An engineering production and operation warning index management system

Abstract

The present invention belongs to the field of engineering production anomaly warning, and discloses an engineering production and operation warning index management system. Through sensors and image recognition, the present invention synchronously considers the materials in static storage and processing, avoids deviation in allowance calculation, accurately reflects the actual consumption of materials, and provides more reliable data for construction progress control and anomaly identification. By quantifying the spatial influence with regional deviation, the present invention accurately locates anomalies from both time and space dimensions, determines the anomaly level according to multiple deviation thresholds for hierarchical classification, provides stepped warnings, can quickly identify risks of different degrees from minor waste to serious process problems, helps managers make efficient decisions, and improves the refined level of engineering management and risk prevention and control capabilities.

Description

Technical Field

[0001] The present invention belongs to the technical field of engineering production anomaly warning, and relates to an engineering production operation warning index management system. Background Art

[0002] Engineering production is a complex process involving a series of activities from project planning to final delivery. In engineering production, material management is of great significance. It accurately obtains material information through technology, analyzes the actual consumption, ensures the continuity of construction, and avoids construction suspension due to material shortage. At the same time, by comparing the actual and theoretical material consumption, it can effectively control costs, prevent waste and overstock. Accurate material management can also ensure the use of qualified materials and guarantee the project quality. Therefore, the research on engineering production operation warning index management is of great significance.

[0003] In the prior art, there are also related solutions for engineering production anomaly warning technology. For example, a Chinese invention patent application for a construction plan and schedule optimization and dispatching management system for a wind farm construction project with the publication number CN114049002A includes: using an intelligent management system to plan and monitor the progress of each part of the project, and then calculating the gap between the current construction progress and the planned construction progress to complete the construction plan with quality and quantity guaranteed. By visually displaying the planned completion ratio of the completed and uncompleted sub-projects in each part of the project and the current construction progress of the total project, it is convenient for project managers to adjust the personnel and material resources in the construction tasks based on these data, and then effectively adjust the current construction progress in real time.

[0004] Although the above solution proposes some solutions for engineering production anomaly warning technology, there are still certain limitations. For example, on the one hand, the prior art solutions lack a comprehensive analysis of static stacking stock and dynamic processing allowance, and cannot accurately identify the actual material consumption.

[0005] On the other hand, the prior art solutions lack a comprehensive analysis and anomaly identification of time-series anomaly detection and spatial correlation anomaly analysis, which may lead to errors in the actual anomaly judgment process and affect the project progress and quality. Summary of the Invention

[0006] In view of this, to solve the problems raised in the above background art, an engineering production operation warning index management system is proposed.

[0007] The object of the present invention can be achieved by the following technical solutions: An engineering production operation warning index management system includes: a material dynamic monitoring module that obtains the static stacking stock of each construction unit based on image recognition technology and detects and analyzes the dynamic processing allowance using a weighing sensor installed on a construction machinery device, and accordingly analyzes the actual material consumption of each construction unit.

[0008] A progress coupling analysis module uses an image acquisition device to collect structural entity images of each construction unit, and adopts a convolutional neural network to identify the completed state of components, and matches the current construction stage of each construction unit according to a preset progress plan model and outputs the corresponding theoretical material consumption.

[0009] A multi-dimensional deviation warning module performs time-series anomaly detection and spatial correlation anomaly analysis on the actual material consumption and the theoretical material consumption, and makes construction anomaly judgments and anomaly level identifications based on the analysis results.

[0010] Compared with the prior art, the beneficial effects of the present invention are as follows: (1) Through sensors and image recognition, the present invention synchronously considers the materials in static storage and processing, avoids deviation in allowance calculation, accurately reflects the real consumption of materials, and provides more reliable data for construction progress control and anomaly identification.

[0011] (2) The present invention uses regional deviation to quantify the spatial influence, accurately locates anomalies from both time and space dimensions, determines the anomaly level according to multiple deviation thresholds, provides stepped warnings, can quickly identify risks of different degrees from minor waste to serious process problems, helps managers make efficient decisions, and improves the refinement level of project management and risk prevention and control capabilities. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0013] Figure 1 It is a schematic diagram of the connection of each module of the system of the present invention.

[0014] Figure 2 It is a schematic diagram of the positioning of the reference distribution position points corresponding to an embodiment provided by the present invention.

[0015] Figure 3 It is a schematic diagram of the division of the reference distribution spacing corresponding to an embodiment provided by the present invention.

[0016] Reference numerals: 1-component, 2-central distribution position, 3-reference distribution position point, 4-construction unit, 5-reference distribution spacing. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0017] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0018] Please refer to Figure 1 As shown, the present invention provides an engineering production and operation early warning index management system, including a material dynamic monitoring module, a progress coupling analysis module, and a multi-dimensional deviation early warning module. Among them, the material dynamic monitoring module is connected to the progress coupling analysis module, and the progress coupling analysis module is connected to the multi-dimensional deviation early warning module.

[0019] The material dynamic monitoring module is used to obtain the static stacking stock of each construction unit based on image recognition technology and detect and analyze the dynamic processing allowance by using the weighing sensors installed on the construction machinery device, and accordingly analyze the actual material consumption of each construction unit.

[0020] The specific analysis method of the static stacking stock is as follows: Use the image acquisition device to obtain the construction images of each construction unit, locate the corresponding material stacking area, use the image processing technology to obtain the material images of each material in the material stacking area, and then compare and match with the pre-saved standard material appearance images to obtain the types of each material, and at the same time obtain the volume of each material.

[0021] Exemplarily, the materials may be steel bars, cement, and yellow sand.

[0022] Combine the volume of each material and the corresponding pre-set reference density to obtain the static stacking stock of each material.

[0023] It should be noted that the reference density is derived from the product manual of the material.

[0024] The specific analysis method of the dynamic processing allowance is as follows: Use the weighing sensors installed on the construction machinery device to obtain the total weight of the processed materials, and at the same time obtain the material ratio of the corresponding processed materials, and perform material quality analysis based on the total weight of the processed materials and the material ratio to obtain the dynamic processing allowance of each material.

[0025] Preferably, the specific method for analyzing the dynamic processing allowance of each material is: Multiply the total weight of the processed materials and the proportion of each material in the material ratio to obtain the dynamic processing allowance of each material.

[0026] It should be noted that the analysis of dynamic processing allowance is extremely crucial in engineering production and operation management. By combining the static stockpile and the material receipt records, through the analysis of dynamic processing allowance, the actual consumption of each material in each construction unit can be accurately obtained, providing accurate data for the evaluation of material usage. Secondly, it helps to control the construction progress in real time.

[0027] The specific process of analyzing the actual material consumption of each construction unit is as follows: Extract the material receipt records at the material storage location, and obtain the construction unit, material type, and receipt quantity corresponding to each material receipt record.

[0028] Classify the material receipt records according to the construction unit to obtain the material receipt records corresponding to each construction unit, and at the same time accumulate the receipt quantities corresponding to the same material type to obtain the total receipt quantity of each material.

[0029] Sum the static stockpile and the dynamic processing allowance of each material in each construction unit to obtain the material allowance corresponding to each material.

[0030] Conduct a net consumption calculation of the total receipt quantity and the material allowance of each material in each construction unit to obtain the actual material consumption of each material in each construction unit.

[0031] It should be noted that the material allowance consists of the static stockpile and the dynamic processing allowance. The total receipt quantity is the cumulative quantity of materials received by each construction unit extracted from the material storage location. Subtracting the material allowance from the total receipt quantity can obtain the actual quantity of materials consumed, that is, the actual material consumption. For example, a construction unit received 100 tons of cement, and after calculation, the material allowance is 30 tons. Then the actual material consumption of cement in this construction unit is 70 tons. Accurate actual material consumption data helps to analyze the material usage efficiency of the construction unit, judge whether there is waste or material shortage, and provide an important basis for subsequent material procurement, allocation, and construction progress adjustment.

[0032] It should be noted that the present invention synchronously considers the materials in static storage and processing through sensors and image recognition, avoids calculation deviation of the allowance, accurately reflects the real consumption of materials, and provides more reliable data for the control of construction progress and the identification of abnormal situations.

[0033] The progress coupling analysis module is used to collect the structural entity images of each construction unit by using an image acquisition device, identify the completion status of components by using a convolutional neural network, match the current construction stage of each construction unit according to a preset progress plan model, and output the corresponding theoretical material consumption.

[0034] The specific process of identifying the completion status of components is as follows: Based on the structural entity images of each construction unit, construct the actual contour images corresponding to each component, and at the same time obtain the expected contour images corresponding to each component based on the construction plan.

[0035] It should be explained that the actual contour images of each component are constructed based on the structural entity images of the construction units, which reflect the true shapes of the components at the current construction stage; the expected contour images are obtained according to the construction plan and represent the shapes that the components should present under the ideal construction progress.

[0036] Compare the actual contour images of each component with the corresponding expected contour images, and mark the parts that coincide between the actual contour images of each component and the corresponding expected contour images as effective contour images, which are then used as the completion status of each component.

[0037] It should be noted that when comparing the actual contour image and the expected contour image, the overlapping part is the effective contour image. For example, when building a house, the expected contour of a beam is a standard rectangle, and the contour of the beam in actual construction may not be completely regular due to construction errors and other factors. After comparing the two, the parts with the same shape and overlap are the effective contour images. The effective contour images are directly used as the basis for the completion status of each component.

[0038] The specific analysis method of the theoretical material consumption is as follows: Compare the completed contour volumes of the effective contour images of each component with the expected contour images of the corresponding components in the construction plan to obtain the completion degrees of each component.

[0039] Preferably, the specific analysis method of the completion degrees of each component is as follows: Divide the volume of the effective contour image by the volume of the expected contour image, and the obtained value is the completion degree of the component.

[0040] Obtain the types and theoretical consumption amounts of each material corresponding to each component based on the construction plan.

[0041] Mark the materials that are not needed and are outside the effective contour images of each component as the materials that have been used up, and at the same time match them with the theoretical consumption amounts of each material of each component to obtain the theoretical consumption amounts of each material that has been used up for each component.

[0042] Mark the materials that are still needed and are outside the effective contour images of each component as the materials to be used, and then match them with the theoretical consumption amounts of each material of each component to obtain the complete component theoretical consumption amounts of each material to be used. Furthermore, conduct a fusion analysis in combination with the completion degrees of each component to obtain the theoretical consumption amounts of each material to be used for each component.

[0043] It should be further explained that classifying materials and calculating their theoretical consumption helps to accurately master the usage and demand prediction of materials, providing an important basis for construction management. Specifically: (1) Calculation of the theoretical consumption of materials that have been used up: After the effective contour images of each component are constructed, the materials outside the effective contour images and not required for subsequent construction are marked as materials that have been used up. The actual usage of this part of the materials has ended. By matching it with the theoretical consumption of each material for each component in the construction plan, it is possible to determine how much these materials that have been used up should consume at the theoretical level. For example, when building a building, some materials used for temporary support structures are no longer used after the effective contour of the main structure is determined. By matching with the theoretical consumption, the quantity they should consume theoretically can be known.

[0044] (2) Calculation of the theoretical consumption of materials to be used: Outside the effective contour image, the materials required for subsequent construction are materials to be used. First, match according to the construction plan to obtain the theoretical consumption of these materials to be used in the complete components. Since the components have a certain degree of completion, not all materials to be used need to be immediately put into use in full. Therefore, by combining the degree of completion of each component for integrated analysis, the actual required theoretical consumption of each material to be used for each component at the current construction progress can be obtained. For example, if a component has a completion degree of 50% and the complete component originally requires 100 units of a certain material to be used, then considering the degree of completion, the current required theoretical consumption of this material is 50 units.

[0045] Classify and sum up the theoretical consumption of materials that have been used up for each component and the theoretical consumption of materials to be used to obtain the theoretical material consumption of each material for each construction unit.

[0046] The multi-dimensional deviation warning module is used to perform time-series anomaly detection and spatial correlation anomaly analysis on the actual material consumption and the theoretical material consumption, and make construction anomaly judgments and anomaly level identifications based on the analysis results.

[0047] The specific analysis process of the time-series anomaly detection is as follows: Based on the preset adaptive sliding time window length, set several monitoring periods, extract the theoretical material consumption and the actual material consumption of each construction unit corresponding to each material within each monitoring period, and then conduct deviation analysis to obtain the absolute deviation of the actual material consumption relative to the theoretical material consumption. Perform mean analysis on each absolute deviation to obtain the material consumption deviation of each construction unit for each monitoring period.

[0048] It should be noted that the length of the adaptive sliding time window is a flexible time setting parameter. The time window can be set according to the actual engineering situation and management requirements, and multiple monitoring periods can be divided based on it. For example, if the length of the adaptive sliding time window is set to one week, then monitoring periods such as the first week and the second week can be divided in sequence. This adaptive setting can better adapt to the characteristics of different construction stages because the material consumption patterns may vary in different stages.

[0049] Preferably, the specific method for performing deviation analysis is as follows: Calculate the difference between the actual material consumption of each material and the theoretical material consumption, and then calculate the ratio with the theoretical material consumption to obtain the absolute deviation of the actual material consumption relative to the theoretical material consumption.

[0050] It should be explained that the mean analysis of each absolute deviation is to eliminate the contingency of a single material or single measurement deviation, and comprehensively consider the overall deviation degree of all material consumption in a certain monitoring period of a construction unit. Because the deviation of a single material may be affected by special factors and cannot represent the material consumption situation of the entire construction unit. By taking the average value, a more representative value, that is, the material consumption deviation, can be obtained.

[0051] Compare the end time of each monitoring period with the end time of the current monitoring period to obtain the time sequence deviation reference coefficient of each monitoring period.

[0052] Preferably, the system will set multiple monitoring periods based on the preset length of the adaptive sliding time window. Each monitoring period has a corresponding end time, and the current monitoring period is the period that is being analyzed. Compare the end times of the previous monitoring periods with the end time of the current monitoring period. This comparison operation can reflect the relative position relationship of different monitoring periods on the time axis. For example, the current monitoring period is the 5th week, and the end time is the end of the 5th week. The end time of the previous 3rd week monitoring period is the end of the 3rd week, and there is a time interval between them.

[0053] A method for calculating the time sequence deviation reference coefficient: Calculate the time interval of each monitoring period relative to the current monitoring period by calculating the difference between the end time of each monitoring period and the end time of the current monitoring period, and calculate the ratio of the preset reference time interval to the time interval of each monitoring period relative to the current monitoring period to obtain the time sequence deviation reference coefficient of each monitoring period.

[0054] It should be explained that the analysis of the time sequence deviation reference coefficient is used to measure the time difference between monitoring periods. By calculating this difference, the referenceability of the change in material consumption between different periods can be judged. Because the material consumption pattern may change over time.

[0055] The material consumption deviation and the time series deviation reference coefficient of each construction unit in each monitoring period are linearly weighted and comprehensively analyzed to obtain the reference time series material deviation of each construction unit. Furthermore, the actual material consumption and the theoretical material consumption of each material of each construction unit are combined to perform time series material deviation analysis to obtain the adjacent time series material deviation of each construction unit.

[0056] Preferably, the specific analysis method of the adjacent time series material deviation is as follows: Calculate the mean value of the absolute deviation of the actual material consumption and the theoretical material consumption of each material of each construction unit to obtain the absolute material deviation of each construction unit. Then, calculate the difference between the reference time series material deviation and the absolute material deviation of each construction unit, take the absolute value, and then calculate the ratio with the reference time series material deviation to obtain the adjacent time series material deviation.

[0057] The specific analysis method of the spatial correlation anomaly analysis is as follows: Please refer to Figure 2 As shown, obtain the central distribution position 2 of each component 1 of each construction unit, and then locate the reference distribution position point 3 of each construction unit.

[0058] Please refer to Figure 3 As shown, connect the reference distribution position points 3 of each construction unit 4 with those of other construction units 4 to obtain the reference distribution distance 5 between each construction unit 4 and other construction units 4. Then, compare it with the pre-set reference distribution distance threshold to identify the adjacent construction units of each construction unit.

[0059] Based on the analysis of the reference distribution distance between each construction unit and its corresponding adjacent construction units, obtain the regional deviation reference coefficient of each construction unit corresponding to each adjacent construction unit.

[0060] Calculate the absolute deviation of the actual material consumption and the theoretical material consumption of each material of each construction unit to obtain the absolute deviation of the actual material consumption relative to the theoretical material consumption.

[0061] Linearly weight and fuse the regional deviation reference coefficient of each adjacent construction unit and the absolute deviation of the actual material consumption of each material relative to the theoretical material consumption to obtain the reference regional material deviation of each material. Then, compare and select the maximum reference regional material deviation as the reference regional material deviation of the corresponding construction unit.

[0062] Analyze the deviation between the reference regional material deviation of each construction unit and the absolute deviation of the actual material consumption relative to the theoretical material consumption to obtain the adjacent regional material deviation of each construction unit.

[0063] It should be noted that the specific calculation method of the adjacent regional material deviation can refer to the calculation method of the adjacent time series material deviation.

[0064] The specific analysis method for judging construction anomalies is as follows: The absolute deviation of the actual material consumption of each material in each construction unit relative to the theoretical material consumption is recorded as the absolute material deviation, and the maximum absolute material deviation is taken as the absolute material deviation of each construction unit.

[0065] The absolute material deviation, adjacent time-series material deviation, and adjacent area material deviation of each construction unit are respectively compared with the preset absolute material deviation threshold, adjacent time-series material deviation threshold, and adjacent area material deviation threshold to obtain the judgment result of whether there are construction anomalies in each construction unit.

[0066] Specifically, if the absolute material deviation of a certain construction unit is greater than the absolute material deviation threshold, it is judged that there are construction anomalies in this construction unit.

[0067] The specific analysis of the anomaly level identification is as follows: If the absolute material deviation, adjacent time-series material deviation, and adjacent area material deviation of a certain construction unit are all greater than the corresponding absolute material deviation threshold, adjacent time-series material deviation threshold, and adjacent area material deviation threshold, the specific anomaly level is identified as a first-level anomaly.

[0068] It should be noted that a first-level anomaly means that this construction unit has seriously deviated from the normal range in terms of the actual and theoretical comparison of material consumption, time-series changes, and spatial correlation. For example, in terms of material consumption, the actual usage far exceeds the theoretical usage, and there are significant differences in the time dimension compared with previous cycles and also in space compared with adjacent construction units. This indicates that there are very likely serious problems in the construction process, such as construction process errors, material management chaos, etc., and comprehensive and in-depth measures need to be taken immediately for rectification.

[0069] If the absolute material deviation of a certain construction unit is greater than the absolute material deviation threshold, and at the same time, one of the adjacent time-series material deviation and adjacent area material deviation is greater than the corresponding threshold, the specific anomaly level is identified as a second-level anomaly.

[0070] It should be noted that a second-level anomaly indicates that there are obvious problems in the construction unit. It may be that there are anomalies in a certain key link during the material usage process, such as serious material waste, or there are large fluctuations in the material consumption law in terms of time or space. However, compared with the first-level anomaly, the severity of the problem is slightly lower. At this time, key investigations and adjustments need to be carried out for the aspects with deviations to avoid the further deterioration of the problem.

[0071] If the absolute material deviation of a certain construction unit is greater than the absolute material deviation threshold, and at the same time, the adjacent time-series material deviation and adjacent area material deviation are both less than the corresponding thresholds, the specific anomaly level is identified as a third-level anomaly.

[0072] It should be noted that the third-level anomaly indicates that although there is an anomaly in the overall comparison of material consumption in the current construction unit, the fluctuations in the time and space dimensions are relatively small. It may be due to improper local material use, such as the material loss in a certain construction link exceeding expectations, but it has not had a great impact on the overall construction rhythm and surrounding construction units. In this regard, targeted local inspections and optimizations can be carried out to prevent the expansion of abnormal situations.

[0073] No anomalies were identified in other cases.

[0074] It should be noted that the present invention quantifies the spatial influence by means of regional deviation, accurately locates anomalies from both the time and space dimensions, determines the anomaly level according to multiple deviation thresholds for classification, provides stepped early warnings, can quickly identify risks of different degrees from minor waste to serious process problems, helps managers make efficient decisions, and improves the refined level of project management and the risk prevention and control ability.

[0075] The above content is only an example and illustration of the concept of the present invention. Those skilled in the art of this technology can make various modifications or supplements to the described specific embodiments or use similar ways to replace them. As long as they do not deviate from the concept of the invention or exceed the scope defined by the present invention, they should fall within the protection scope of the present invention.

Claims

1. An engineering production and operation warning index management system, characterized in that, Including: A material dynamic monitoring module, which obtains the static stacking inventory of each construction unit based on image recognition technology, and uses the weighing sensors installed on the construction device to detect and analyze the dynamic processing allowance, and accordingly analyzes the actual material consumption of each construction unit; A progress coupling analysis module, which collects the structural entity images of each construction unit, uses a convolutional neural network to identify the completion status of components, matches the current construction stage of each construction unit according to the preset progress plan model, and outputs the corresponding theoretical material consumption; A multi-dimensional deviation warning module, which performs time-series anomaly detection and spatial correlation anomaly analysis on the actual material consumption and the theoretical material consumption, and makes construction anomaly judgments and anomaly level identifications based on the analysis results.

2. The engineering production and operation warning index management system according to claim 1, characterized in that: The specific analysis method of the static stacking inventory is as follows: Obtain the construction images of each construction unit, locate the corresponding material stacking area, use image processing technology to obtain the material images of each material in the material stacking area, and then compare and match them with the pre-saved standard material appearance images to obtain the types of each material, and at the same time obtain the volume of each material; Combine the volume of each material and the corresponding pre-set reference density to obtain the static stacking inventory of each material.

3. The engineering production and operation warning index management system according to claim 2, wherein: The specific analysis method of the dynamic processing allowance is as follows: Use the weighing sensors installed on the construction machinery device to obtain the total weight of the processed materials, and at the same time obtain the material ratio of the corresponding processed materials, and perform material quality analysis based on the total weight of the processed materials and the material ratio to obtain the dynamic processing allowance of each material.

4. The engineering production and operation warning index management system according to claim 3, wherein: The specific process of analyzing the actual material consumption of each construction unit is as follows: Extract the material receiving records at the material storage location, and obtain the construction unit, material type, and receiving quantity corresponding to each material receiving record; Classify the material receiving records according to the construction unit to obtain the material receiving records corresponding to each construction unit, and at the same time accumulate the receiving quantities corresponding to the same material type to obtain the total receiving quantity of each material; Sum the static stacking inventory and the dynamic processing allowance of each material of each construction unit to obtain the material allowance of each material; Conduct net consumption accounting on the total receiving quantity and the material allowance of each material of each construction unit to obtain the actual material consumption of each material of each construction unit.

5. The engineering production and operation warning index management system according to claim 1, characterized in that: The specific process of identifying the completion status of components is as follows: Construct the actual contour images of each component based on the structural entity images of each construction unit, and at the same time obtain the expected contour images of each component based on the construction plan; Compare the actual contour images of each component with the corresponding expected contour images, and record the overlapping part of the actual contour images of each component with the corresponding expected contour images as the effective contour images, and then use them as the completion status of each component.

6. The engineering production and operation warning index management system according to claim 5, characterized in that: The specific analysis method of the theoretical material consumption is as follows: Compare the completed contour volumes of the effective contour images of each component with the expected contour images of the corresponding components in the construction plan to obtain the completion degree of each component; Obtain the types and theoretical consumption of each material corresponding to each component based on the construction plan; Mark the materials that do not need to be used other than the effective contour images of each component as materials that have been used up, and at the same time match them with the theoretical consumption of each material of each component to obtain the theoretical consumption of each used-up material of each component. The materials that still need to be used other than the effective contour images of each component are recorded as materials to be used. Then, they are matched with the theoretical consumption of each material of each component to obtain the complete component theoretical consumption of each material to be used. Furthermore, by combining the completion degrees of each component, a fusion analysis is carried out to obtain the theoretical consumption of each material to be used for each component; The theoretical consumption of each used material of each component and the theoretical consumption of each material to be used are classified and summed to obtain the theoretical material consumption of each material for each construction unit.

7. The engineering production and operation warning index management system according to claim 1, wherein: The specific analysis process of the above-mentioned time series anomaly detection is as follows: Based on the preset adaptive sliding time window length, several monitoring periods are set. The theoretical material consumption and the actual material consumption of each material corresponding to each construction unit in each monitoring period are extracted. Then, a deviation analysis is carried out to obtain the absolute deviation of the actual material consumption relative to the theoretical material consumption. The mean analysis of each absolute deviation is carried out to obtain the material consumption deviation of each construction unit in each monitoring period; The end time of each monitoring period is compared with the end time of the current monitoring period to obtain the time series deviation reference coefficient of each monitoring period; The material consumption deviation and the time series deviation reference coefficient of each construction unit in each monitoring period are fused and linearly weighted for comprehensive analysis to obtain the reference time series material deviation of each construction unit. Furthermore, by combining the actual material consumption and the theoretical material consumption of each material of each construction unit, a time series material deviation analysis is carried out to obtain the adjacent time series material deviation of each construction unit.

8. The engineering production and operation warning index management system according to claim 7, characterized in that: The specific analysis method of the above-mentioned spatial correlation anomaly analysis is as follows: The central distribution positions of each component of each construction unit are obtained, and then the reference distribution position points of each construction unit are located; The reference distribution position points of each construction unit and other construction units are connected to obtain the reference distribution spacing between each construction unit and other construction units. Then, it is compared with the preset reference distribution spacing threshold to identify the adjacent construction units of each construction unit; Based on the reference distribution spacing between each construction unit and its corresponding adjacent construction units, the regional deviation reference coefficient of each construction unit corresponding to each adjacent construction unit is analyzed; The absolute deviation of the actual material consumption relative to the theoretical material consumption of each material of each construction unit is calculated; The regional deviation reference coefficient of each adjacent construction unit and the absolute deviation of the actual material consumption relative to the theoretical material consumption of each material are linearly weighted and fused for analysis to obtain the reference regional material deviation of each material. Then, the maximum reference regional material deviation is selected by comparison as the reference regional material deviation of the corresponding construction unit; The deviation analysis is carried out on the reference regional material deviation of each construction unit and the absolute deviation of the actual material consumption relative to the theoretical material consumption to obtain the adjacent regional material deviation of each construction unit.

9. The engineering production and operation early warning index management system according to claim 8, characterized in that: The specific analysis method of the above-mentioned construction anomaly judgment is as follows: The absolute deviation of the actual material consumption of each material of each construction unit relative to the theoretical material consumption is recorded as the absolute material deviation, and the maximum absolute material deviation is used as the absolute material deviation of each construction unit; Compare the absolute material deviation, adjacent time-series material deviation, and adjacent area material deviation of each construction unit with the preset absolute material deviation threshold, adjacent time-series material deviation threshold, and adjacent area material deviation threshold respectively to obtain the judgment result on whether there is construction abnormality in each construction unit.

10. The engineering production and operation warning index management system according to claim 9, characterized in that: The specific analysis of the abnormal level identification is as follows: If the absolute material deviation, adjacent time-series material deviation, and adjacent area material deviation of a certain construction unit are all greater than the corresponding absolute material deviation threshold, adjacent time-series material deviation threshold, and adjacent area material deviation threshold, identify the specific abnormal level as a first-level abnormality; If the absolute material deviation of a certain construction unit is greater than the absolute material deviation threshold, and at the same time one of the adjacent time-series material deviation and adjacent area material deviation is greater than the corresponding threshold, identify the specific abnormal level as a second-level abnormality; If the absolute material deviation of a certain construction unit is greater than the absolute material deviation threshold, and at the same time the adjacent time-series material deviation and adjacent area material deviation are both less than the corresponding thresholds, identify the specific abnormal level as a third-level abnormality; In other cases, it is identified that there is no abnormality.

Images