid foundation for real-time supervision and management.

[0045] S2: Determine the neighborhood anomaly degree based on the first neighborhood range of each data point.

[0046] In the supervision and management system of the present invention, the neighborhood anomaly degree of each data point is determined according to its first neighborhood range. A fixed neighborhood range is set for each data point according to the traditional robust weighted least squares method. The neighborhood range is 7 (empirical value), and the size of the first neighborhood range of all data points is . Among them, is a length value. For example, , for the th data point, starting from the th data point, intercept 5 data points forward. The th data point and the intercepted 5 data points are used as the first neighborhood range of the th data point.

[0047] In the process of supervision and management of coal construction projects, accurately grasping the characteristics and laws of data is crucial for ensuring the smooth progress of the project. If the data points within the first neighborhood range of a data point have poor stability and high outlier property, it indicates that the neighborhood anomaly degree of this data point is greater. If no adjustment is made and the robust weight value is still obtained according to the first neighborhood range, the result will be difficult to accurately reflect the actual situation, thereby affecting the accurate judgment of the project status.

[0048] First, analyze the fluctuation degree of the first neighborhood range of each data point:

[0049] Calculate the variance of the coordinate values of all data points within the first neighborhood range of each data point , and the variance of the coordinate values of all data points in the coordinate system ; Compare with The ratio is used as the degree of fluctuation in the first neighborhood range of the data point to effectively evaluate the stability of the data in the local area where the data point is located. The larger the ratio, the greater the degree of fluctuation in the first neighborhood range of the data point, and the more unstable the data points within the first neighborhood range. Vice versa.

[0050] For the th data point, the degree of fluctuation in its first neighborhood range is:

[0051]

[0052] In this formula, is the degree of fluctuation in the first neighborhood range of the th data point, is the variance of the coordinate values of all data points within the first neighborhood range of the th data point, is the variance of the coordinate values of all data points in the coordinate system.

[0053] As a statistic measuring the degree of data dispersion, variance can intuitively reflect the fluctuation of data. When the degree of fluctuation in the first neighborhood range of the th data point is greater, it means that is larger relative to , that is, the degree of fluctuation of the data points within the first neighborhood range of the th data point is more intense compared to the overall fluctuation, indicating that the data points within the first neighborhood range of this data point are unstable, meaning that there are factors affecting the stability of the project progress in the construction stage corresponding to the first neighborhood range, such as construction process adjustment, equipment failure, or personnel allocation problems, etc. Vice versa, when the degree of fluctuation in the first neighborhood range of the th data point is smaller, it shows that the degree of fluctuation of the data points within the first neighborhood range of this data point is within the normal range of the overall fluctuation, and the data points within the first neighborhood range of this data point are relatively stable, meaning that the project is in a stable progress state in the construction stage corresponding to the first neighborhood range.

[0054] Then, calculate the neighborhood anomaly degree of each data point:

[0055]

[0056] In the formula, is the neighborhood anomaly degree of the th data point, comprehensively reflecting the anomaly situation of all data points within the first neighborhood range of this data point. The larger its value, the higher the anomaly degree of the first neighborhood range of this data point, and the more unstable the local data. is the The degree of fluctuation of the first neighborhood range of a data point reflects the magnitude of the fluctuation of the first neighborhood range of the data point relative to the fluctuation of the overall data. The larger the value, the more drastic the fluctuation of the first neighborhood of the data point is compared with the overall value. It will amplify the impact of other factors on the degree of anomaly, emphasize the contribution of neighborhood fluctuations to the overall degree of anomaly, and make the final result more prominent in the unstable characteristics of the first neighborhood range. For the The total number of data points within the first neighborhood of a data point, For the The first neighborhood of the data point The original data point Coordinate values, For the The first neighborhood of the data point The original data point Coordinate values, For the The original data points of all data points in the first neighborhood of the data point The mean of the coordinate values, is the preset first neighborhood range, is the absolute value symbol, is a natural exponential function. The coordinate value indicates the total amount of material consumed. The coordinate value is the project progress.

[0057] In this formula, Combined with the The original data points of all data points in the first neighborhood of the data point The coordinate value is relative to the original The deviation from the average level of the coordinate values, and The distance weight between a data point and all the data points in its first neighborhood in the dimension of the total amount of consumed materials can accurately reflect the deviation of all the data points in the first neighborhood. The department reflects The deviation of the engineering progress of each data point within the first neighborhood of the data points from the average engineering progress. The larger the deviation, the higher the degree of outlier. Part is the distance weight calculated by the Gaussian kernel function, Measured the data point and the first neighborhood The distance between data points on the total amount of consumed material, according to The principle is to use the first neighbor range Instead of the standard deviation in the Gaussian kernel function, it is used to adjust the width of the Gaussian kernel function. When the distance between two data points in terms of the total material consumption is closer, the value of this part is closer to 1, indicating that the data points within the first neighborhood range of the th data point have a greater impact on the neighborhood anomaly degree of the th data point; conversely, the farther the distance, the closer the value of this part is to 0, meaning that the data points within the first neighborhood range of the th data point have a smaller impact on the neighborhood anomaly degree of the th data point. This distance-weighted method takes into account the correlation of data points in the dimension of the total consumed material, more reasonably synthesizes the contributions of data points at different positions within the first neighborhood range to the neighborhood anomaly degree of the current data point, enabling the calculation result to more accurately reflect the actual situation of the data points within the first neighborhood range of the th data point.

[0058] In summary, by correlating the neighborhood fluctuations and overall fluctuations of data points, combining the degree of deviation of data points within the neighborhood from the mean in terms of project progress, and the distance weights of data points within the neighborhood in the dimension of the total consumed material, this formula comprehensively and meticulously reflects the neighborhood anomaly situation of each data point.

[0059] S3: Adjust the first neighborhood range to the second neighborhood range according to the neighborhood anomaly degree.

[0060] If the neighborhood anomaly degree of a data point is greater, it means that the uncertainty of the data points within the first neighborhood range of this data point is higher. At this time, a larger neighborhood range is required to synthesize more data information to make the calculated robust weight tend to be stable, and vice versa.

[0061] Therefore, adjust the first neighborhood range to the second neighborhood range according to the following method:

[0062] Preset the neighborhood anomaly degree threshold to be 0.47 (empirical value).

[0063] Calculate the second neighborhood range of each data point:

[0064]

[0065] In this formula, is the second neighborhood range of the th data point, is the preset first neighborhood range, is the neighborhood anomaly degree of the th data point, is the ceiling symbol.

[0066] If Greater than , indicating that the degree of abnormality in the neighborhood of this data point exceeds the preset normal range, and it is necessary to expand the neighborhood range to stabilize the robust weight. At this time is greater than 1, and the preset first neighborhood range is magnified; if is less than , it indicates that the degree of neighborhood abnormality is relatively low, and the adjustment range of the neighborhood is correspondingly small. At this time is less than 1, and the preset first neighborhood range is reduced.

[0067] This adjustment strategy can adapt to the complex and changeable data characteristics in coal construction projects. By expanding or reducing the neighborhood range, more or more accurate data information is integrated, so that the calculated robust weight tends to be stable, providing a more reliable data basis for subsequent least squares fitting based on the robust weight and engineering supervision and management decisions.

[0068] Among them, is the length value. For example , then starting from the th data point, 10 data points are intercepted forward. The th data point and the intercepted 10 data points are used as the second neighborhood range of the th data point.

[0069] S4: Evaluate the adaptability of the second neighborhood range.

[0070] Accurately evaluating the project status depends on the accurate grasp of the relationship between material consumption and project progress data. The adaptability of the second neighborhood range helps to identify the neighborhood data that can more accurately reflect the actual progress of the project. For example, when the adaptability of the second neighborhood range of a certain data point is high, it indicates that the data points in this neighborhood are more consistent and reliable in reflecting the relationship between material consumption and project progress. Based on this, managers can more accurately judge whether the actual progress of the project at this stage meets the expectations and whether the material consumption is reasonable, and timely discover potential project problems, such as schedule delays or material waste.

[0071] When calculating the robust weight of each data point subsequently, the second neighborhood range with high adaptability can provide a more reliable data basis, so that the robust weight calculated based on these data can more accurately reflect the true distribution of the data, avoiding deviations in the robust weight caused by inappropriate selection of the neighborhood range, including too many abnormal or unstable data, and thus affecting the accuracy of subsequent data processing results such as least squares fitting.

[0072] First, obtain the local fitting error of each data point:

[0073] Curve fitting is performed on all data points within the second neighborhood range of each data point to obtain the local curve of each data point; calculate the difference between the coordinate value corresponding to the data point on the local curve and the original coordinate value of the data point, and take the absolute value of this difference as the local fitting error of the data point.

[0074] Next, calculate the adaptability degree of the second neighborhood range of each data point according to the following formula:

[0075]

[0076] In this formula, is the adaptability degree of the second neighborhood range of the th data point, and its numerical value directly reflects the desirability of this neighborhood range in the overall data processing and engineering analysis. The larger the value, the more reliable and stable the data points covered by this second neighborhood range are in reflecting key information such as the relationship between material consumption and project progress, and the more suitable it is for subsequent robust weight calculation. is the total number of data points within the second neighborhood range of the th data point, is the local fitting error of the th data point, is the local fitting error of the th data point within the second neighborhood range of the th data point, is the neighborhood abnormality degree of the th data point, is the neighborhood abnormality degree of the th data point within the second neighborhood range of the th data point, is the standard deviation of the local fitting errors of all data points within the second neighborhood range of the th data point, is the standard deviation of the neighborhood abnormality degrees of all data points within the second neighborhood range of the th data point, is the mean value of the neighborhood abnormality degrees of all data points within the second neighborhood range of the th data point, is the mean value of the local fitting errors of all data points within the second neighborhood range of the th data point, is the natural exponential function, is the absolute value symbol.

[0077] In this formula, multiply by It plays a role in normalization. Since the number of data points included in the second neighborhood range of different data points may vary greatly, without normalization, if there are many data points in the second neighborhood range of a certain data point, it may dominate in the cumulative calculation. If there are few data points in the second neighborhood range of a certain data point, its impact on the cumulative calculation is weak, resulting in an inability to fairly compare the adaptation degrees of the second neighborhood ranges of different data points. Through normalization, the calculation results of different data points are on the same scale and are more comparable.

[0078] In this formula, part, measures the th data point's relative difference in local fitting error between itself and the th data point within its second neighborhood range, reflecting the relative change in fitting error between the th data point and each data point within its second neighborhood range; measures the relative difference in neighborhood abnormality degree between the th data point and the th data point within its second neighborhood range in terms of abnormality degree, and are used for normalization, and adding 1 is to avoid the generation of zero or negative values, so as to more stably reflect the adaptation degree of the second neighborhood range.

[0079] This part comprehensively considers the co-variation of each data point and the data points within its second neighborhood range in two key dimensions: local fitting error and neighborhood abnormality degree. When the calculation result is larger, it indicates that each pixel point and the data points within its second neighborhood range change consistently in these two dimensions, the correlation between the data points within the second neighborhood range is strong, it is more in line with the internal law of engineering data, and the adaptation degree of the second neighborhood range is higher; on the contrary, when the calculation result is smaller, it indicates that the data points within the second neighborhood range change chaotically in these two dimensions, the quality of the second neighborhood range is low, and the adaptation degree is low.

[0080] In this formula, part, reflects the ratio of the local fitting error to the neighborhood abnormality degree of the th data point itself, reflecting the relative relationship of the th data point itself in these two key factors. represents the ratio of the mean of the local fitting errors of all data points within the second neighborhood range of the th data point to the mean of the neighborhood abnormality degrees of all data points, reflecting the relative relationship of all data points within the second neighborhood range in these two factors. measures and The smaller the difference, the better the consistency of these two relative relationships. It means that the greater the correlation between the local fitting error of the th data point and each data point within its second neighborhood range and the neighborhood anomaly degree, the more the data points within the second neighborhood range of the th data point conform to the rules, and it is considered that the th data point has a greater degree of adaptation in its second neighborhood range. Therefore, by constructing and a negative correlation relationship, and vice versa.

[0081] In summary, by comprehensively considering the relationship between the local fitting error of the data points within the second neighborhood range of each data point and the neighborhood anomaly degree, and the consistency of each data point with the data points within the second neighborhood range in key features, the adaptation degree of the second neighborhood range of each data point can be accurately evaluated. The higher the adaptation degree, the more effectively the second neighborhood range can screen out high-quality neighborhood data.

[0082] S5: According to the first neighborhood range, second neighborhood range and adaptation degree of each data point, comprehensively determine the third neighborhood range of each data point.

[0083] As of the current step, the first neighborhood range and second neighborhood range of each data point have been obtained. The first neighborhood range is a preset initial range, which provides a basic range for data processing, but it cannot fully adapt to the specific situation of each data point. The second neighborhood range is an appropriate adjustment to the first neighborhood range. However, there are also differences in its reliability and applicability, which need to be measured by the adaptation degree.

[0084] Since the characteristics and environments of different data points are different, it is difficult to accurately capture the true characteristics and internal laws of the data by simply using the first neighborhood range or the second neighborhood range. In order to more accurately reflect the relationship between the data point and the surrounding data and improve the accuracy and reliability of data processing, this step comprehensively considers the first neighborhood range, the second neighborhood range and their adaptation degrees to determine a reasonable third neighborhood range, making subsequent operations such as robust weight calculation based on this range more accurate and reliable.

[0085] Specifically, adjust the second neighborhood range to the third neighborhood range according to the following relational formula:

[0086]

[0087] In this formula, is the third neighborhood range of the th data point, is the adaptation degree of the second neighborhood range of the th data point, is a preset first neighborhood range, is the second neighborhood range of the th data point.

[0088] In this formula, when is larger, it indicates that the second neighborhood range of the th data point is more reliable and stable in reflecting key information such as the relationship between material consumption and project progress, and is more suitable for subsequent calculations. At this time, means that the second neighborhood range will be more used to calculate the third neighborhood range (the final neighborhood range) because this neighborhood range is more preferable. On the contrary, when is smaller, it indicates that the reliability of the second neighborhood range is lower, will be relatively larger, and then in the calculation, more reliance will be placed on the preset first neighborhood range , that is, reducing the reliance on the unreliable second neighborhood range.

[0089] Among them, is a length value. For example, , then starting from the th data point, 20 data points are intercepted forward, and the th data point and the intercepted 20 data points are used as the third neighborhood range of the th data point.

[0090] S6: Determine the robust weight of each data point through the third neighborhood range.

[0091] Perform curve fitting on all data points within the third neighborhood range of each data point to obtain the local curve of each data point. Because data points with similar material consumption and project progress data in space or time often have similar change trends, by using the data within the neighborhood for curve fitting, this correlation can be fully exploited to make the fitted local curve more conform to the actual data distribution, thereby more accurately reflecting the internal law of the data.

[0092] Calculate the difference between the Y - coordinate value corresponding to the data point on the local curve and the original Y - coordinate value of the data point, and take the reciprocal of the absolute value of this difference as the robust weight of the data point. This operation can intuitively reflect the fitting degree of the data point to the local curve. The smaller the difference, the closer the data point is to the local curve, indicating that its change trend is more consistent with other data points in the neighborhood. At this time, the larger the robust weight obtained by taking the reciprocal. On the contrary, the larger the difference, the smaller the robust weight. For example, in coal construction projects, if the robust weight of a certain data point is large, it indicates that the relationship between the material consumption and the project progress represented by this data point is consistent with the overall situation in the neighborhood and is more trustworthy; while data points with smaller robust weights may have abnormal situations and need further attention and analysis.

[0093] This calculation method of robust weights can highlight those data points that fit well with the local curve. In subsequent data processing and analysis, such as performing least - squares fitting and other operations, data points with large robust weights will have a greater impact on the results. This can make the analysis results more inclined to reliable data, improving the accuracy and stability of overall data processing. Taking project progress prediction as an example, using this robust weight calculation method can make the prediction results more dependent on reliable data points, reducing the interference of abnormal data on the prediction results, thereby improving the prediction accuracy.

[0094] S7: Perform least - squares fitting based on the robust weights, and conduct real - time supervision and management of the material consumption and project progress on the current date based on the overall fitting curve.

[0095] In real - time supervision and management, it is crucial to accurately identify abnormalities in material consumption and project progress. By setting reasonable robust weights for data points, the fitting curve can more accurately reflect the characteristics of project data under normal circumstances. When the slope of a data point on a certain date shows an abnormality, since the fitting curve has fully considered the importance of data at different stages, it is more certain to determine that this is a real abnormal situation rather than a misjudgment caused by unreasonable data weights.

[0096] Therefore, take the robust weight of each data point as the weight during least - squares fitting, then perform the fitting operation on all data points (all data points collected from the start of the project to the current date), and finally obtain an overall fitting curve, as Figure 2 shown.

[0097] Subsequently, the process of real - time supervision and management of the material consumption and project progress on the current date based on the overall fitting curve is as Figure 3 shown:

[0098] S71: Obtain all the slopes on the overall fitting curve.

[0099] After obtaining the overall fitting curve, calculate the slope at each data point on the curve to obtain all slope data.

[0100] S72: Use the box plot method to perform outlier detection on all the obtained slope data. The results are as Figure 4 shown. The two middle dashed lines are the normal ranges of the slope. The slope on the far left exceeds the normal range, and this slope is an outlier slope. Compare the slope of the data point for the current date with the normal range of the slope to determine whether it is an outlier.

[0101] S73: Determine whether the slope at the data point corresponding to the current date is abnormal.

[0102] If it is abnormal, then execute step S731: Determine that the material consumption and project progress for the current date are abnormal, and then execute step S7311: Send a warning notice, and conduct a detailed inspection and analysis of the material consumption situation and project progress status for the current date.

[0103] If it is not abnormal, then execute step S732: Determine that the material consumption and project progress for the current date are in a normal state, and then execute step S7321: Do not send a warning notice.

[0104] Through the above operation process, the real-time supervision and management of the material consumption and project progress for the current date are realized. For each day during the project construction process, according to the process described in the present invention, the overall fitting curve of all data points can be obtained, and based on the slope change of the overall fitting curve, the real-time and accurate supervision and management of the material consumption and project progress for each day can be implemented.

[0105] The present invention also provides a supervision and management system for coal construction projects based on big data. The supervision and management system includes a memory and a processor. A computer program is stored on the memory, and the processor executes the computer program to implement the steps of any one of the supervision and management methods to realize the supervision and management of the material consumption and project progress.

Claims

1. A supervision and management method for coal construction projects based on big data, characterized in that, Including: During the construction process of coal construction projects, the total amount of consumed materials and the project progress per day form a data point. All data points from the start of construction to the current date are obtained, and a two-dimensional coordinate system of all data points is constructed with the total amount of consumed materials as the horizontal axis and the project progress as the vertical axis. Presetting the first neighborhood range of all data points; Determining the neighborhood anomaly degree of each data point according to the fluctuation degree of the first neighborhood range of each data point includes: ; In the formula, is the neighborhood anomaly degree of the th data point, is the fluctuation degree of the first neighborhood range of the th data point, is the total number of data points within the first neighborhood range of the th data point, is the original coordinate value of the th data point within the first neighborhood range of the th data point, is the original coordinate value of the th data point within the first neighborhood range of the th data point, is the mean value of the original coordinate values of all data points within the first neighborhood range of the th data point, is the preset first neighborhood range, is the absolute value symbol, is the natural exponential function; Adjusting the first neighborhood range of each data point to a second neighborhood range according to the neighborhood anomaly degree of each data point includes: a preset neighborhood anomaly degree threshold ; , where is the second neighborhood range of the -th data point, is the preset first neighborhood range, is the neighborhood anomaly degree of the -th data point, is the ceiling symbol; Evaluating the adaptability degree of the second neighborhood range of each data point includes: , 、 is the adaptation degree of the second neighborhood range of the -th data point and the total number of data points within the second neighborhood range, 、 is the local fitting error of the -th data point, the -th data point within the second neighborhood range of the -th data point, 、 is the neighborhood abnormality degree of the -th data point, the -th data point within the second neighborhood range of the -th data point, 、 is the standard deviation of the local fitting errors and the standard deviation of the neighborhood abnormality degrees of all data points within the second neighborhood range of the -th data point, 、 is the mean value of the local fitting errors and the mean value of the neighborhood abnormality degrees of all data points within the second neighborhood range of the -th data point, is the absolute value symbol; Calculate the third neighborhood range of each data point: , in the formula, is the third neighborhood range of the th data point, is the adaptation degree of the second neighborhood range of the th data point, is the preset first neighborhood range, is the second neighborhood range of the th data point; Determine the robust weight of each data point according to the third neighborhood range of each data point: perform curve fitting on all data points within the third neighborhood range of each data point to obtain the local curve of each data point, and calculate the coordinate value corresponding to the data point on the local curve and the original coordinate value of the data point. Take the reciprocal of the absolute value of the difference as the robust weight of the data point. Based on the robust weights of all data points, perform least squares fitting to obtain the overall fitting curve, and conduct real-time supervision and management of the material consumption and project progress on the current date according to the slope change of the overall fitting curve.

2. The supervision and management method for coal construction projects based on big data according to claim 1, wherein, The method for real-time supervision and management of material consumption and project progress on the current date according to the slope change of the overall fitting curve is: Obtaining the slope at each data point on the overall fitting curve, and using the box plot method to perform anomaly detection on all slopes; if the slope at the data point on the current date has an anomaly, it is determined that the material consumption and project progress on the current date have an anomaly, a warning notice is issued, and the consumed materials and project progress on the current date are inspected and analyzed; if the slope at the data point on the current date does not have an anomaly, it is determined that the material consumption and project progress on the current date do not have an anomaly, and no warning notice is issued.

3. The coal construction project supervision and management method based on big data according to claim 1, characterized in that, The first neighborhood range, the second neighborhood range, and the third neighborhood range of each data point are all length values, starting from each data point and intercepting forward according to the length value to obtain the neighborhood range corresponding to the data point.

4. The coal construction project supervision and management method based on big data according to claim 1, wherein The local fitting error is determined based on the following method: Perform curve fitting on all data points within the second neighborhood of each data point to obtain the local curve of each data point; calculate the difference between the coordinate value corresponding to the data point on the local curve and the original coordinate value of the data point, and take the absolute value of this difference as the local fitting error of the data point.

5. The method for supervision and management of coal construction projects based on big data according to claim 1, wherein, The fluctuation degree of the first neighborhood range of each data point is determined based on the following method: Calculate the variance of the coordinate values of all data points within the first neighborhood range of each data point , and the variance of the coordinate values of all data points in the coordinate system ; Take the ratio of as the degree of fluctuation of the first neighborhood range of this data point.

6. A supervision and management system for coal construction projects based on big data, characterized in that, The supervision and management system includes a memory and a processor. A computer program is stored on the memory, and the processor executes the computer program to implement the steps of the supervision and management method according to any one of claims 1-5.

Images