Cost prediction collaborative analysis method and system based on data analysis

Abstract

The invention is suitable for the technical field of road infrastructure maintenance management, and provides a cost prediction collaborative analysis method and system based on data analysis, and the method comprises the steps: obtaining a real-time collaborative cost element set of a specific road segment shielded by an upper structure, historical road segment data in a historical maintenance period, and corresponding maintenance records, screening historical maintenance samples consistent with the road section data in the preset maintenance period; extracting the historical deterioration degree of the specific road section in the historical maintenance sample, and taking the average value as the average deterioration degree of the specific road section in the preset maintenance period. Refined prediction of the maintenance cost of a specific road section shielded by an upper structure can be realized. The specific road section is divided into the air inlet section, the middle section and the air outlet section, the transverse air speed distribution and the evaporation rate difference are combined, the dry and wet state changes of all the sections are quantified, and the problem that in the prior art, local airflow disturbance and heterogeneous degradation are ignored, and consequently the cost prediction error is large is solved.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of road infrastructure maintenance management, and particularly relates to a cost prediction collaborative analysis method and system based on data analysis. BACKGROUND

[0002] At present, the maintenance cost prediction of road facilities is usually based on the pavement structure deterioration model and historical maintenance data, and the pavement service life and maintenance cycle are predicted by statistical analysis method or empirical model. The existing technology adopts the average or partition weighting method to evaluate the pavement deterioration degree, and estimates the maintenance cost accordingly. However, this kind of method generally assumes that the pavement is relatively uniform under the action of environmental factors, and ignores the local microclimate difference caused by the shelter of bridge, tunnel or elevated structure, especially the inhomogeneity of wind speed distribution, evaporation rate and dry-wet cycle frequency, resulting in low prediction accuracy of the model under complex environment. In addition, the traditional model usually considers the factors of material aging and traffic load statically, and lacks the response ability to the dynamic characteristics of environment (such as the change of rainfall and ventilation conditions).

[0003] In the road section sheltered by the upper structure, the air flow is limited, the wind speed is significantly reduced compared with the open area and the transverse distribution is uneven, and there is obvious evaporation difference between the inlet section, the middle section and the outlet section. This non-uniform ventilation condition leads to spatial difference of pavement dry-wet state, some areas are long-term humid, some areas are frequently dry, and then produces temperature and humidity stress difference, accelerates the local deterioration of materials. In the prior art, the maintenance cost prediction is still based on the average deterioration index of the whole road section, and the inhomogeneous deterioration law caused by local wind speed shear, evaporation difference and dry-wet spatial and temporal variation cannot be fully reflected, resulting in deviation of the prediction result from the actual maintenance demand, and the problems of over-repair or delayed repair are easy to appear. SUMMARY

[0004] The purpose of the present application is to provide a cost prediction collaborative analysis method and system based on data analysis, which aims to solve the problems proposed in the background.

[0005] The present application is realized in the following way: a cost prediction collaborative analysis method based on data analysis, the method comprising:

[0006] obtaining a real-time collaborative cost element set of a specific road section sheltered by the upper structure, historical road section data and corresponding maintenance records in the historical maintenance cycle, and screening the historical maintenance samples consistent with the road section data in the preset maintenance cycle;

[0007] extracting the historical deterioration degree of the specific road section in the historical maintenance sample, and taking the average value as the average deterioration degree of the specific road section in the preset maintenance cycle;

[0008] A specific road segment is pre-divided into an air intake segment, a middle segment, and an air outlet segment. Based on the road segment data, the rate of change of the wet-dry ratio after each wet cycle in each segment within the preset maintenance cycle is obtained, as well as the standard rate of change of the wet-dry ratio in non-specific road segments. The rate of change of the wet-dry ratio is calculated based on the ratio of the dry area to the wet area determined by the difference in lateral wind speed distribution and evaporation rate.

[0009] Based on the rate of change of the wet-dry ratio of each segment, a wet-dry ratio change curve is plotted, and the slope of the curve is obtained. When the absolute value of the slope is greater than the preset threshold, the difference between the rate of change of the wet-dry ratio of each segment and the standard rate of change of the wet-dry ratio is used as the correction factor for each segment.

[0010] The degradation level of each segment is calculated by using the correction factor and the average degradation level. The maintenance cost of each segment is calculated by combining the real-time collaborative cost element set. The total maintenance cost prediction value for the preset maintenance cycle is obtained by summing them up.

[0011] As a further limitation of the technical solution of this invention embodiment, a specific road segment is pre-divided into an air intake segment, a middle segment, and an air outlet segment. Based on the road segment data, the dry-wet ratio change rate of each segment after each wet period within a preset maintenance cycle, and the standard dry-wet ratio change rate of non-specific road segments are obtained. The dry-wet ratio change rate is calculated based on the ratio of the dry area to the wet area determined by the difference in lateral wind speed distribution and evaporation rate. The steps include:

[0012] A specific road section is pre-divided into an air intake section, a middle section, and an air outlet section. Each section is further divided into several sub-segments, and the cross wind speed, temperature, and humidity data corresponding to each sub-segment within the preset maintenance cycle are obtained.

[0013] The convective heat transfer coefficient between air and road surface is determined based on the cross wind speed corresponding to each segment; the saturated water vapor pressure difference of air is determined based on the temperature and humidity data corresponding to each segment; the evaporation rate of each segment is obtained by multiplying the convective heat transfer coefficient and the saturated water vapor pressure difference corresponding to each segment.

[0014] Based on the evaporation rate of each segment, the evaporation rate distribution field of each segment surface is constructed by spatial interpolation, and the evaporation rate of each segment is compared with the preset evaporation rate threshold.

[0015] When the evaporation rate of a segment is greater than the preset evaporation rate threshold, it is determined to be a dry zone; when the evaporation rate of a segment is less than the preset evaporation rate threshold, it is determined to be a wet zone.

[0016] The areas of dry and wet zones in each segment are counted, and the ratio of the dry area to the wet area is calculated as the rate of change of the dry-wet ratio for that segment.

[0017] Obtain the standard wet-dry ratio change rate for non-specific road sections.

[0018] As a further limitation of the technical solution of this invention, the step of plotting the wet-dry ratio change curve based on the wet-dry ratio change rate of each segment, obtaining the slope of the curve, and using the difference between the wet-dry ratio change rate of each segment and the standard wet-dry ratio change rate as the correction factor for each segment when the absolute value of the slope is greater than a preset threshold includes:

[0019] Collect the dry-wet ratio change rate data for each segment within the preset maintenance cycle, recorded in chronological order.

[0020] Based on the dry-wet ratio change rate data, plot the dry-wet ratio change curves for each segment, and calculate the slope of the curves using the difference in the dry-wet ratio change rate between adjacent time points.

[0021] When the absolute value of the slope exceeds a preset threshold, the corresponding abnormal fluctuation segment is identified.

[0022] Calculate the difference between the rate of change of the wet-dry ratio of each segment within the abnormal fluctuation range and the standard rate of change of the wet-dry ratio, and determine the absolute value of the difference as the correction factor for that segment within the abnormal fluctuation range;

[0023] When the absolute value of the slope does not exceed the threshold, the correction factor is set to zero.

[0024] As a further limitation of the technical solution of this invention, the steps of calculating the degradation degree of each segment by using the correction factor of each segment and the average degradation degree, calculating the maintenance cost of each segment by combining the real-time collaborative cost element set, and accumulating the results to obtain the total maintenance cost prediction value for the preset maintenance cycle include:

[0025] The average value obtained by weighting the correction factors of each segment within the preset maintenance cycle is used as the weight coefficient to weight the average deterioration degree of a specific road segment, thereby obtaining the deterioration degree of each segment.

[0026] Obtain the real-time collaborative cost element set for each segment within the preset maintenance cycle. The collaborative cost element set includes labor costs, material costs, equipment usage costs, energy consumption costs, and traffic occupancy costs.

[0027] The maintenance cost of each segment is obtained by weighting the degradation degree of each segment with the real-time collaborative cost factor set.

[0028] The maintenance costs of each section are summed up to obtain the predicted total maintenance cost of a specific road section within a preset maintenance cycle.

[0029] As a further limitation of the technical solution of the present invention, the specific road section obstructed by the superstructure includes the area under the viaduct, the area under the overpass, or other road sections with partial obstruction structures.

[0030] A cost prediction and collaborative analysis system based on data analysis, characterized in that the system comprises:

[0031] The data acquisition module is used to acquire the real-time collaborative cost element set of a specific road segment that is blocked by the superstructure, historical road segment data within the historical maintenance cycle and corresponding maintenance records, and to filter historical maintenance samples that are consistent with the road segment data within the preset maintenance cycle.

[0032] The degradation degree extraction module is used to extract the historical degradation degree of a specific road segment from the historical maintenance samples, and use its average value as the average degradation degree of the specific road segment within the preset maintenance cycle;

[0033] The wet-dry ratio calculation module is used to pre-divide a specific road segment into an air intake segment, a middle segment, and an air outlet segment. Based on the road segment data, it obtains the wet-dry ratio change rate of each segment after each wet cycle within a preset maintenance period, as well as the standard wet-dry ratio change rate of non-specific road segments. The wet-dry ratio change rate is calculated based on the ratio of the dry area to the wet area determined by the difference in lateral wind speed distribution and evaporation rate.

[0034] The correction factor determination module is used to draw the dry-wet ratio change curve based on the dry-wet ratio change rate of each segment, obtain the slope of the curve, and when the absolute value of the slope is greater than the preset threshold, the difference between the dry-wet ratio change rate of each segment and the standard dry-wet ratio change rate is used as the correction factor for each segment.

[0035] The cost prediction module is used to calculate the degradation degree of each segment by using the correction factor of each segment and the average degradation degree, and to calculate the maintenance cost of each segment by combining the real-time collaborative cost element set, and to accumulate the total maintenance cost prediction value of the preset maintenance cycle.

[0036] As a further limitation of the technical solution of this embodiment of the invention, the wet-dry ratio calculation module specifically includes:

[0037] The road segment zoning unit is used to pre-divide a specific road segment into an air intake segment, a middle segment, and an air outlet segment, and further divide each segment into several sub-segments to obtain the lateral wind speed, temperature, and humidity data corresponding to each sub-segment within a preset maintenance cycle.

[0038] The evaporation rate calculation unit is used to determine the convective heat transfer coefficient between the air and the road surface based on the cross wind speed corresponding to each segment; to determine the saturated water vapor pressure difference of the air based on the temperature and humidity data corresponding to each segment; and to multiply the convective heat transfer coefficient and the saturated water vapor pressure difference corresponding to each segment to obtain the evaporation rate of each segment.

[0039] The distribution field construction unit is used to construct the evaporation rate distribution field of each segment surface through spatial interpolation based on the evaporation rate of each segment, and compare the evaporation rate of each segment with the preset evaporation rate threshold.

[0040] The area determination unit is used to determine a dry area when the evaporation rate of a segment is greater than a preset evaporation rate threshold, and to determine a wet area when the evaporation rate of a segment is less than the preset evaporation rate threshold.

[0041] The ratio calculation unit is used to count the area of ​​the dry and wet areas of each segment and calculate the ratio of the dry area to the wet area as the dry-wet ratio change rate of that segment.

[0042] The average value calculation unit is used to obtain the standard wet-dry ratio change rate of non-specific road sections.

[0043] As a further limitation of the technical solution of this embodiment of the invention, the correction factor determination module specifically includes:

[0044] The data acquisition unit is used to collect the dry-wet ratio change rate data recorded in chronological order for each segment within a preset maintenance cycle.

[0045] The curve generation unit is used to draw the dry-wet ratio change curves for each segment based on the dry-wet ratio change rate data, and to calculate the slope of the curve using the difference in the dry-wet ratio change rate between adjacent time points.

[0046] An anomaly detection unit is used to determine the corresponding abnormal fluctuation segment when the absolute value of the slope exceeds a preset threshold.

[0047] The correction factor calculation unit is used to calculate the difference between the rate of change of the dry-wet ratio of each segment in the abnormal fluctuation range and the standard rate of change of the dry-wet ratio, and to determine the absolute value of the difference as the correction factor of that segment in the abnormal fluctuation range.

[0048] The threshold control unit sets the correction factor to zero when the absolute value of the slope does not exceed the threshold.

[0049] As a further limitation of the technical solution of this embodiment of the invention, the cost prediction module specifically includes:

[0050] The deterioration degree correction unit is used to take the average value of the correction factors of each section within the preset maintenance cycle as the weight coefficient, and then use it to correct the average deterioration degree of a specific road section to obtain the deterioration degree of each section.

[0051] The element acquisition unit is used to acquire the real-time collaborative cost element set of each segment within a preset maintenance cycle. The collaborative cost element set includes labor cost, material cost, equipment usage cost, energy consumption cost, and traffic occupation cost.

[0052] The cost calculation unit is used to calculate the maintenance cost of each segment by weighting the degree of deterioration of each segment with the real-time collaborative cost element set.

[0053] The cost aggregation unit is used to sum up the maintenance costs of each section to obtain the predicted total maintenance cost of a specific road section within a preset maintenance cycle.

[0054] As a further limitation of the technical solution of the present invention, the specific road section obstructed by the superstructure includes the area under the viaduct, the area under the overpass, or other road sections with partial obstruction structures.

[0055] Compared with the prior art, the present invention has the following beneficial effects:

[0056] This invention achieves refined prediction of maintenance costs for specific road sections obstructed by superstructures by introducing a dynamic correction mechanism based on the rate of change of the wet-dry ratio. By dividing the specific road section into air intake, intermediate, and exhaust sections, and combining the differences in lateral wind speed distribution and evaporation rate, the changes in wet-dry state of each section are quantified. Abnormal fluctuation zones are then extracted, and a correction factor model is established, thus solving the problem of large cost prediction errors caused by neglecting local airflow disturbances and heterogeneous degradation in existing technologies. Based on historical degradation data and integrating a real-time collaborative cost element set, this method achieves synergistic analysis of physical degradation characteristics and economic factors, resulting in more dynamic and adaptable predictions. This invention can be widely applied to maintenance decisions for areas such as roads under urban overpasses, tunnel entrances and exits, and obstructed traffic facilities. It can provide a scientific basis for the periodic maintenance of urban roads, achieving optimal cost allocation and precise resource scheduling, and has significant engineering promotion value and intelligent management application prospects. Attached Figure Description

[0057] Figure 1 A flowchart of the method provided in the embodiments of the present invention;

[0058] Figure 2 This is a flowchart illustrating the determination of the rate of change of the wet-dry ratio in the method provided in this embodiment of the invention;

[0059] Figure 3 This is a flowchart illustrating the determination of the correction factor in the method provided in this embodiment of the invention;

[0060] Figure 4 This is a flowchart illustrating the method for determining the total maintenance cost provided in this embodiment of the invention;

[0061] Figure 5 Application architecture diagram of the system provided in the embodiments of the present invention;

[0062] Figure 6 This is a structural block diagram of the wet-dry ratio calculation module in the system provided in the embodiment of the present invention;

[0063] Figure 7 This is a structural block diagram of the correction factor determination module in the system provided in the embodiments of the present invention;

[0064] Figure 8 This is a structural block diagram of the cost prediction module in the system provided in an embodiment of the present invention. Detailed Implementation

[0065] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0066] Figure 1 A flowchart of the method provided by an embodiment of the present invention is shown.

[0067] Specifically, a cost prediction collaborative analysis method based on data analysis includes the following steps:

[0068] Step S100: Obtain the real-time collaborative cost element set of a specific road segment obscured by the superstructure, historical road segment data within the historical maintenance cycle, and corresponding maintenance records, and filter historical maintenance samples that are consistent with the road segment data within the preset maintenance cycle.

[0069] In this embodiment of the invention, the "specific road section obstructed by superstructures" refers to a road section with elevated bridges, interchanges, bridge approach roads, building eaves, utility tunnels, or other fixed superstructures above the road. Because these superstructures obstruct natural wind, sunlight, and rainwater evaporation, the ventilation conditions, temperature and humidity distribution, solar radiation, and evaporation rate of this road section differ significantly from open sections, resulting in unique wet-dry cycle characteristics and deterioration patterns over long-term operation. Therefore, this type of road section requires separate modeling for maintenance decisions and cost predictions to avoid prediction biases caused by differences in environmental characteristics.

[0070] In certain road sections obstructed by superstructures, the superstructures block the free flow of the atmosphere, resulting in wind speeds below the superstructures typically only 30%-60% of those in open sections. This reduced airflow leads to decreased water vapor exchange efficiency. The airflow velocity is relatively high on the intake side, with the lowest wind speed directly below the superstructure. On the exhaust side, influenced by reverse turbulence, the wind speed slightly increases or vortex zones appear. This uneven wind speed creates lateral evaporation differences on the road surface. These evaporation differences create localized areas of persistent dampness and relatively dryness on the road surface. The frequency of wet-dry cycles and the effects of temperature and humidity stress vary in different areas of the road surface, leading to spatial non-uniformity in the aging rate of the road material. Due to the differences in the degree of aging at different locations within a specific road section, the corresponding maintenance frequency and costs also differ. However, existing technologies typically predict maintenance costs based on the average degree of deterioration of a specific road section, ignoring the environmental heterogeneity caused by local wind speed differences and uneven evaporation due to overlying structures. This results in significant deviations in the predictions, making it difficult to accurately reflect the actual maintenance needs and cost distribution of such obstructed road sections.

[0071] Historical road segment data refers to structural condition data, environmental and usage-related external data collected for a specific road segment during historical maintenance cycles. This includes monitoring data such as pavement temperature and humidity, wind speed distribution, wind direction, evaporation rate, crack density, surface moisture content, rainfall data, sunshine conditions, urban management / sanitation operation data, traffic load and usage intensity data, and environmental meteorological data. These data reflect the road surface deterioration process and environmental response characteristics under different climatic conditions.

[0072] The "maintenance records" include information such as maintenance time, maintenance method, types and quantities of materials used, construction process parameters, post-maintenance performance evaluation results, maintenance costs, and working environment conditions for each historical maintenance cycle. These records reflect the causal relationship between road maintenance activities and changes in pavement performance.

[0073] The role of the "historical maintenance sample" is to match historical road segment data with corresponding maintenance records according to time and environmental characteristics, forming a sample set consistent with the road segment data of the current preset maintenance cycle. By selecting the historical maintenance sample, historical deterioration patterns similar to the current environmental conditions can be effectively extracted, thus providing a statistically significant baseline for assessing the degree of deterioration and predicting costs for the current maintenance cycle. In other words, the historical maintenance sample, as the "experience learning set" of this invention, realizes the transition from historical data to real-time prediction, making the prediction results more reliable and targeted.

[0074] Furthermore, the aforementioned cost prediction collaborative analysis method based on data analysis also includes the following steps:

[0075] Step S200: Extract the historical deterioration degree of a specific road segment from the historical maintenance samples, and use its average value as the average deterioration degree of the specific road segment within the preset maintenance cycle.

[0076] In this embodiment of the invention, the "historical deterioration level" refers to a numerical parameter reflecting the level of pavement aging or damage, calculated from pavement structural performance indicators recorded in historical maintenance samples. This parameter can be determined based on indicators such as pavement crack density, rut depth, surface moisture content, skid resistance degradation rate, and material strength reduction rate, and is used to comprehensively reflect the functional degradation of the pavement within a complete maintenance cycle.

[0077] The historical degradation level is extracted as follows: Indicators reflecting degradation status are extracted from historical road segment data, including: inter-row roughness (IRI), rut depth, crack density; pavement moisture content, surface bond strength, material aging coefficient; and environmental parameters (average temperature and humidity, evaporation rate fluctuation range, etc.). The state parameters of different dimensions are then normalized to obtain standardized values ​​for each indicator, which are then compared and analyzed on a unified scale. Weighting coefficients are set according to the importance of each state parameter in pavement performance evaluation, and a comprehensive degradation index is calculated. The degradation index at different time points within the historical period is fitted, and linear or nonlinear regression models (such as exponential decay models) are used to calculate the degradation rate per unit time to reflect the dynamic trend of degradation.

[0078] By analyzing the performance change records of road sections across multiple maintenance cycles in historical maintenance samples, the degradation degree values ​​of specific road sections at the end of each cycle are extracted, and these degradation degree values ​​are statistically calculated to obtain the average degradation degree. This average degradation degree reflects the typical aging trend of a specific road section within a maintenance cycle under similar environmental conditions and usage intensity. The average degradation degree can serve as a historical experience benchmark, providing an initial reference for subsequent predictions corrected based on real-time environmental factors. This is a typical approach in existing road maintenance budget models. However, it ignores the dynamic differences in environmental factors and cannot reflect the spatial aging unevenness caused by lateral wind speed and evaporation difference in shaded road sections. This invention compensates for this deficiency through a wet-dry ratio change correction mechanism, achieving dynamic adaptability and high accuracy in maintenance cost prediction.

[0079] Furthermore, the aforementioned cost prediction collaborative analysis method based on data analysis also includes the following steps:

[0080] Step S300: The specific road segment is pre-divided into an air intake segment, a middle segment and an air outlet segment. Based on the road segment data, the dry-wet ratio change rate of each segment after each wet period within the preset maintenance cycle is obtained, as well as the standard dry-wet ratio change rate of non-specific road segments. The dry-wet ratio change rate is calculated based on the ratio of dry area to wet area determined by the difference in lateral wind speed distribution and evaporation rate.

[0081] Specifically, Figure 2 A flowchart for determining the rate of change of the wet-dry ratio is shown.

[0082] The process involves pre-dividing a specific road segment into an intake segment, a middle segment, and an exhaust segment. Based on road segment data, the change rate of the wet / dry ratio after each wet cycle within a preset maintenance period is obtained for each segment, as well as the standard change rate of the wet / dry ratio for non-specific road segments. The wet / dry ratio change rate is calculated based on the ratio of the dry area to the wet area determined by the difference in lateral wind speed distribution and evaporation rate. Specifically, the process includes the following steps:

[0083] Step S301: The specific road section is pre-divided into an air intake section, a middle section and an air outlet section, and each section is further divided into several sub-segments. The cross wind speed, temperature and humidity data corresponding to each sub-segment within the preset maintenance cycle are obtained.

[0084] Step S302: Determine the convective heat transfer coefficient between air and road surface based on the lateral wind speed corresponding to each segment; determine the saturated water vapor pressure difference of air based on the temperature and humidity data corresponding to each segment; multiply the convective heat transfer coefficient and saturated water vapor pressure difference corresponding to each segment to obtain the evaporation rate of each segment.

[0085] Step S303: Based on the evaporation rate of each segment, construct the evaporation rate distribution field of each segment surface through spatial interpolation, and compare the evaporation rate of each segment with the preset evaporation rate threshold.

[0086] Step S304: When the evaporation rate of a segment is greater than a preset evaporation rate threshold, it is determined to be a dry zone; when the evaporation rate of a segment is less than a preset evaporation rate threshold, it is determined to be a wet zone.

[0087] Step S305: Calculate the area of ​​the dry and wet areas of each segment, and calculate the ratio of the dry area to the wet area as the dry-wet ratio change rate of that segment.

[0088] Step S306: Obtain the standard wet-dry ratio change rate for non-specific road sections.

[0089] In this embodiment of the invention, a specific road segment is pre-divided into an intake section, a middle section, and an outlet section. This aims to structurally process the differences in wind speed distribution caused by airflow disturbances within the road segment area obstructed by upper structures, thereby enabling quantitative analysis of evaporation rate differences. Due to the obstruction of upper structures, the airflow direction is generally consistent with the prevailing wind direction. The intake side is the first to contact the external airflow, resulting in a higher airflow velocity, sufficient air exchange, and a relatively high evaporation rate. The middle section, located directly below the upper structure, experiences the strongest obstruction effect, leading to a significant decrease in airflow velocity and limited air exchange, resulting in the lowest evaporation rate in this area. The outlet section, located at the exit point where the airflow leaves the obstructed area, experiences a slight increase in wind speed due to partial turbulence and vortex effects, and the evaporation rate fluctuates with the intensity of airflow disturbance. By dividing a specific road segment into intake, middle, and outlet sections, the impact of lateral wind speed distribution differences on the evaporation rate can be more accurately reflected, thus providing higher spatial resolution basic data for subsequent calculations of the wet-dry ratio change rate. Furthermore, by further subdividing each segment into several sub-segments, local wind speed and temperature and humidity variation characteristics can be captured at a smaller spatial scale, thereby improving the accuracy of evaporation rate calculation and avoiding the loss of details caused by averaging data within a single segment.

[0090] In this embodiment of the invention, the convective heat transfer coefficient can be determined based on the transverse wind speed data corresponding to each segment combined with empirical formulas. For example, by establishing a convective heat transfer correlation model between airflow and surface, it can be adopted... The form is determined, in which The convective heat transfer coefficient is... The wind speeds corresponding to the segments are as follows: and This is a constant calibrated based on field experience or experimental data. This coefficient describes the intensity of heat transfer between the air and the road surface. The saturated vapor pressure difference can be determined based on the temperature and humidity data of each segment, specifically using the formula for the saturated vapor pressure of air. Calculate the saturated vapor pressure, and then calculate the actual vapor pressure based on the measured relative humidity. The difference between the two This is the saturated vapor pressure difference of the air. Multiplying the convective heat transfer coefficient by the saturated vapor pressure difference can characterize the moisture exchange capacity between the air and the road surface per unit time in that segment, thus obtaining an approximate value for the evaporation rate.

[0091] Based on the evaporation rate of each segment, an evaporation rate distribution field is constructed for each segment's surface using spatial interpolation methods. This distribution field can be achieved using bilinear interpolation, Kriging interpolation, or spline interpolation, and is used to extrapolate the evaporation rate distribution over continuous space based on data from limited monitoring points, intuitively reflecting the spatial variation trend of evaporation intensity at different locations. By establishing the evaporation rate distribution field, the spatial continuity of evaporation differences within the air inlet, middle, and outlet sections can be quantified, providing accurate input for subsequent dry / wet zone identification and wet / dry ratio calculation. The evaporation rate of each segment is compared with a preset evaporation rate threshold to identify the wetness state of each segment at a specific time. When the evaporation rate of a segment is greater than the preset evaporation rate threshold, it indicates that the evaporation intensity in that area is high, and the road surface is in a dry state; when the evaporation rate is lower than the threshold, it indicates that the evaporation in that area is insufficient, the moisture retention time is long, and it belongs to a wet zone. Through this comparison, automatic division between dry and wet zones can be achieved.

[0092] The preset evaporation rate threshold can be determined based on long-term on-site monitoring data or experimental data. Typically, it is determined by statistically analyzing the distribution of road surface evaporation rate under different temperature, humidity, and wind speed conditions, and selecting the critical value at the dry-wet inflection point of the evaporation rate change curve as the threshold. It can also be dynamically adjusted in conjunction with meteorological conditions.

[0093] The dry and wet areas of each segment are statistically analyzed, and the ratio of the dry area to the wet area is calculated as the dry-wet ratio change rate for that segment. This quantitatively describes the spatial differences in the road surface at different locations during the dry-wet transition process after a single wet period. A non-specific road segment refers to an open road segment that is spatially adjacent to a specific road segment shaded by an overlying structure, has the same structural form, similar traffic load and usage intensity, and is not affected by the overlying structure. The "standard dry-wet ratio change rate" refers to the average change rate calculated based on the dry-wet ratio change rate sequence data collected from non-specific road segments under the same maintenance cycle and similar climatic conditions. This change rate represents the standard speed at which the road surface transitions from a wet to a dry state under natural wind field and natural evaporation conditions, reflecting the baseline state of the road surface moisture balance under natural conditions.

[0094] Furthermore, the aforementioned cost prediction collaborative analysis method based on data analysis also includes the following steps:

[0095] Step S400: Plot the wet-dry ratio change curve based on the wet-dry ratio change rate of each segment, obtain the slope of the curve, and when the absolute value of the slope is greater than the preset threshold, use the difference between the wet-dry ratio change rate of each segment and the standard wet-dry ratio change rate as the correction factor for each segment.

[0096] Specifically, Figure 3 A flowchart for determining the correction factor is shown.

[0097] The process involves plotting a wet-dry ratio change curve based on the wet-dry ratio change rate for each segment, obtaining the curve slope, and using the difference between the wet-dry ratio change rate for each segment and the standard wet-dry ratio change rate as the correction factor for each segment when the absolute value of the slope is greater than a preset threshold. Specifically, this includes the following steps:

[0098] Step S401: Collect the dry-wet ratio change rate data of each segment in time sequence within the preset maintenance cycle;

[0099] Step S402: Based on the dry-wet ratio change rate data, plot the dry-wet ratio change curves for each segment, and calculate the slope of the curves using the difference in the dry-wet ratio change rate between adjacent time points.

[0100] Step S403: When the absolute value of the slope exceeds a preset threshold, the corresponding abnormal fluctuation segment is determined;

[0101] Step S404: Calculate the difference between the rate of change of the wet / dry ratio of each segment in the abnormal fluctuation zone and the standard rate of change of the wet / dry ratio, and determine the absolute value of the difference as the correction factor of that segment in the abnormal fluctuation zone.

[0102] Step S405: When the absolute value of the slope does not exceed the threshold, the correction factor is set to zero.

[0103] In this embodiment of the invention, the wet-dry ratio change rate data may also be derived from environmental monitoring equipment, evaporation rate model calculation results, or historical maintenance data correction results, and form a continuous numerical sequence in time sequence. The wet-dry ratio change rate data of each segment constitute a time series sample, used to reflect the evolution of the wet and dry state during the maintenance cycle of that segment.

[0104] When plotting the wet-dry ratio change curves for each segment based on the wet-dry ratio change rate data, time is used as the horizontal axis and the wet-dry ratio change rate value is used as the vertical axis, forming a continuously changing curve. This curve reflects the trend of wet-dry ratio change during multiple wetting and drying processes within the maintenance cycle of that road segment, and its fluctuation amplitude reflects the intensity of the wet-dry cycle under the combined effects of meteorological, environmental, and shading structures. To quantitatively describe the trend of the curve, the slope of the curve is calculated by dividing the difference in wet-dry ratio change rate between adjacent time points by the time interval. ,in and These represent the rates of change in the wet-dry ratio at adjacent time points. tᵢ and This corresponds to a specific time period. This calculation allows us to obtain the rate of change of the curve within different time intervals, thereby determining the severity of changes in wet and dry conditions.

[0105] In this embodiment of the invention, a preset threshold is set to determine whether the fluctuation of the wet-dry ratio change curve is abnormal. The preset threshold can be determined based on the historical standard deviation or fluctuation range of the wet-dry ratio change rate for a specific road section. For example, the average value of the curve slope distribution in long-term monitoring data plus twice the standard deviation can be used as the threshold. When the absolute value of the curve slope exceeds the preset threshold, it indicates that the wet-dry ratio change rate deviates significantly from the normal range during that time period, possibly due to sudden weather conditions (such as heavy rainfall or sudden evaporation) or human factors (such as watering operations or construction interference). The significance of setting the preset threshold is to distinguish between normal and abnormal fluctuations through quantitative standards, thereby automatically identifying short-term, drastic fluctuations caused by environmental anomalies in the analysis, and preventing these fluctuations from being masked by averaging, thus avoiding their actual impact on the deterioration process.

[0106] When the absolute value of the curve slope exceeds a preset threshold, the corresponding abnormal fluctuation segment is identified. An abnormal fluctuation segment refers to a time interval in the time series where the slope continuously exceeds the threshold; this segment reflects a stage where the dry and wet conditions change drastically within a short period. This segment typically corresponds to abnormal changes in the external environment, such as localized heavy rain, sudden dry winds, or water accumulation under bridges. The significance of identifying abnormal fluctuation segments lies in treating this stage as an independent analysis unit, allowing for differentiated correction of the dry and wet changes within this segment to reflect the rapid changes in actual road surface conditions.

[0107] When the absolute value of the curve slope does not exceed the threshold, it indicates that the dry and wet conditions are in a stable range during that time period, and there is no significant environmental disturbance. Therefore, the correction factor is set to zero. The difference between the rate of change of the dry-wet ratio and the standard rate of change of the dry-wet ratio can quantitatively reflect the degree of deviation between the shaded road section and the open road section during the dry-wet evolution process. The introduction of the correction factor allows the impact of each section on the average degree of deterioration under abnormal dry-wet fluctuations to be dynamically quantified. This enables compensation for the deterioration differences of road sections in different locations under heterogeneous environments, improving the cost prediction model's responsiveness to local abnormal conditions and the accuracy of overall prediction.

[0108] Furthermore, the aforementioned cost prediction collaborative analysis method based on data analysis also includes the following steps:

[0109] Step S500: The degradation degree of each segment is calculated by using the correction factor of each segment and the average degradation degree. The maintenance cost of each segment is calculated by combining the real-time collaborative cost element set. The total maintenance cost prediction value of the preset maintenance cycle is obtained by summing them up.

[0110] Specifically, Figure 4 A flowchart for determining the total maintenance cost is shown.

[0111] The specific steps involved are as follows: The degradation level of each segment is calculated using correction factors and the average degradation level. The maintenance cost of each segment is then calculated using a real-time collaborative cost element set, and the total maintenance cost prediction for the preset maintenance cycle is obtained by summing these steps.

[0112] Step S501: The average value obtained by weighting the correction factors of each segment within the preset maintenance cycle is used as the weight coefficient to weight and correct the average deterioration degree of a specific road segment, so as to obtain the deterioration degree of each segment.

[0113] Step S502: Obtain the real-time collaborative cost element set for each segment within the preset maintenance cycle. The collaborative cost element set includes labor costs, material costs, equipment usage costs, energy consumption costs, and traffic occupancy costs.

[0114] Step S503: The degradation degree of each segment is weighted and calculated with the real-time collaborative cost element set to obtain the maintenance cost of each segment;

[0115] Step S504: The maintenance costs of each segment are summed to obtain the predicted total maintenance cost of a specific road segment within a preset maintenance cycle.

[0116] In this embodiment of the invention, the correction factor is a parameter obtained from the aforementioned analysis of abnormal fluctuations in the rate of change of the wet-dry ratio. It reflects the relative deterioration differences among different sections of a specific road segment due to abnormal changes in wet-dry conditions. Since each segment may experience multiple abnormal fluctuations of varying magnitudes throughout the maintenance cycle, the correction factor at a single moment cannot fully reflect the overall impact of that segment within the cycle. Therefore, it is necessary to perform a weighted average of the correction factors within the cycle. The weighted average process can employ time weighting or fluctuation duration weighting, giving higher weights to road segments that frequently experience abnormal fluctuations or have longer fluctuation durations in the overall correction. This ensures that the final weight coefficient accurately reflects the cumulative degree of environmental disturbance experienced by that segment throughout the maintenance cycle. By weighting and correcting the average deterioration degree in this way, a deterioration degree for each segment that better reflects the actual environmental impact characteristics can be obtained, enabling the model to reflect the heterogeneous deterioration differences between the intake section, intermediate section, and exhaust section due to different ventilation conditions.

[0117] In this embodiment of the invention, the real-time collaborative cost element set refers to a set of multi-dimensional cost parameters directly or indirectly related to maintenance activities within a specific maintenance cycle. The collaborative cost element set includes labor costs, material costs, equipment usage costs, energy consumption costs, and traffic occupancy costs. Labor costs characterize the human resource consumption during maintenance at each stage, influenced by factors such as work time, construction difficulty, and work environment. Material costs reflect the quantity and unit price of various materials used during maintenance, such as road repair materials, waterproofing materials, and adhesives. Equipment usage costs include depreciation, usage time, fuel, and maintenance costs of machinery and equipment. Energy consumption costs characterize the product of energy consumption and unit price of construction machinery, lighting equipment, etc., during maintenance. Traffic occupancy costs reflect the socio-economic losses caused by the impact on road capacity during construction, and can be calculated based on factors such as closure duration, traffic flow, and detour distance. The introduction of the real-time collaborative cost element set allows maintenance cost calculation to not only consider physical degradation factors but also dynamically reflect the actual economic expenditure and social impact during maintenance, achieving comprehensive and timely cost prediction.

[0118] By weighting the degradation levels of each segment with a set of real-time collaborative cost elements, the synergistic relationship between environmental degradation and economic impact can be comprehensively considered. Specifically, weighting coefficients can be determined based on the correlation model between the degradation levels of each segment and the corresponding cost elements. For example, for segments with high degradation levels, higher weights are assigned to labor and material costs; for segments with high construction difficulty and significant traffic disruption, the weights of equipment usage and traffic occupancy costs are increased. This weighted calculation can be implemented using a linear weighted model or a fitting model based on multi-factor regression, thereby obtaining the estimated maintenance costs for each segment.

[0119] Finally, the maintenance costs of each segment are summed to obtain the predicted total maintenance cost for a specific road segment within a preset maintenance cycle. Because each segment exhibits significant differences in wind speed distribution, evaporation rate, wet-dry variation patterns, and environmental disturbance frequency, traditional averaging methods easily overlook these differences, leading to prediction bias. This invention, by introducing a correction factor-weighted deterioration degree and linking it with the real-time collaborative cost element set, enables a fully coupled analysis from physical deterioration characteristics to economic maintenance needs, thereby significantly improving the accuracy and adaptability of maintenance cost prediction for specific road segments obstructed by superstructures.

[0120] Furthermore, Figure 5 An application architecture diagram of the system provided in an embodiment of the present invention is shown.

[0121] In another preferred embodiment of the present invention, a cost prediction collaborative analysis system based on data analysis includes:

[0122] The data acquisition module 100 is used to acquire the real-time collaborative cost element set of a specific road segment that is blocked by the superstructure, historical road segment data within the historical maintenance cycle and corresponding maintenance records, and to filter historical maintenance samples that are consistent with the road segment data within the preset maintenance cycle.

[0123] Furthermore, the data-based cost prediction collaborative analysis system also includes:

[0124] The degradation degree extraction module 200 is used to extract the historical degradation degree of a specific road segment from the historical maintenance samples, and use its average value as the average degradation degree of the specific road segment within the preset maintenance cycle.

[0125] Furthermore, the data-based cost prediction collaborative analysis system also includes:

[0126] The wet-dry ratio calculation module 300 is used to pre-divide a specific road segment into an air intake segment, a middle segment, and an air outlet segment. Based on the road segment data, it obtains the wet-dry ratio change rate of each segment after each wet cycle within a preset maintenance period, as well as the standard wet-dry ratio change rate of non-specific road segments. The wet-dry ratio change rate is calculated based on the ratio of dry area to wet area determined by the difference in lateral wind speed distribution and evaporation rate.

[0127] Specifically, Figure 6 The diagram shows a structural block diagram of the wet-dry ratio calculation module 300 in the system provided in an embodiment of the present invention.

[0128] In a preferred embodiment of the present invention, the wet-dry ratio calculation module 300 specifically includes:

[0129] The road section partitioning unit 301 is used to pre-divide a specific road section into an air intake section, a middle section and an air outlet section, further divide each section into several sub-segments, and obtain the lateral wind speed, temperature and humidity data corresponding to each sub-segment within a preset maintenance cycle.

[0130] Evaporation rate calculation unit 302 is used to determine the convective heat transfer coefficient between air and road surface based on the cross wind speed corresponding to each segment; determine the saturated water vapor pressure difference of air based on the temperature and humidity data corresponding to each segment; and multiply the convective heat transfer coefficient and saturated water vapor pressure difference corresponding to each segment to obtain the evaporation rate of each segment.

[0131] The distribution field construction unit 303 is used to construct the evaporation rate distribution field of each segment surface by spatial interpolation based on the evaporation rate of each segment, and compare the evaporation rate of each segment with the preset evaporation rate threshold.

[0132] The area determination unit 304 is used to determine a dry area when the evaporation rate of a segment is greater than a preset evaporation rate threshold, and to determine a wet area when the evaporation rate of a segment is less than a preset evaporation rate threshold.

[0133] The ratio calculation unit 305 is used to count the area of ​​the dry area and the wet area of ​​each segment, and calculate the ratio of the dry area area to the wet area area as the dry-wet ratio change rate of that segment.

[0134] The average value calculation unit 306 is used to obtain the standard wet-dry ratio change rate of non-specific road sections.

[0135] Furthermore, the data-based cost prediction collaborative analysis system also includes:

[0136] The correction factor determination module 400 is used to draw the dry-wet ratio change curve based on the dry-wet ratio change rate of each segment, obtain the slope of the curve, and when the absolute value of the slope is greater than the preset threshold, the difference between the dry-wet ratio change rate of each segment and the standard dry-wet ratio change rate is used as the correction factor for each segment.

[0137] Specifically, Figure 7 The diagram shows a structural block diagram of the correction factor determination module 400 in the system provided in an embodiment of the present invention.

[0138] In a preferred embodiment provided by the present invention, the correction factor determination module 400 specifically includes:

[0139] The data acquisition unit 401 is used to collect the dry-wet ratio change rate data recorded in chronological order for each segment within a preset maintenance cycle.

[0140] The curve generation unit 402 is used to draw the dry-wet ratio change curves of each segment based on the dry-wet ratio change rate data, and to calculate the slope of the curve using the difference in the dry-wet ratio change rate between adjacent time points.

[0141] The anomaly detection unit 403 is used to determine the corresponding abnormal fluctuation segment when the absolute value of the slope exceeds a preset threshold.

[0142] The correction factor calculation unit 404 is used to calculate the difference between the rate of change of the dry-wet ratio of each segment in the abnormal fluctuation range and the rate of change of the standard dry-wet ratio, and to determine the absolute value of the difference as the correction factor of the segment in the abnormal fluctuation range.

[0143] The threshold control unit 405 is used to set the correction factor to zero when the absolute value of the slope does not exceed the threshold.

[0144] Furthermore, the data-based cost prediction collaborative analysis system also includes:

[0145] The cost prediction module 500 is used to calculate the degradation degree of each segment by using the correction factor of each segment and the average degradation degree, and to calculate the maintenance cost of each segment by combining the real-time collaborative cost element set, and to accumulate the total maintenance cost prediction value of the preset maintenance cycle.

[0146] Specifically,Figure 8 A structural block diagram of the cost prediction module 500 in the system provided in an embodiment of the present invention is shown.

[0147] In a preferred embodiment provided by the present invention, the cost prediction module 500 specifically includes:

[0148] The deterioration degree correction unit 501 is used to take the average value of the correction factors of each section within the preset maintenance cycle as the weight coefficient, and perform weighted correction on the average deterioration degree of a specific road section to obtain the deterioration degree of each section.

[0149] The element acquisition unit 502 is used to acquire the real-time collaborative cost element set of each segment within the preset maintenance cycle. The collaborative cost element set includes labor cost, material cost, equipment usage cost, energy consumption cost, and traffic occupation cost.

[0150] Cost calculation unit 503 is used to calculate the maintenance cost of each segment by weighting the degree of deterioration of each segment with the real-time collaborative cost element set.

[0151] The cost aggregation unit 504 is used to sum up the maintenance costs of each section to obtain the predicted total maintenance cost of a specific road section within a preset maintenance cycle.

[0152] It should be understood that although the steps in the flowcharts of the various embodiments of the present invention are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the various embodiments may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least a portion of the sub-steps or stages of other steps.

[0153] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0154] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0155] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention. Therefore, the scope of protection of this patent should be determined by the appended claims.

[0156] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A cost prediction and collaborative analysis method based on data analysis, characterized in that, The method includes: Acquire the real-time collaborative cost element set of a specific road segment obscured by the superstructure, historical road segment data within the historical maintenance cycle and corresponding maintenance records, and filter historical maintenance samples that are consistent with the road segment data within the preset maintenance cycle; Extract the historical deterioration level of a specific road segment from the historical maintenance samples, and use the average value as the average deterioration level of the specific road segment within the preset maintenance cycle; A specific road segment is pre-divided into an air intake segment, a middle segment, and an air outlet segment. Based on the road segment data, the rate of change of the wet-dry ratio after each wet cycle in each segment within the preset maintenance cycle is obtained, as well as the standard rate of change of the wet-dry ratio in non-specific road segments. The rate of change of the wet-dry ratio is calculated based on the ratio of the dry area to the wet area determined by the difference in lateral wind speed distribution and evaporation rate. Based on the rate of change of the wet-dry ratio of each segment, a wet-dry ratio change curve is plotted, and the slope of the curve is obtained. When the absolute value of the slope is greater than the preset threshold, the difference between the rate of change of the wet-dry ratio of each segment and the standard rate of change of the wet-dry ratio is used as the correction factor for each segment. The degradation level of each segment is calculated by using the correction factor and the average degradation level. The maintenance cost of each segment is calculated by combining the real-time collaborative cost element set. The total maintenance cost prediction value for the preset maintenance cycle is obtained by summing them up.

2. The cost prediction and collaborative analysis method based on data analysis according to claim 1, characterized in that, The process of pre-dividing a specific road segment into an intake segment, a middle segment, and an exhaust segment, and obtaining the change rate of the wet-dry ratio after each wet period within a preset maintenance cycle for each segment based on road segment data, as well as the standard change rate of the wet-dry ratio for non-specific road segments, wherein the change rate of the wet-dry ratio is calculated based on the ratio of the dry area to the wet area determined by the difference in lateral wind speed distribution and evaporation rate, includes the following steps: A specific road section is pre-divided into an air intake section, a middle section, and an air outlet section. Each section is further divided into several sub-segments, and the cross wind speed, temperature, and humidity data corresponding to each sub-segment within the preset maintenance cycle are obtained. The convective heat transfer coefficient between air and road surface is determined based on the cross wind speed corresponding to each segment; the saturated water vapor pressure difference of air is determined based on the temperature and humidity data corresponding to each segment; the evaporation rate of each segment is obtained by multiplying the convective heat transfer coefficient and the saturated water vapor pressure difference corresponding to each segment. Based on the evaporation rate of each segment, the evaporation rate distribution field of each segment surface is constructed by spatial interpolation, and the evaporation rate of each segment is compared with the preset evaporation rate threshold. When the evaporation rate of a segment is greater than the preset evaporation rate threshold, it is determined to be a dry zone; when the evaporation rate of a segment is less than the preset evaporation rate threshold, it is determined to be a wet zone. The areas of dry and wet zones in each segment are counted, and the ratio of the dry area to the wet area is calculated as the rate of change of the dry-wet ratio for that segment. Obtain the standard wet-dry ratio change rate for non-specific road sections.

3. The cost prediction and collaborative analysis method based on data analysis according to claim 1, characterized in that, The steps include plotting the wet-dry ratio change curve based on the wet-dry ratio change rate of each segment, obtaining the slope of the curve, and using the difference between the wet-dry ratio change rate of each segment and the standard wet-dry ratio change rate as the correction factor for each segment when the absolute value of the slope is greater than a preset threshold. Collect the dry-wet ratio change rate data for each segment within the preset maintenance cycle, recorded in chronological order. Based on the dry-wet ratio change rate data, plot the dry-wet ratio change curves for each segment, and calculate the slope of the curves using the difference in the dry-wet ratio change rate between adjacent time points. When the absolute value of the slope exceeds a preset threshold, the corresponding abnormal fluctuation segment is identified. Calculate the difference between the rate of change of the wet-dry ratio of each segment within the abnormal fluctuation range and the standard rate of change of the wet-dry ratio, and determine the absolute value of the difference as the correction factor for that segment within the abnormal fluctuation range; When the absolute value of the slope does not exceed the threshold, the correction factor is set to zero.

4. The cost prediction and collaborative analysis method based on data analysis according to claim 1, characterized in that, The steps include: calculating the degradation level of each segment by using correction factors and average degradation level, calculating the maintenance cost of each segment by combining the real-time collaborative cost element set, and summing them up to obtain the total maintenance cost prediction value for the preset maintenance cycle. The average value obtained by weighting the correction factors of each segment within the preset maintenance cycle is used as the weight coefficient to weight the average deterioration degree of a specific road segment, thereby obtaining the deterioration degree of each segment. Obtain the real-time collaborative cost element set for each segment within the preset maintenance cycle. The collaborative cost element set includes labor costs, material costs, equipment usage costs, energy consumption costs, and traffic occupancy costs. The maintenance cost of each segment is obtained by weighting the degradation degree of each segment with the real-time collaborative cost factor set. The maintenance costs of each section are summed up to obtain the predicted total maintenance cost of a specific road section within a preset maintenance cycle.

5. The cost prediction and collaborative analysis method based on data analysis according to claim 1, characterized in that, The specific road sections obstructed by superstructures include those under viaducts, under overpasses, or other road sections with partial obstruction structures.

6. A cost prediction and collaborative analysis system based on data analysis, characterized in that, The system includes: The data acquisition module is used to acquire the real-time collaborative cost element set of a specific road segment that is blocked by the superstructure, historical road segment data within the historical maintenance cycle and corresponding maintenance records, and to filter historical maintenance samples that are consistent with the road segment data within the preset maintenance cycle. The degradation degree extraction module is used to extract the historical degradation degree of a specific road segment from the historical maintenance samples, and use its average value as the average degradation degree of the specific road segment within the preset maintenance cycle; The wet-dry ratio calculation module is used to pre-divide a specific road segment into an air intake segment, a middle segment, and an air outlet segment. Based on the road segment data, it obtains the wet-dry ratio change rate of each segment after each wet cycle within a preset maintenance period, as well as the standard wet-dry ratio change rate of non-specific road segments. The wet-dry ratio change rate is calculated based on the ratio of the dry area to the wet area determined by the difference in lateral wind speed distribution and evaporation rate. The correction factor determination module is used to draw the dry-wet ratio change curve based on the dry-wet ratio change rate of each segment, obtain the slope of the curve, and when the absolute value of the slope is greater than the preset threshold, the difference between the dry-wet ratio change rate of each segment and the standard dry-wet ratio change rate is used as the correction factor for each segment. The cost prediction module is used to calculate the degradation degree of each segment by using the correction factor of each segment and the average degradation degree, and to calculate the maintenance cost of each segment by combining the real-time collaborative cost element set, and to accumulate the total maintenance cost prediction value of the preset maintenance cycle.

7. The cost prediction and collaborative analysis system based on data analysis according to claim 6, characterized in that, The wet-dry ratio calculation module specifically includes: The road segment zoning unit is used to pre-divide a specific road segment into an air intake segment, a middle segment, and an air outlet segment, and further divide each segment into several sub-segments to obtain the lateral wind speed, temperature, and humidity data corresponding to each sub-segment within a preset maintenance cycle. The evaporation rate calculation unit is used to determine the convective heat transfer coefficient between the air and the road surface based on the cross wind speed corresponding to each segment; to determine the saturated water vapor pressure difference of the air based on the temperature and humidity data corresponding to each segment; and to multiply the convective heat transfer coefficient and the saturated water vapor pressure difference corresponding to each segment to obtain the evaporation rate of each segment. The distribution field construction unit is used to construct the evaporation rate distribution field of each segment surface through spatial interpolation based on the evaporation rate of each segment, and compare the evaporation rate of each segment with the preset evaporation rate threshold. The area determination unit is used to determine a dry area when the evaporation rate of a segment is greater than a preset evaporation rate threshold, and to determine a wet area when the evaporation rate of a segment is less than the preset evaporation rate threshold. The ratio calculation unit is used to count the area of ​​the dry and wet areas of each segment and calculate the ratio of the dry area to the wet area as the dry-wet ratio change rate of that segment. The average value calculation unit is used to obtain the standard wet-dry ratio change rate of non-specific road sections.

8. The cost prediction and collaborative analysis system based on data analysis according to claim 6, characterized in that, The correction factor determination module specifically includes: The data acquisition unit is used to collect the dry-wet ratio change rate data recorded in chronological order for each segment within a preset maintenance cycle. The curve generation unit is used to draw the dry-wet ratio change curves for each segment based on the dry-wet ratio change rate data, and to calculate the slope of the curve using the difference in the dry-wet ratio change rate between adjacent time points. An anomaly detection unit is used to determine the corresponding abnormal fluctuation segment when the absolute value of the slope exceeds a preset threshold. The correction factor calculation unit is used to calculate the difference between the rate of change of the dry-wet ratio of each segment in the abnormal fluctuation range and the standard rate of change of the dry-wet ratio, and to determine the absolute value of the difference as the correction factor of that segment in the abnormal fluctuation range. The threshold control unit sets the correction factor to zero when the absolute value of the slope does not exceed the threshold.

9. A cost prediction and collaborative analysis system based on data analysis according to claim 6, characterized in that, The cost prediction module specifically includes: The deterioration degree correction unit is used to take the average value of the correction factors of each section within the preset maintenance cycle as the weight coefficient, and then use it to correct the average deterioration degree of a specific road section to obtain the deterioration degree of each section. The element acquisition unit is used to acquire the real-time collaborative cost element set of each segment within a preset maintenance cycle. The collaborative cost element set includes labor cost, material cost, equipment usage cost, energy consumption cost, and traffic occupation cost. The cost calculation unit is used to calculate the maintenance cost of each segment by weighting the degree of deterioration of each segment with the real-time collaborative cost element set. The cost aggregation unit is used to sum up the maintenance costs of each section to obtain the predicted total maintenance cost of a specific road section within a preset maintenance cycle.

10. A cost prediction and collaborative analysis system based on data analysis according to claim 6, characterized in that, The specific road sections obstructed by superstructures include those under viaducts, under overpasses, or other road sections with partial obstruction structures.

Images