Roadway average air volume prediction method and system

Abstract

The invention relates to the technical field of data processing, and discloses a roadway average air volume prediction method and system. The method comprises the following steps: acquiring roadway parameters to obtain resistance interval data; quantifying the air volume uncertainty to obtain an air volume interval range; converting into a triangular fuzzy number to obtain air volume fuzzy distribution data; obtaining average air volume fusion data through weight operator fusion; and air volume prediction data is obtained based on historical sequence error correction. The prediction accuracy of the average air volume of the roadway is improved.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a method and system for predicting average air volume in roadways. Background Technology

[0002] Existing methods for predicting average ventilation volume in mine roadways are primarily based on traditional fluid mechanics principles and numerical calculation models. These methods collect fundamental data such as roadway geometric parameters, ventilation resistance coefficients, and fan performance parameters. They then use ventilation network theory to simplify the complex mine ventilation system into a network model composed of nodes and branches. A mathematical model is established using airflow balance equations and air pressure balance equations. Iterative calculations are then used to solve the network equations to obtain the airflow distribution in each roadway branch. These methods can provide a certain level of prediction accuracy under stable operating conditions, offering fundamental technical support for the design and operation management of mine ventilation systems.

[0003] However, the data acquisition accuracy is low and there is a lot of uncertainty. Roadway parameters such as roughness coefficient and cross-sectional area often rely on empirical estimation or single measurement, which cannot accurately reflect the actual range of parameter changes. Secondly, the prediction model is too simplified, treating roadway resistance and air volume as deterministic values ​​and ignoring the impact of measurement errors and parameter fluctuations on the prediction results. Furthermore, there is a lack of an effective multi-data source fusion mechanism, which cannot make full use of different types of data acquired by multiple sensors to improve prediction accuracy.

[0004] The inability to effectively handle the measurement uncertainties of roadway parameters leads to insufficient reliability of the input data for the prediction model; the lack of a dedicated data fusion algorithm for roadway characteristics makes it impossible to effectively integrate multi-sensor data; and the lack of an error correction mechanism based on historical data makes it impossible to dynamically adjust and optimize the prediction results according to the actual operating conditions. Summary of the Invention

[0005] This application provides a method and system for predicting average air volume in roadways, which addresses the problems of insufficient data uncertainty handling capability, low efficiency of multi-source data fusion, and poor prediction accuracy and stability in existing roadway air volume prediction methods, thereby improving the accuracy and reliability of roadway average air volume prediction.

[0006] In a first aspect, this application provides a method for predicting the average air volume in a roadway, the method comprising: Data on roadway resistance range is obtained by collecting and processing data on roadway cross-sectional area, roadway length, and roadway roughness coefficient through a multi-sensor network. The uncertainty of the roadway air volume is quantified based on the roadway resistance range data to obtain the roadway air volume range. The tunnel air volume range is processed by triangular fuzzy number transformation to obtain fuzzy distribution data of tunnel air volume. The fuzzy distribution data of the roadway air volume is fused by the roadway weight-induced ordered weighted average operator to obtain the fused average air volume data of the roadway. Error correction processing is performed on the historical air volume sequence of the roadway based on the fused data of the roadway's average air volume to obtain the predicted data of the roadway's average air volume.

[0007] Secondly, this application provides a roadway average air volume prediction system, the roadway average air volume prediction system comprising: The data acquisition module is used to collect and process the cross-sectional area, length, and roughness coefficient of the roadway through a multi-sensor network to obtain roadway resistance range data. The quantization module is used to quantify the uncertainty of the roadway air volume based on the roadway resistance range data to obtain the roadway air volume range. The conversion module is used to perform triangular fuzzy number conversion processing on the air volume range of the roadway to obtain fuzzy distribution data of the air volume in the roadway. The fusion module is used to fuse the fuzzy distribution data of the roadway air volume through the roadway weight-induced ordered weighted average operator to obtain the fused average air volume data of the roadway. The correction module is used to perform error correction processing on the historical air volume sequence of the roadway based on the fused data of the roadway average air volume, so as to obtain the predicted data of the roadway average air volume.

[0008] Thirdly, a roadway average air volume prediction device is provided, comprising: a memory and at least one processor, wherein the memory stores instructions; the at least one processor invokes the instructions in the memory to cause the roadway average air volume prediction device to execute the roadway average air volume prediction method described above.

[0009] Fourthly, a computer-readable storage medium is provided, wherein instructions are stored therein, which, when executed on a computer, cause the computer to perform the above-described method for predicting average air volume in roadways.

[0010] The technical solution provided in this application collects and processes roadway cross-sectional area, roadway length, and roadway roughness coefficient data through a multi-sensor network to obtain roadway resistance interval data. This effectively solves the problem of insufficient data reliability caused by single-point measurement of roadway parameters in traditional methods, transforming originally deterministic parameter values ​​into interval data that reflects the uncertainty of actual measurement, providing more realistic and reliable basic data support for subsequent airflow prediction. Based on the roadway resistance interval data, the uncertainty of roadway airflow is quantified to obtain the roadway airflow interval range. This innovatively introduces uncertainty theory into the field of roadway airflow calculation, effectively transmitting and quantifying the impact of parameter uncertainty on airflow prediction results through interval operations, avoiding the technical defect of traditional deterministic calculation methods that ignore error accumulation. The roadway airflow interval range is then transformed using triangular fuzzy numbers to obtain fuzzy distribution data of roadway airflow, further enriching the expression form of airflow data. Fuzzy mathematics theory is used to more accurately characterize the probability distribution characteristics of roadway airflow, laying a theoretical foundation for achieving accurate airflow fusion.

[0011] The fuzzy distribution data of roadway airflow is fused using a roadway weight-induced ordered weighted average operator to obtain fused average roadway airflow data. This operator fully considers the differences in the importance of different roadways in the ventilation system, and highlights the role of the main ventilation roadways through a dynamic weight allocation mechanism. This effectively reduces the adverse impact of measurement errors in secondary roadways on the overall prediction results, significantly improving the accuracy and rationality of multi-roadway airflow data fusion. Based on the fused average roadway airflow data, error correction processing is performed on the historical airflow sequences of the roadways to obtain predicted average roadway airflow data. An innovative time series analysis and error compensation mechanism are introduced, enabling dynamic correction of the current prediction results based on the changing patterns of historical operating data. This effectively solves the technical limitations of traditional static prediction methods that cannot adapt to changes in roadway ventilation conditions, achieving adaptive optimization of roadway airflow prediction and significantly improving the stability of prediction accuracy. Attached Figure Description

[0012] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 This is a schematic diagram of an embodiment of the roadway average air volume prediction method in this application. Figure 2 This is a schematic diagram of the membership function of the triangular fuzzy number in the embodiments of this application; Figure 3 This is a schematic diagram of one embodiment of the roadway average air volume prediction system in this application. Figure 4 This is a schematic block diagram of the structure of the average air volume prediction device for roadways in an embodiment of the present invention. Detailed Implementation

[0014] This application provides a method and system for predicting average air volume in roadways. The terms "first," "second," "third," "fourth," etc. (if present) in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in a sequence other than that illustrated or described herein. Furthermore, the terms "comprising" or "having" and any variations thereof are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0015] For ease of understanding, the specific process of the embodiments of this application is described below. Please refer to [link / reference]. Figure 1 One embodiment of the method for predicting average air volume in roadways in this application includes: Step S101: Collect and process the cross-sectional area, length and roughness coefficient of the roadway through a multi-sensor network to obtain the roadway resistance range data; Step S102: Quantify the uncertainty of the roadway air volume based on the roadway resistance range data to obtain the roadway air volume range. Step S103: Perform triangular fuzzy number transformation on the range of air volume in the roadway to obtain fuzzy distribution data of air volume in the roadway; Step S104: The fuzzy distribution data of the roadway air volume is fused by the roadway weight-induced ordered weighted average operator to obtain the fused average air volume data of the roadway. Step S105: Based on the fusion data of the average air volume of the roadway, perform error correction processing on the historical air volume sequence of the roadway to obtain the predicted data of the average air volume of the roadway.

[0016] It is understood that the executing entity of this application can be a roadway average air volume prediction system, a terminal, or a server; no specific limitation is made here. This application's embodiment uses a server as the executing entity for illustration.

[0017] Specifically, the cross-sectional area, length, and roughness coefficient of the tunnel are collected through a multi-sensor network. These parameters are key to airflow calculation. The sensor network collects this data in real time and converts it into interval data, providing an interval range for each parameter. This processing method effectively reduces the error that may arise from a single measurement. The obtained tunnel resistance interval data is analyzed and calculated to obtain the airflow interval range, quantifying the impact of different factors on airflow prediction. Traditional prediction methods typically assume airflow is a deterministic value, while this method uses interval data to more comprehensively reflect the uncertainty of airflow and improve the reliability of the prediction results. After obtaining the airflow interval range, triangular fuzzy number transformation is performed. By defining upper and lower bounds and the most probable value, the fuzziness of the airflow is represented, resulting in fuzzy distribution data of the airflow.

[0018] A weighted average operator induced by roadway weights is used to fuse fuzzy airflow distribution data. Based on the importance of each roadway in the overall ventilation system, a weight value is assigned to each roadway, with primary ventilation roadways receiving a larger weight and secondary ventilation roadways receiving a smaller weight. The weighted average operator then fuses the fuzzy airflow distribution data from different roadways to obtain unified average airflow data for each roadway. This process effectively handles the differences between data from multiple roadways, ensuring that the influence of primary roadways is prioritized, thereby improving overall prediction accuracy. Based on the fused average airflow data, historical airflow sequences are corrected for errors. Through time series analysis, periodic variation patterns in airflow are identified, time decay coefficients are calculated, and a time-weighted decay function is constructed. The decay function is used to perform weighted analysis on historical airflow data to obtain a historical error sequence. A trend prediction method is then used to compensate for the errors, correcting the predicted values ​​and ultimately obtaining more accurate average airflow prediction data for each roadway.

[0019] Taking the ventilation system of a mine as an example, a multi-sensor network is used to collect key parameters such as the cross-sectional area, length, and roughness coefficient of the mine roadways in real time. Sensors deployed inside the mine can acquire data in real time under different roadways and working conditions and transmit it to the central control system. This data is not presented as a single numerical value, but rather as interval data; that is, each measurement value provides a range. This approach effectively reduces single-measurement errors and more accurately reflects the impact of environmental factors on the measurement results.

[0020] The system obtains roadway resistance range data to quantify airflow uncertainty. In this process, the system analyzes the resistance range data of the mine roadway and calculates the airflow range using the airflow balance equation. Unlike traditional airflow prediction methods, this method uses interval calculations instead of treating airflow as a single deterministic value, thus more comprehensively reflecting the impact of uncertainties on the airflow prediction results. Through this quantification, the system can handle airflow fluctuations caused by equipment measurement errors, environmental changes, or other uncertainties, thereby providing more accurate and reliable airflow range predictions.

[0021] After obtaining the airflow range, the airflow range data is converted into triangular fuzzy numbers. By defining the upper and lower bounds of the airflow and its most probable value, fuzzy mathematics is used to transform this airflow data into fuzzy distribution data. This process can more accurately represent the uncertainty of airflow, and by calculating the membership function of the airflow, the probability distribution of the airflow data is further refined. Through this transformation, not only can the measurement range of airflow be expressed, but the probabilistic characteristics of airflow changes can also be taken into account, making the data more consistent with reality in subsequent processing. The system obtains fuzzy distribution data of airflow, which provides a necessary basis for subsequent data fusion and correction.

[0022] The system fuses fuzzy distribution data of airflow from different roadways using a weighted average operator. Since a mine ventilation system consists of multiple roadways, each with varying importance, different weights need to be assigned to each roadway. Primary ventilation roadways are assigned larger weights, while secondary ventilation roadways receive smaller weights. The system uses an ordered weighted average operator to weight and fuse the airflow data from multiple roadways, ultimately obtaining a unified average airflow data for each roadway.

[0023] The system performs error correction on historical airflow sequences. Through time series analysis, the system identifies periodic patterns in airflow variation and calculates time decay coefficients based on these patterns, constructing a time-weighted decay function. This function weights historical airflow data according to time changes, yielding an error sequence for the airflow data. The system then uses trend prediction methods to compensate for these errors, thereby adjusting the predicted airflow values. This correction process eliminates deviations caused by measurement errors, changes in the external environment, or unstable equipment operation, ensuring that the final predicted airflow data more accurately reflects reality. Through these processing steps, the system provides accurate predicted airflow data, helping mine managers monitor and adjust the ventilation system in real time.

[0024] In this embodiment, a multi-sensor network is used to collect and process the cross-sectional area, length, and roughness coefficient of the roadway to obtain roadway resistance interval data. This effectively solves the problem that single measurement data in traditional methods cannot reflect actual environmental changes and measurement errors. Traditional airflow prediction methods typically rely on single deterministic data, which cannot account for changing factors in the complex environment of mine roadways, such as measurement errors and equipment fluctuations. By deploying a multi-sensor network, multiple key parameters within the roadway can be collected in real time and converted into interval data. This processing method not only reduces the errors that may be caused by a single measurement but also more realistically reflects the uncertainty of actual measurements, providing more reliable basic data for subsequent airflow prediction. After obtaining the roadway resistance interval data, the system quantifies the uncertainty of roadway airflow using the airflow balance equation to obtain the airflow interval range. Unlike traditional methods, this method quantifies airflow using interval data, avoiding the limitation of treating airflow as a deterministic value. In this way, the system can comprehensively reflect the uncertainties brought about by the environment and equipment, thereby improving the reliability of airflow prediction results. The system converts the roadway airflow interval range into triangular fuzzy numbers and uses fuzzy mathematics methods to accurately represent the range of airflow variation. In this process, the system extracts the upper and lower bounds of air volume by combining historical air volume data and calculates the most probable value of air volume, ultimately constructing fuzzy distribution data of air volume. This processing method makes the air volume data more consistent with actual measurement characteristics and can express the probabilistic characteristics of air volume changes. Based on the importance of each roadway in the ventilation system, the system assigns different weights to different roadways. Through a weighted average operator, the system weights and fuses the fuzzy distribution data of air volume from each roadway, ultimately obtaining unified average air volume data for each roadway, improving prediction accuracy. The system corrects errors in historical air volume sequences through time series analysis, identifies periodic change patterns in air volume and calculates a time decay coefficient. This coefficient is used to perform weighted analysis on historical data to obtain a historical error sequence. The system compensates for errors using trend prediction methods, correcting the predicted air volume values, and ultimately providing accurate roadway air volume prediction results, thus providing effective decision support for the management and optimization of mine ventilation systems.

[0025] In one specific embodiment, the process of performing step S101 may specifically include the following steps: (1) The error range of the measured cross-sectional area of ​​the roadway is calculated and processed to obtain the boundary value of the cross-sectional area interval of the roadway; (2) Based on the boundary values ​​of the cross-sectional area interval of the roadway, the roadway length measurement data is corrected to obtain the roadway length correction parameters; (3) The roadway roughness coefficient is analyzed and processed to obtain the roadway roughness interval coefficient; (4) Perform interval calculation on the roadway resistance value according to the boundary value of the roadway cross-sectional area interval and the roadway length correction parameter to obtain the lower limit value and upper limit value of the roadway resistance; (5) Based on the lower limit value of the roadway resistance and the upper limit value of the roadway resistance, the interval number construction process is performed to obtain the roadway resistance interval data.

[0026] Specifically, the cross-sectional area of ​​the tunnel is measured using a multi-sensor network. The sensors collect the cross-sectional area data in real time and convert it into interval data. This conversion effectively reduces the impact of single-measurement errors and more accurately reflects the actual cross-sectional area of ​​the tunnel. In this way, the system can monitor changes in the tunnel's geometry in real time and provide a reliable basis for subsequent airflow calculations.

[0027] The length of the tunnel is measured via a sensor network. The system converts the total tunnel length into interval data, ensuring that the length of each tunnel segment is accurately recorded. The use of interval data further improves the tolerance to potential measurement errors, ensuring accuracy in real-world environments.

[0028] To accurately calculate air pressure loss, sensors measure the roughness of the tunnel and convert the measured roughness coefficient into interval data. This method takes into account the impact of roughness on airflow calculation and avoids errors that may result from single numerical measurements, making the airflow prediction results more consistent with reality. By using interval data, the system can comprehensively consider changes in the roughness coefficient, improving prediction accuracy.

[0029] For the obtained measurement data of tunnel cross-sectional area, length, and roughness coefficient, the system calculates the error range and corrects the data accuracy. By analyzing the measurement errors of the sensors and the influence of environmental changes, the system can determine the interval boundaries of each measurement value. The data can effectively cover all possible error ranges.

[0030] After obtaining the intervals of all measurement data, the system calculates the resistance interval of the roadway through interval operations. This process combines the roadway's geometric characteristics and airflow conditions, using a complex calculation model to derive the upper and lower bounds of the roadway's resistance. The interval data of the roadway resistance provides an accurate basis for subsequent airflow prediction, ensuring that the airflow calculation more closely matches actual ventilation conditions.

[0031] Taking the ventilation system of an underground parking lot as an example, to achieve more accurate airflow prediction, a method was implemented to acquire the parking lot's geometric parameters through a multi-sensor network. Sensors installed in the parking lot's passageways measure the cross-sectional area. The sensors collect the cross-sectional area data of the passageways in real time and convert the measurement results into interval data. Since the actual shape of the parking lot's passageways may be affected by factors such as vehicles and ambient temperature, the use of interval data by the sensors can accurately reflect the actual cross-sectional area and eliminate the influence of errors from single measurements.

[0032] After obtaining the cross-sectional area data, the system continues to measure the length of the passageways. Through a sensor network, the system acquires real-time data on the total length of the parking lot passageways and calculates the specific length of each passageway segment based on this data. This data is also converted into interval data to ensure that the length of each passageway segment is accurately recorded. In the calculation of airflow distribution, high-precision length data is crucial for ensuring the accuracy of airflow prediction. The use of interval data improves the measurement's error tolerance, ensuring that all potential errors and variations are considered in the airflow calculation.

[0033] Sensors measure the surface roughness coefficient of the parking lot aisles. The roughness coefficient affects wind pressure loss. The sensors record surface roughness data using high-precision measuring tools and convert it into interval data. This allows the system to effectively consider the impact of roughness on airflow during airflow calculations, avoiding the errors caused by treating roughness as a fixed value in traditional methods.

[0034] After these data are collected and converted into interval data, the system calculates and corrects the error range for all data. Considering the potential measurement errors of the sensors, the system corrects the data for channel cross-sectional area, length, and roughness coefficient based on the known sensor error range and the actual working environment. The corrected data effectively covers all possible error ranges, ensuring that the measurement results are more accurate in the actual environment and avoiding the impact of measurement errors on the airflow prediction results.

[0035] The system combines all measured interval data and calculates the resistance range of the passage through interval calculations. In this process, the system considers various factors such as the passage's geometry, roughness, and airflow velocity, ultimately determining the upper and lower limits of the passage resistance. This interval data serves as input for airflow prediction, ensuring the accuracy of subsequent airflow calculations. These processing steps enable the parking lot ventilation system to more accurately predict airflow, ensuring air circulation and environmental quality in the parking lot.

[0036] In one specific embodiment, the process of performing step S102 may specifically include the following steps: (1) Input the roadway resistance interval data into the air volume continuity calculation for node balance processing to obtain the roadway node air volume balance constraint conditions; (2) Based on the air volume balance constraint of the roadway node, the roadway air pressure loss value is calculated in intervals to obtain the roadway air pressure loss interval value; (3) Perform a balance analysis on the wind pressure of the roadway loop based on the wind pressure loss interval value of the roadway to obtain the roadway loop balance data; (4) The roadway loop balance data is iteratively solved to obtain the lower limit value and upper limit value of the roadway air volume; (5) Based on the lower limit value of the roadway air volume and the upper limit value of the roadway air volume, the interval range is constructed to obtain the interval range of the roadway air volume.

[0037] Specifically, the system inputs the roadway resistance range data into the airflow continuity calculation model for node balancing. Through this process, the system calculates the airflow distribution between each airflow node based on the roadway resistance data. This step aims to accurately simulate the airflow within the roadway, avoid uneven airflow distribution, and form a preliminary airflow prediction model.

[0038] After node balancing, the system calculates the air pressure loss range in the roadway based on balance constraints. By analyzing the roadway's geometric characteristics, air velocity, and resistance, the system calculates the air pressure loss range. Air pressure loss directly affects ventilation efficiency, and an accurate air pressure loss range provides crucial information for subsequent calculations, enabling the system to more precisely adjust ventilation plans.

[0039] The system performs a pressure balance analysis on the roadway loops. This process analyzes the pressure data of each roadway loop to ensure that the pressure is balanced across different ducts and loops. This analysis considers not only the roadway resistance but also changes in airflow. Through this balance analysis, the system can optimize the pressure distribution, ensuring a reasonable allocation of airflow among the loops and improving the overall efficiency of the ventilation system.

[0040] After completing the loop pressure balance analysis, the system iteratively solves for the airflow. During this process, the system continuously adjusts the airflow distribution until a stable balance is achieved between all nodes. Through multiple iterations, the system minimizes errors caused by initial assumptions, resulting in more accurate airflow predictions and ensuring that the airflow distribution across all loops meets actual ventilation requirements.

[0041] The system constructs an airflow range based on the calculated upper and lower bounds. This range reflects the uncertainty of airflow and provides more accurate data support for subsequent airflow calculations, helping the system dynamically adjust prediction results to meet ventilation needs under different environmental conditions.

[0042] Taking the air conditioning system of a large office building as an example, sensors measure indoor temperature, humidity, airflow velocity, and other parameters in real time. Combined with the air conditioning system's resistance data, this data is converted into interval data to reduce the impact of single measurement errors and ensure accurate reflection of airflow. The system uses this resistance data to calculate the wind pressure loss interval, precisely quantifying the wind pressure loss in each area based on airflow velocity and resistance coefficient, providing a basis for airflow regulation. The system also performs a balance analysis on the wind pressure difference between the return air vent and the supply air vent, adjusting the amount of return and supply air to ensure uniform indoor airflow and avoid localized overheating or overcooling. By iteratively solving and adjusting the airflow, the system ensures precise airflow distribution in each area, thereby optimizing the efficiency of the air conditioning system. Through airflow interval adjustment, the system ensures efficient operation and energy-saving effects under different environmental conditions.

[0043] In one specific embodiment, the process of executing step S103 may specifically include the following steps: (1) Based on the air volume range of the roadway, the lower limit value and the upper limit value of the air volume are extracted to obtain the roadway air volume boundary parameters; (2) Based on the roadway air volume boundary parameters, perform statistical analysis on the historical air volume data of the roadway to obtain the most likely value of the roadway air volume; (3) The boundary parameters of the roadway air volume and the most likely value of the roadway air volume are processed by triangular fuzzy number construction to obtain the triangular fuzzy number of the roadway air volume; (4) The membership function of the triangular fuzzy number of the roadway air volume is calculated to obtain the membership distribution curve of the roadway air volume; (5) Based on the membership distribution curve of the roadway air volume, perform fuzzy distribution data assembly processing to obtain the fuzzy distribution data of the roadway air volume.

[0044] Specifically, the system extracts the upper and lower bounds of the airflow range within the tunnel, calculates the maximum and minimum airflow values ​​within the tunnel, and obtains the possible range of airflow, providing data support for subsequent fuzzy number construction. Statistical analysis is performed using historical airflow data to calculate the most probable value of the tunnel airflow. Based on the actual airflow fluctuation pattern, the most probable value is determined, improving prediction accuracy. Based on the most probable value and the upper and lower bounds of the airflow range, a triangular fuzzy number of the tunnel airflow is constructed, using fuzzy mathematics to represent the uncertainty of airflow and express the range of airflow fluctuation. (See also...) Figure 2The figure is a schematic diagram of the membership function of the triangular fuzzy number provided in the embodiment of this application. The membership function represents the degree of membership of air volume in different intervals, and the probability distribution of air volume change is obtained. The formula for constructing the membership function of the triangular fuzzy number is described as follows: ,in This refers to the specific value of the air volume. This represents the minimum value within the airflow range. The most likely value for the air volume range. This represents the maximum value within the airflow range. Based on the airflow membership distribution curve, fuzzy distribution data is assembled. Using a membership function, the airflow data is organized into a fuzzy distribution form to reflect the possibility of airflow changes. This is based on the airflow membership distribution curve. This allows the construction of fuzzy distribution datasets. Let's define a discretized airflow dataset. Each airflow value Corresponding to a membership value The fuzzy distribution dataset of air volume can be represented as: in, A fuzzy distribution dataset representing air volume, containing air volume values. and their corresponding membership values .

[0045] In one specific embodiment, the process of executing step S104 may specifically include the following steps: (1) Based on the fuzzy distribution data of the air volume in the roadway, the importance of the roadway cross-sectional area and the roadway length is calculated and processed to obtain the roadway importance index; (2) The roadway function coefficient is weighted according to the roadway importance index to obtain the roadway dynamic weight value; (3) Input the dynamic weight values ​​of the roadway into the sorting algorithm for importance sorting to obtain the roadway weight sorting sequence; (4) The fuzzy distribution data of the roadway air volume is weighted and fused based on the roadway weight sorting sequence to obtain the roadway air volume weighted result; (5) The average value is calculated based on the weighted results of the roadway air volume to obtain the fused data of the average air volume of the roadway.

[0046] Specifically, the system calculates the importance index of each roadway based on the fuzzy distribution data of roadway airflow, analyzes the cross-sectional area and length data of the roadways, and evaluates the role and importance of each roadway in the overall ventilation system, obtaining an importance value that reflects the criticality of the roadway in the ventilation effect. The system assigns weights based on the calculated roadway importance index, ensuring that primary ventilation roadways receive a larger weight, while secondary ventilation roadways receive a relatively smaller weight. This more accurately reflects the influence of each roadway on airflow distribution and overall ventilation effect, with key roadways having a greater impact on the prediction results. The system inputs the dynamic weights of the roadways into a sorting algorithm, ranking the roadways according to their weight values. This ensures that airflow data from important roadways is processed first in airflow prediction, improving ventilation efficiency and accuracy. The system performs weighted fusion of the fuzzy distribution data of airflow based on the roadway weight ranking sequence, ensuring that the data for each roadway is weighted according to its importance, ultimately making the airflow prediction results more accurate and consistent with actual ventilation needs. By using the weighted fusion results, the system calculates the average air volume data of the roadway, providing an accurate reference for subsequent ventilation control and system adjustment, thus ensuring the stable operation and effective adjustment of the ventilation system.

[0047] Taking the air conditioning system of a smart office building as an example, the system collects data such as temperature, humidity, and airflow velocity in each room through sensors, calculates the importance index of each room, and determines the weight based on room area and usage frequency to ensure that frequently used rooms and large rooms have a larger proportion in airflow allocation. The system assigns weights to each room according to these importance indicators, ensuring that airflow is prioritized for main office areas. The system inputs the weight of each room into a sorting algorithm to rank the rooms according to their weights, so that rooms with higher weights are prioritized during airflow prediction, improving the overall energy efficiency of the air conditioning system. The system performs weighted fusion of the airflow data from each room based on the weighted ranking results, ensuring that the airflow prediction for each room meets its actual needs and is accurate. The system calculates the average airflow data for the entire office building using the weighted results, providing accurate reference data for subsequent temperature control and air conditioning, ensuring that the temperature and air quality in all areas of the building are maintained at an ideal state.

[0048] In one specific embodiment, the process of performing importance calculations on the cross-sectional area and length of the roadway based on the fuzzy distribution data of the roadway air volume can specifically include the following steps: (1) The cross-sectional area of ​​the fuzzy distribution data of the air volume in the roadway is extracted to obtain the cross-sectional area value of the roadway; (2) Based on the cross-sectional area values ​​of the roadway, the maximum cross-sectional area is calculated to obtain the weighting coefficient of the roadway cross-sectional area. (3) Perform a reciprocal operation on the reference length based on the roadway length correction parameters to obtain the roadway length weighting coefficient; (4) The weight coefficient of the roadway cross-sectional area and the weight coefficient of the roadway length are multiplied to obtain the importance value of the roadway foundation; (5) The importance index of the roadway is obtained by performing a weighted product of the roadway basic importance value and the roadway functional importance coefficient.

[0049] Specifically, the system analyzes the fuzzy distribution data of airflow in the roadways and extracts key parameters related to cross-sectional area. The fuzzy airflow distribution reflects the flow characteristics of airflow through the cross-section. Combined with the physical relationship between wind speed and airflow, the cross-sectional area of ​​the roadway is deduced. The system calculates or fits the functional relationship between wind speed distribution and airflow through fuzzy number expectation, extracting representative cross-sectional information to eliminate the interference of airflow uncertainty on cross-sectional area estimation, thus forming a structural characterization of the cross-sectional areas of different roadways. After obtaining the roadway cross-sectional area, the cross-sectional area weight coefficient is obtained by comparing the current roadway cross-sectional area with the maximum cross-sectional area, reflecting the relative proportion of the roadway's airflow carrying capacity. The larger the ratio, the more significant the roadway's contribution to the ventilation system, and thus it is assigned a higher weight in subsequent importance modeling.

[0050] The system introduces a length correction mechanism to normalize the tunnel length. The reciprocal of the reference length is calculated, assigning higher weights to shorter tunnels to reflect their priority in the airflow transport path. Shorter tunnels mean lower ventilation resistance, higher airflow efficiency, and stronger control over the overall ventilation path, thus making them more important. Multiplying the tunnel cross-sectional area weighting coefficient by the length weighting coefficient yields a fundamental importance value describing the tunnel's physical structure's airflow transmission capacity. This value comprehensively considers both cross-sectional size and length resistance, reflecting the tunnel's physical value in airflow transmission.

[0051] The system further introduces a roadway functional importance coefficient, considering the regulatory role of roadways on the overall ventilation system. For example, whether a roadway is a main airflow channel, connects to multiple branch roads, or undertakes special safety tasks. The basic importance value and the functional importance coefficient are weighted and multiplied to obtain a roadway importance index. This index simultaneously reflects the impact of the roadway's physical parameters and functional attributes on the ventilation system's operating status, giving the importance assessment both physical significance and practical application value, providing support for subsequent airflow allocation, prediction, and optimization.

[0052] Taking the ventilation system of an intelligent warehouse as an example, the system analyzes the fuzzy distribution data of airflow in various areas of the warehouse to extract the cross-sectional area parameters of different areas. By combining airflow and wind speed, the cross-sectional area values ​​of each section of the warehouse are deduced, and the ratio of the cross-sectional area of ​​each area to the maximum cross-sectional area is calculated to obtain the cross-sectional area weight coefficient for each area, which is used to evaluate the area's capacity to carry airflow. Next, the system normalizes the length information of each area in the warehouse, and assigns higher weights to shorter areas by calculating the reciprocal of the length of the reference area, reflecting their priority for airflow. Then, by multiplying the cross-sectional area weight coefficient and the length weight coefficient, the basic importance value of each area is obtained, representing the physical ventilation capacity of each area. Based on this, combined with the functional settings of the warehouse, such as the functional differences between the main cargo storage area and the aisle area, the system introduces a functional importance coefficient to weight the basic importance value, obtaining the final area importance index. Through this index, the system can dynamically adjust the ventilation effect of different areas in the warehouse, optimize airflow distribution, and improve the overall operating efficiency of the ventilation system.

[0053] In one specific embodiment, the process of executing step S105 may specifically include the following steps: (1) The average air volume data of the roadway is fused and processed by time series analysis to obtain the periodic change pattern of the roadway air volume; (2) The time decay coefficient is calculated based on the periodic change pattern of the roadway air volume to obtain the roadway time weight decay function; (3) The historical air volume sequence of the roadway is weighted and analyzed according to the roadway time weight decay function to obtain the roadway historical error sequence; (4) Perform trend prediction processing on the historical error sequence of the roadway to obtain the predicted error value of the roadway; (5) Based on the fusion data of the average air volume of the roadway and the predicted error value of the roadway, error compensation processing is performed to obtain the predicted data of the average air volume of the roadway.

[0054] Specifically, the system performs time-series analysis on the fused average airflow data from the tunnels to identify periodic patterns in the airflow data. Long-term analysis of historical airflow data reveals regular fluctuations in airflow, which may originate from seasonal factors, work schedules, or other external environmental changes. Through time-series processing, the system identifies the implicit periodic trends in the airflow data and establishes a corresponding periodic variation model, providing a theoretical basis and data support for subsequent airflow prediction. Using this periodic variation pattern, the system calculates a time decay coefficient to measure the influence of historical data on current airflow prediction over time. The decay coefficient calculation takes time into account; the influence of more distant historical data on current predictions gradually weakens, while newer data contributes more to the prediction results. This mechanism effectively improves the timeliness and accuracy of the prediction results.

[0055] After obtaining the time decay coefficient, the system performs a weighted analysis on the historical airflow sequence of the tunnel to obtain a historical error sequence. The weighted analysis process assigns different weights to historical data based on the decay coefficient. Combined with the error information from the historical data, the system can identify deviations and fluctuation trends in airflow prediction. This process helps identify potential sources of error in airflow prediction and provides a basis for subsequent error correction. By analyzing the error sequence, the system can more clearly understand which data have a significant impact on the prediction and further provide a reference for optimizing the prediction model. Based on the historical error sequence, the system uses a trend prediction method to compensate for the error. Through trend analysis of the error, the system can identify possible future error change trends, thereby correcting future airflow prediction results and reducing prediction deviations.

[0056] The system combines the compensated error with the average airflow data of the roadway for error compensation processing to obtain the final airflow prediction data. Through this error compensation processing, the system can optimize the original airflow prediction data, eliminating uncertainties caused by historical errors. This process not only improves the accuracy of airflow prediction but also enables the ventilation system to respond more flexibly to changing environments and working conditions. The combination of error compensation processing and airflow prediction data provides a more reliable basis for ventilation system control, ensuring system stability and efficiency. Using this method, the system can achieve precise airflow control in various complex environments, improving the overall efficiency of the ventilation system.

[0057] Taking an intelligent temperature control system as an example, the system performs time-series analysis on indoor temperature data to identify periodic temperature change patterns, such as daytime and nighttime temperature fluctuations or seasonal variations. Based on these periodic changes, the system calculates a time decay coefficient to measure the impact of historical data on current temperature predictions. This decay coefficient allows the system to place greater emphasis on recent temperature data, while the influence of more distant historical data on predictions gradually decreases. The system applies the time decay function to historical temperature data for weighted analysis, obtaining an error sequence in temperature prediction. By analyzing these error sequences, the system can identify potential biases in the temperature control model and compensate for these errors using trend prediction methods. The system then merges the compensated temperature prediction data with the actual temperature to obtain more accurate temperature control prediction data. This process ensures that the intelligent temperature control system can accurately adjust indoor temperature under various environmental changes, optimize energy use, and improve comfort and energy efficiency.

[0058] The method for predicting the average air volume in roadways in the embodiments of this application has been described above. The system for predicting the average air volume in roadways in the embodiments of this application is described below. Please refer to [link / reference needed]. Figure 3 One embodiment of the roadway average air volume prediction system in this application includes: The data acquisition module 201 is used to collect and process the cross-sectional area, length and roughness coefficient of the roadway through a multi-sensor network to obtain the roadway resistance range data. Quantization module 202 is used to quantify the uncertainty of roadway air volume based on the roadway resistance range data to obtain the roadway air volume range. The conversion module 203 is used to perform triangular fuzzy number conversion processing on the air volume range of the roadway to obtain fuzzy distribution data of the air volume in the roadway. The fusion module 204 is used to fuse the fuzzy distribution data of the roadway air volume through the roadway weight-induced ordered weighted average operator to obtain the fused data of the roadway average air volume. The correction module 205 is used to perform error correction processing on the historical air volume sequence of the roadway based on the fused data of the roadway average air volume, so as to obtain the predicted data of the roadway average air volume.

[0059] Through the collaborative efforts of the aforementioned components, the system can accurately acquire key parameters of the tunnel and perform precise airflow prediction. The acquisition module collects data such as cross-sectional area, length, and roughness coefficient of the tunnel in real time via a multi-sensor network, generating tunnel resistance range data to provide a reliable foundation for subsequent airflow prediction. The quantification module quantifies the uncertainty of tunnel airflow based on the resistance range data, deriving the airflow range range to comprehensively reflect the range of airflow changes and its uncertainty. The transformation module transforms the airflow range range using triangular fuzzy numbers, accurately describing the probability distribution of airflow through fuzzy mathematics, avoiding airflow prediction being limited to a single value. The fusion module fuses the fuzzy distribution data of airflow using a weighted average operator, combining tunnel weights to achieve reasonable fusion of airflow prediction results from different tunnels, ultimately obtaining accurate average airflow data for the tunnel. The correction module uses historical airflow data for error correction, further optimizing the prediction results and ensuring the accuracy of the final airflow prediction data. Through the collaborative work of this series of steps, the system achieves high-precision tunnel airflow prediction, providing reliable data support for actual ventilation control.

[0060] above Figure 3 The average air volume prediction system for roadways in this embodiment of the invention will be described in detail from the perspective of modular functional entities. The average air volume prediction device for roadways in this embodiment of the invention will be described in detail from the perspective of hardware processing.

[0061] Reference Figure 4 This invention also provides a roadway average air volume prediction device, which can be a server, and its internal structure can be as follows: Figure 4 As shown, the roadway average airflow prediction device includes a processor, memory, display screen, input device, network interface, and database connected via a system bus. The processor in this computer design provides computing and control capabilities. The memory of the roadway average airflow prediction device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores the operating system, computer programs, and database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database of the roadway average airflow prediction device stores the data corresponding to this embodiment. The network interface of the roadway average airflow prediction device is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements the above-described method.

[0062] Those skilled in the art will understand that Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present invention and does not constitute a limitation on the roadway average air volume prediction device to which the present invention is applied.

[0063] The present invention also provides a computer-readable storage medium, which can be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium, wherein the computer-readable storage medium stores instructions that, when the instructions are executed on a computer, cause the computer to perform the steps of the roadway average air volume prediction method.

[0064] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0065] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a lane average air volume prediction device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0066] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for predicting average air volume in roadways, characterized in that, The method includes: Data on roadway resistance range is obtained by collecting and processing data on roadway cross-sectional area, roadway length, and roadway roughness coefficient through a multi-sensor network. The uncertainty of the roadway air volume is quantified based on the roadway resistance range data to obtain the roadway air volume range. The tunnel air volume range is processed by triangular fuzzy number transformation to obtain fuzzy distribution data of tunnel air volume. The fuzzy distribution data of the roadway air volume is fused by the roadway weight-induced ordered weighted average operator to obtain the fused average air volume data of the roadway. Error correction processing is performed on the historical air volume sequence of the roadway based on the fused data of the roadway's average air volume to obtain the predicted data of the roadway's average air volume.

2. The method for predicting average air volume in roadways according to claim 1, characterized in that, The process of collecting and processing cross-sectional area, length, and roughness coefficient of the roadway through a multi-sensor network to obtain roadway resistance range data includes: The error range of the measured cross-sectional area of ​​the roadway is calculated to obtain the boundary values ​​of the roadway cross-sectional area interval. Based on the boundary values ​​of the tunnel cross-sectional area interval, the tunnel length measurement data is corrected to obtain the tunnel length correction parameters. By analyzing the variation range of the roadway roughness coefficient, the roadway roughness interval coefficient is obtained. The tunnel resistance values ​​are processed by interval calculation based on the tunnel cross-sectional area interval boundary value and the tunnel length correction parameter to obtain the lower limit value and upper limit value of the tunnel resistance. Based on the lower limit value and the upper limit value of the roadway resistance, interval number construction processing is performed to obtain the roadway resistance interval data.

3. The method for predicting average air volume in roadways according to claim 1, characterized in that, The process of quantifying the uncertainty of roadway airflow based on the roadway resistance range data to obtain the roadway airflow range includes: The roadway resistance range data is input into the air volume continuity calculation for node balancing processing to obtain the roadway node air volume balance constraint conditions. Based on the air volume balance constraint of the roadway node, the roadway air pressure loss value is calculated in intervals to obtain the roadway air pressure loss interval value. Based on the aforementioned roadway wind pressure loss range, the roadway loop wind pressure is balanced and processed to obtain roadway loop balance data; The roadway loop balance data is iteratively solved to obtain the lower limit value and upper limit value of the roadway air volume. Based on the lower limit value and the upper limit value of the roadway air volume, an interval range is constructed to obtain the roadway air volume interval range.

4. The method for predicting average air volume in roadways according to claim 1, characterized in that, The process of performing triangular fuzzy number transformation on the air volume range of the tunnel to obtain fuzzy distribution data of the air volume in the tunnel includes: Based on the air volume range of the roadway, the lower and upper limits of the air volume are extracted to obtain the roadway air volume boundary parameters. Based on the roadway air volume boundary parameters, the historical air volume data of the roadway is statistically analyzed and processed to obtain the most likely value of the roadway air volume. The roadway air volume boundary parameters and the most likely value of the roadway air volume are processed by triangular fuzzy number construction to obtain the roadway air volume triangular fuzzy number. The membership function of the triangular fuzzy number of the roadway air volume is calculated to obtain the membership distribution curve of the roadway air volume; Based on the membership distribution curve of the roadway air volume, fuzzy distribution data assembly processing is performed to obtain the fuzzy distribution data of the roadway air volume.

5. The method for predicting average air volume in roadways according to claim 2, characterized in that, The process of fusing the fuzzy distribution data of roadway airflow using a roadway weight-induced ordered weighted average operator to obtain fused roadway average airflow data includes: Based on the fuzzy distribution data of the roadway air volume, the importance of the roadway cross-sectional area and roadway length is calculated to obtain the roadway importance index. The roadway function coefficient is weighted according to the roadway importance index to obtain the roadway dynamic weight value. The dynamic weight values ​​of the roadway are input into a sorting algorithm for importance sorting to obtain a roadway weight sorting sequence. The fuzzy distribution data of the roadway air volume is weighted and fused based on the roadway weight sorting sequence to obtain the weighted result of the roadway air volume; The average value of the weighted results of the roadway air volume is calculated to obtain the fused data of the roadway average air volume.

6. The method for predicting average air volume in roadways according to claim 5, characterized in that, The importance index of the roadway is obtained by calculating the importance of the roadway cross-sectional area and roadway length based on the fuzzy distribution data of the roadway air volume, including: The fuzzy distribution data of the air volume in the tunnel is processed by cross-sectional area extraction to obtain the cross-sectional area value of the tunnel. Based on the roadway cross-sectional area value, the maximum cross-sectional area is calculated as a ratio to obtain the roadway cross-sectional area weighting coefficient. The reference length is calculated by reciprocal operation based on the tunnel length correction parameters to obtain the tunnel length weighting coefficient. The importance value of the roadway foundation is obtained by multiplying the weighting coefficient of the roadway cross-sectional area and the weighting coefficient of the roadway length. The roadway importance index is obtained by performing a weighted product of the roadway basic importance value and the roadway functional importance coefficient.

7. The method for predicting average air volume in roadways according to claim 1, characterized in that, The step of performing error correction processing on the historical air volume sequence of the roadway based on the fused average air volume data of the roadway to obtain the predicted average air volume data of the roadway includes: The average air volume data of the tunnel is fused and processed by time series analysis to obtain the periodic change pattern of the tunnel air volume. The time decay coefficient is calculated based on the periodic change pattern of the roadway air volume to obtain the roadway time weight decay function. The historical air volume sequence of the roadway is weighted and analyzed according to the roadway time weight decay function to obtain the roadway historical error sequence. The historical error sequence of the roadway is subjected to trend prediction processing to obtain the predicted error value of the roadway. Error compensation processing is performed based on the fused data of the average air volume of the roadway and the predicted error value of the roadway to obtain the predicted data of the average air volume of the roadway.

8. A roadway average air volume prediction system, characterized in that, For implementing the method for predicting average air volume in roadways as described in any one of claims 1-7, the average air volume prediction system in roadways comprises: The data acquisition module is used to collect and process the cross-sectional area, length, and roughness coefficient of the roadway through a multi-sensor network to obtain roadway resistance range data. The quantization module is used to quantify the uncertainty of the roadway air volume based on the roadway resistance range data to obtain the roadway air volume range. The conversion module is used to perform triangular fuzzy number conversion processing on the air volume range of the roadway to obtain fuzzy distribution data of the air volume in the roadway. The fusion module is used to fuse the fuzzy distribution data of the roadway air volume through the roadway weight-induced ordered weighted average operator to obtain the fused average air volume data of the roadway. The correction module is used to perform error correction processing on the historical air volume sequence of the roadway based on the fused data of the roadway average air volume, so as to obtain the predicted data of the roadway average air volume.

9. A roadway average air volume prediction device, characterized in that, It includes a memory and a processor, the memory storing a computer program that can run on the processor, and the processor executing the computer program to implement the roadway average air volume prediction method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is run by the processor, it causes the processor to perform the method for predicting the average air volume in the alley as described in any one of claims 1 to 7.

Images