A roadbed surface temperature control method and system for roadbed antifreeze test

Abstract

The present invention relates to the field of temperature control technology, and discloses a roadbed surface temperature control method and system for roadbed antifreeze experiments, the system comprising: a centralized cooling device, a distributed cooling device, a resistive temperature sensor and a control device; the distributed cooling device is movably arranged on the experimental roadbed, and the resistive temperature sensor is arranged under the experimental roadbed; the control device comprises a collection unit that collects temperature data for abnormal data analysis; when abnormal data exists, it is judged to start distributed cooling or mixed cooling according to the abnormal data and non-abnormal data; the judgment unit extracts the environmental parameters of the abnormal position to establish a feature set, processes all feature sets based on K-Means clustering, and judges whether they are the same type of abnormalities; the processing unit determines the operating power of the distributed cooling device. The present application improves the flexibility and accuracy of temperature regulation, and realizes the dynamic adjustment of the cooling power according to different abnormal situations.

Description

Technical Field

[0001] The present invention relates to the technical field of temperature control, and in particular to a method and system for controlling the surface temperature of a roadbed for a roadbed antifreeze test. Background Art

[0002] With climate change and the increasing demand for construction in cold regions, testing the frost resistance of roadbeds has become an important part of evaluating civil engineering and road construction. Roadbed frost resistance tests usually involve artificially controlling the temperature to simulate the freezing and thawing behavior of soil under different environmental conditions, so as to verify the stability and bearing capacity of the roadbed in severe cold weather. This experiment is crucial for the design and construction of road infrastructure in freezing areas, especially in the cold north and plateau areas.

[0003] In traditional roadbed antifreeze tests, temperature control is usually achieved by refrigeration equipment to simulate low-temperature environments, but current technologies have many problems in practical applications, especially in terms of uniformity and accuracy of temperature control. Most traditional refrigeration devices use centralized refrigeration systems to transfer cooling media to the experimental roadbed through refrigeration pipes, but this method cannot ensure the uniform distribution of the roadbed surface temperature, and is prone to local overcooling or uneven temperatures, which in turn affects the accuracy and reliability of the experimental results. In addition, existing cooling devices rely on fixed temperature control equipment during temperature regulation, which lacks flexibility and adjustability. For example, centralized cooling systems are usually unable to dynamically adjust according to temperature changes in different parts of the roadbed surface, which can cause some parts to be overcooled or insufficient to meet the required low-temperature conditions, especially in complex terrain or changing environments.

[0004] Therefore, it is necessary to design a roadbed surface temperature control method and system for roadbed antifreeze experiments to solve the problems existing in the current technology. Summary of the invention

[0005] In view of this, the present invention proposes a roadbed surface temperature control method and system for roadbed antifreeze tests, aiming to solve the problems of insufficient temperature control accuracy and uniformity in current roadbed antifreeze tests, and prone to local overcooling or uneven temperature.

[0006] In one aspect, the present invention provides a roadbed surface temperature control system for roadbed antifreeze test, comprising:

[0007] A centralized cooling device, a distributed cooling device, a resistive temperature sensor and a control device; wherein the centralized cooling device is connected to a cooling pipeline, the cooling pipeline is arranged above the experimental roadbed, the distributed cooling device is movably arranged on the experimental roadbed, the resistive temperature sensor is arranged under the experimental roadbed, and the resistive temperature sensor is provided with a plurality of them to form a temperature sensor array;

[0008] The control device is connected to the centralized cooling device, the distributed cooling device and the resistive temperature sensor, and the control device includes a collection unit, a judgment unit and a processing unit, wherein:

[0009] The acquisition unit is configured to acquire temperature data of the temperature sensor array and perform abnormal data analysis on the temperature data; when it is determined that there is no abnormal data, the acquisition unit determines whether to start centralized cooling according to the mean value of the temperature data; when it is determined that there is abnormal data, the acquisition unit determines whether to start distributed cooling or mixed cooling according to the abnormal data and non-abnormal data, and the mixed cooling includes centralized cooling and distributed cooling;

[0010] The judgment unit is configured to extract environmental parameters of abnormal locations to establish feature sets when the acquisition unit determines to perform distributed cooling, process all feature sets based on K-Means clustering, and judge whether they are the same type of abnormalities according to the clustering results;

[0011] The processing unit is configured to determine the operating power of the distributed cooling device according to the judgment result of the judgment unit.

[0012] Furthermore, when the acquisition unit performs abnormal data analysis on the temperature data, it includes:

[0013] The acquisition unit creates a two-dimensional temperature map based on the temperature data according to the distribution position of each resistive temperature sensor in the temperature sensor array;

[0014] In the two-dimensional temperature map, any temperature data is determined as the origin ( ), with the origin as the center and r as the correction radius, determine the correction range;

[0015] Calculating the correction temperature according to the temperature data of each coordinate point within the correction range, when the difference between the temperature data of the origin and the correction temperature is greater than the temperature difference threshold, determining the origin as an abnormal data point, and recording the coordinates of the abnormal data point;

[0016] When the abnormal data point exists in the two-dimensional temperature map, the acquisition unit determines that abnormal data exists;

[0017] The corrected temperature is calculated by the following formula:

[0018]

[0019] in, represents the correction temperature, r represents the correction radius, (x, ) represents the coordinates of the origin, Represents a two-dimensional temperature graph Temperature data of the point.

[0020] Further, when it is determined that there is no abnormal data, the acquisition unit determines whether to start centralized cooling according to the mean value of the temperature data, including:

[0021] The acquisition unit obtains a temperature data mean value of the temperature sensor array according to the temperature data, compares the temperature data mean value with a maximum temperature threshold value, and determines whether to start centralized cooling according to the comparison result;

[0022] When the average value of the temperature data is less than or equal to the maximum temperature threshold, the acquisition unit determines not to start centralized cooling; when the average value of the temperature data is greater than the maximum temperature threshold, the acquisition unit determines to start centralized cooling and determines the operating power of the centralized cooling device based on the temperature data.

[0023] Furthermore, when the acquisition unit determines the operating power of the centralized cooling device according to the temperature data, it includes:

[0024] The acquisition unit obtains a temperature difference based on the temperature data mean and the maximum temperature threshold, and the temperature difference is the difference between the temperature data and the maximum temperature threshold. The operating power of the centralized cooling device is determined based on the temperature difference, and the temperature difference is proportional to the operating power of the centralized cooling device.

[0025] Further, when it is determined that there is abnormal data, the acquisition unit determines to start distributed cooling or mixed cooling according to the abnormal data and the non-abnormal data, including:

[0026] The acquisition unit classifies the temperature data of the abnormal data points into an abnormal temperature set, and classifies the temperature data of the non-abnormal data points into a non-abnormal temperature set, obtains an abnormal temperature mean according to the abnormal temperature set, obtains a non-abnormal temperature mean according to the non-abnormal temperature set, compares the abnormal temperature mean and the non-abnormal temperature mean with the maximum temperature threshold, and determines whether to start distributed cooling or mixed cooling according to the comparison result;

[0027] When the abnormal temperature average and the non-abnormal temperature average are both greater than the maximum temperature threshold, the acquisition unit determines to start mixed cooling;

[0028] When the abnormal temperature average is greater than the maximum temperature threshold and the non-abnormal temperature average is less than or equal to the maximum temperature threshold, the acquisition unit determines to start distributed cooling.

[0029] Further, the judgment unit processes all feature sets based on K-Means clustering to obtain clustering results, including: the environmental parameters include temperature, humidity and wind speed;

[0030] When the judgment unit establishes the feature set, it includes normalizing the data in each feature set;

[0031] S1: The judgment unit initializes K centroids in all the feature sets, and distributes the remaining feature sets to the nearest centroids to form K clusters;

[0032] S2: Recalculate the centroid of each cluster;

[0033] S3: Repeat S1 and S2 until the center of mass no longer changes;

[0034] S4: when there is only one centroid, the judgment unit determines that the abnormal type of all abnormal data is unique; when there are multiple centroids, the judgment unit determines that the abnormal type of the abnormal data is not unique;

[0035] The centroid calculation formula is as follows:

[0036]

[0037] Among them, Mk represents the centroid of the kth cluster, represents the number of feature sets in the kth cluster, and Zi represents the feature set of the i-th abnormal data.

[0038] Furthermore, when the processing unit determines the operating power of the distributed cooling device according to the judgment result of the judgment unit, it includes:

[0039] When the judgment unit determines that the abnormal type of all abnormal data is unique, the processing unit compares the feature set with a historical feature set data set, wherein the historical feature set data set includes a historical feature set and a corresponding historical operating power of a historical distributed cooling device;

[0040] When the same data as the feature set exists in the historical feature set data set, the processing unit uses the historical operating power as the operating power;

[0041] When there is no data identical to the feature set in the historical feature set data set, the processing unit obtains the operating power according to the feature set by the following formula;

[0042]

[0043] Among them, P represents the operating power, Pmin represents the minimum power of the distributed cooling device, T represents the normalized result of temperature data, H represents the normalized result of humidity data, V represents the normalized result of wind speed data, T0 represents the normalized result of the maximum temperature threshold, and T0≠0.

[0044] Furthermore, when the judgment unit determines that the abnormal type of all abnormal data is not unique, the processing unit obtains the number of feature sets in each abnormal type according to the clustering result, takes the abnormal type containing the largest number of feature sets as the main type, calculates the abnormal factors of the remaining abnormal types and the main type through a similarity calculation formula, obtains the operating power of the main type at the abnormal point according to the feature set of the main type, and determines the adjustment coefficient according to the abnormal factor to adjust the operating power to obtain the operating power at the remaining abnormal types.

[0045] Further, when the judgment unit determines the adjustment coefficient according to the abnormal factor to adjust the operating power to obtain the operating power at other abnormal types, it includes:

[0046] The abnormal factor is compared with a preset first abnormal factor and a preset second abnormal factor respectively, and an adjustment coefficient is determined according to the comparison result to adjust the operating power to obtain the operating power at other abnormal types, wherein the first abnormal factor is less than the second abnormal factor;

[0047] When the abnormal factor is less than or equal to the first abnormal factor, the first adjustment coefficient is determined to adjust the operating power; when the abnormal factor is greater than the first abnormal factor and less than or equal to the second abnormal factor, the second adjustment coefficient is determined to adjust the operating power; when the abnormal factor is greater than the second abnormal factor, the third adjustment coefficient is determined to adjust the operating power; the first adjustment coefficient is less than the second adjustment coefficient, and the second adjustment coefficient is less than the third adjustment coefficient.

[0048] Compared with the prior art, the beneficial effect of the present invention is that by combining a centralized cooling device with a distributed cooling device, the problem of uneven temperature control and slow response in the traditional roadbed antifreeze experiment is solved. By laying out an array of resistive temperature sensors under the experimental roadbed, the temperature data of different areas are monitored in real time. The control device performs intelligent analysis on temperature anomalies, identifies the type of anomalies based on a clustering algorithm, and flexibly adjusts the cooling method. If a temperature anomaly is detected, a distributed cooling or mixed cooling strategy is initiated according to different environmental parameters to ensure accurate control and uniform distribution of the temperature. The flexibility and accuracy of temperature regulation are improved, and the cooling power is dynamically adjusted according to different abnormal situations, effectively ensuring the stability and reliability of the experiment.

[0049] On the other hand, the present application also provides a roadbed surface temperature control method for roadbed antifreeze test, which is applied to the roadbed surface temperature control system for roadbed antifreeze test, comprising:

[0050] Collect temperature data from the temperature sensor array and perform abnormal data analysis on the temperature data; when it is determined that there is no abnormal data, determine whether to start centralized cooling according to the mean value of the temperature data; when it is determined that there is abnormal data, determine whether to start distributed cooling or mixed cooling according to the abnormal data and non-abnormal data, and the mixed cooling includes centralized cooling and distributed cooling;

[0051] When it is determined that distributed cooling is to be performed, the environmental parameters of the abnormal location are extracted to establish a feature set, all feature sets are processed based on K-Means clustering, and whether they are the same type of anomalies is determined based on the clustering results;

[0052] The operating power of the distributed cooling device is determined according to the judgment result of the judgment unit.

[0053] It is understandable that the above-mentioned roadbed surface temperature control method and system for roadbed antifreeze test have the same beneficial effects, which will not be described in detail here. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0055] Figure 1 A structural block diagram of a roadbed surface temperature control system for a roadbed antifreeze test provided by an embodiment of the present invention;

[0056] Figure 2 A flow chart of a method for controlling the surface temperature of a roadbed for a roadbed antifreeze test provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0057] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art. It should be noted that, in the absence of conflict, the embodiments of the present invention and the features described in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0058] In some embodiments of the present application, see Figure 1 As shown, a roadbed surface temperature control system for roadbed antifreeze test includes:

[0059] A centralized cooling device, a distributed cooling device, a resistive temperature sensor and a control device. The centralized cooling device is connected to a cooling pipe, the cooling pipe is arranged above the experimental roadbed, the distributed cooling device is movably arranged on the experimental roadbed, the resistive temperature sensor is arranged under the experimental roadbed, and a plurality of resistive temperature sensors are arranged to form a temperature sensor array.

[0060] The control device is connected with the centralized cooling device, the distributed cooling device and the resistive temperature sensor. The control device includes a collection unit, a judgment unit and a processing unit, wherein:

[0061] The acquisition unit is configured to acquire temperature data from the temperature sensor array and perform abnormal data analysis on the temperature data. When it is determined that there is no abnormal data, the acquisition unit determines whether to start centralized cooling according to the mean value of the temperature data. When it is determined that there is abnormal data, the acquisition unit determines whether to start distributed cooling or mixed cooling according to the abnormal data and non-abnormal data, and the mixed cooling includes centralized cooling and distributed cooling.

[0062] The judgment unit is configured to extract environmental parameters of abnormal locations to establish feature sets when the acquisition unit determines to perform distributed cooling, process all feature sets based on K-Means clustering, and judge whether they are the same type of abnormalities according to the clustering results.

[0063] The processing unit is configured to determine the operating power of the distributed cooling device according to the judgment result of the judgment unit.

[0064] Specifically, the centralized cooling device transports the cooling medium to the top of the experimental roadbed through the cooling pipe, thereby cooling a large area. Centralized cooling is suitable for cooling a large area of ​​the entire area, but due to insufficient local temperature regulation, uneven temperature is prone to occur. The distributed cooling device is movable and flexibly set on the surface of the experimental roadbed, and can be precisely adjusted for local temperature anomalies. Through the distributed device, it is possible to ensure that the temperature is evenly distributed in different areas, especially in the case of temperature fluctuations, to achieve local fine regulation. The resistive temperature sensor is arranged under the experimental roadbed to form a temperature sensor array to collect temperature data from different areas in real time. Through the array arrangement, the temperature distribution of the entire experimental area can be fully and evenly monitored to ensure that temperature anomalies can be discovered in time. The control device is responsible for integrating, analyzing and processing the data collected from the temperature sensor. The acquisition unit in the control device monitors the temperature changes in real time through the resistive temperature sensor array. When abnormal data is detected, it is analyzed whether the data belongs to temperature anomalies. If there is no abnormal data, the temperature data mean is calculated to decide whether to start centralized cooling. When abnormal data is detected, the abnormal data is further analyzed to determine whether it is necessary to start distributed cooling or mixed cooling (i.e., start centralized and distributed cooling at the same time). When it is determined that distributed cooling needs to be started, the judgment unit extracts the environmental parameters of the abnormal location to form a feature set. These feature sets are analyzed by the K-Means clustering algorithm, all abnormal data are classified, and different types of abnormalities are identified. The auxiliary processing unit adopts different distributed cooling powers according to different types of abnormalities to improve the cooling effect. The processing unit determines the operating power of the distributed cooling device based on the results of the K-Means clustering analysis. If the abnormal type is relatively consistent, it will be compared with historical data, and the historical operating power will be used as a reference to determine the current distributed cooling power. If a new or unknown abnormal type occurs, a new cooling power is calculated based on the current feature set.

[0065] It is understandable that by deploying the resistive temperature sensor array, the temperature distribution of the experimental roadbed can be monitored in real time and comprehensively, so as to detect local temperature anomalies in time and take corresponding cooling measures. In the case of temperature anomalies, centralized cooling, distributed cooling or a hybrid cooling strategy combining the two is automatically selected. It can be flexibly adjusted according to actual conditions, avoiding the problem that the single cooling method in the traditional temperature control system cannot cope with complex temperature changes. Through the K-Means clustering algorithm, the type of temperature anomaly can be intelligently identified, and targeted cooling solutions can be adopted according to the different types of anomalies. The temperature control accuracy is improved, avoiding the limitations of human intervention and fixed rules. By adjusting the operating power of the distributed cooling device in real time, it is possible to improve the energy utilization efficiency while ensuring the temperature control accuracy, avoiding excessive cooling or energy waste.

[0066] In some embodiments of the present application, when the acquisition unit performs abnormal data analysis on the temperature data, it includes: the acquisition unit creates a two-dimensional temperature map of the temperature data according to the distribution position of each resistive temperature sensor in the temperature sensor array.

[0067] In the two-dimensional temperature graph, any temperature data is determined as the origin ( ), with the origin as the center and r as the correction radius to determine the correction range.

[0068] The correction temperature is calculated based on the temperature data of each coordinate point within the correction range. When the difference between the temperature data of the origin and the correction temperature is greater than the temperature difference threshold, the origin is determined to be an abnormal data point and the coordinates of the abnormal data point are recorded.

[0069] When there are abnormal data points in the two-dimensional temperature map, the acquisition unit determines that there are abnormal data.

[0070] The corrected temperature is calculated using the following formula:

[0071]

[0072] in, represents the correction temperature, r represents the correction radius, (x, ) represents the coordinates of the origin, Represents a two-dimensional temperature graph Temperature data of the point.

[0073] Specifically, the experimental area is divided into several coordinate points by arranging the positions of the resistive temperature sensor array, and the data of each temperature sensor is mapped to the coordinate point using a two-dimensional temperature map. The temperature value of each point represents the temperature of the position, and all points together constitute a panoramic view of the temperature distribution. After selecting an origin as a reference point, with this point as the center of the circle, other points within the correction radius r will affect the temperature correction of the origin. Pay attention to the changes in temperature distribution around the origin to avoid interference from isolated abnormal points. The setting of the temperature difference threshold is the key to judging whether the temperature data is abnormal. If the temperature difference between the origin and the corrected temperature of the surrounding neighborhood points is too large, it means that the temperature of the point is abnormal and there is a significant difference from the surrounding temperature, which may affect the accuracy of the experimental results. By recording the coordinates of the abnormal points, the area with abnormal temperature can be accurately located, and data support can be provided for subsequent cooling adjustments. For example, when distributed cooling is required, these abnormal points can be used to determine which areas need to be cooled.

[0074] It can be understood that by calculating the corrected temperature on the two-dimensional temperature map and comparing the difference with the origin temperature, local temperature anomalies can be accurately identified. This spatialized anomaly detection method is more comprehensive than traditional single-point temperature detection, and can accurately locate the temperature anomaly area, thereby improving the pertinence and effectiveness of temperature control. By setting the correction radius r and the temperature difference threshold, the sensitivity of temperature judgment can be flexibly adjusted according to different experimental requirements. By adjusting these parameters, the tolerance to temperature anomalies under different experimental conditions can be adapted and the temperature control strategy can be optimized. Once the abnormal data point is determined, the cooling strategy can be quickly adjusted, and distributed cooling or mixed cooling can be started for the abnormal area, so as to ensure that the temperature of the experimental area is accurately controlled. The data-driven dynamic adjustment method can effectively avoid the problem of excessive cooling or uneven cooling, and ensure the stability and reliability of the experimental results. Intelligent control is achieved by combining the spatial distribution of temperature data and neighborhood analysis. The dynamic identification and automatic processing of abnormal points reduce manual intervention and human errors, and improve the automation of the experiment.

[0075] In some embodiments of the present application, when it is determined that there is no abnormal data, the acquisition unit determines whether to turn on centralized cooling based on the average temperature data, including: the acquisition unit obtains the average temperature data of the temperature sensor array based on the temperature data, compares the average temperature data with the maximum temperature threshold, and determines whether to turn on centralized cooling based on the comparison result.

[0076] Specifically, when the mean value of the temperature data is less than or equal to the maximum temperature threshold, the collection unit determines not to start centralized cooling. When the mean value of the temperature data is greater than the maximum temperature threshold, the collection unit determines to start centralized cooling and determines the operating power of the centralized cooling device according to the temperature data.

[0077] In some embodiments of the present application, when the acquisition unit determines the operating power of the centralized cooling device based on the temperature data, it includes: the acquisition unit obtains a temperature difference based on the average of the temperature data and the maximum temperature threshold, the temperature difference is the difference between the temperature data and the maximum temperature threshold, and the operating power of the centralized cooling device is determined based on the temperature difference, and the temperature difference is proportional to the operating power of the centralized cooling device.

[0078] Specifically, the acquisition unit sums up the temperature data collected from the resistive temperature sensor array and then divides it by the number of sensors to obtain the temperature mean. This mean represents the overall temperature level of the experimental roadbed. The temperature mean is compared with the preset maximum temperature threshold, which can be the maximum tolerable temperature set according to the experimental requirements. When the mean exceeds the threshold, the temperature is deemed to be excessive and cooling is triggered. When the temperature mean exceeds the maximum threshold, the temperature difference is calculated, that is, "temperature mean - maximum temperature threshold". It reflects the deviation between the current temperature and the expected temperature. The temperature difference is proportional to the operating power of the centralized cooling device. Specifically, the larger the temperature difference, the greater the required cooling power. The cooling is accelerated by controlling the power output of the temperature control device until the temperature drops to the target range.

[0079] It is understandable that by real-time monitoring of temperature data, and automatically deciding whether to start cooling measures based on the relationship between the temperature mean and the threshold, the power of the centralized cooling device can be flexibly adjusted according to actual needs, based on the proportional relationship between the temperature difference and the operating power. The greater the temperature difference, the greater the cooling capacity provided, thereby avoiding excessive or insufficient cooling and ensuring accurate control of the roadbed temperature. By comparing the mean calculation with the temperature threshold, it is possible to quickly identify high temperature situations and quickly take cooling measures. Compared with traditional systems, it effectively responds to temperature changes and avoids temperature fluctuations affecting experimental results. The proportional relationship between the temperature difference and power helps to control the power output of the cooling device and avoid ineffective waste of power. When cooling is required, only the minimum power required is provided, which optimizes energy use and reduces unnecessary energy consumption.

[0080] In some embodiments of the present application, when it is determined that abnormal data exists, the acquisition unit determines whether to start distributed cooling or mixed cooling based on the abnormal data and non-abnormal data, including: the acquisition unit classifies the temperature data of the abnormal data points into an abnormal temperature set, and classifies the temperature data of the non-abnormal data points into a non-abnormal temperature set, obtains the abnormal temperature mean based on the abnormal temperature set, obtains the non-abnormal temperature mean based on the non-abnormal temperature set, compares the abnormal temperature mean and the non-abnormal temperature mean with the maximum temperature threshold, respectively, and determines to start distributed cooling or mixed cooling based on the comparison result.

[0081] Specifically, when the average value of abnormal temperature and the average value of non-abnormal temperature are both greater than the maximum temperature threshold, the acquisition unit determines to start mixed cooling. When the average value of abnormal temperature is greater than the maximum temperature threshold and the average value of non-abnormal temperature is less than or equal to the maximum temperature threshold, the acquisition unit determines to start distributed cooling.

[0082] In some embodiments of the present application, the judgment unit processes all feature sets based on K-Means clustering to obtain clustering results, including: environmental parameters include temperature, humidity and wind speed.

[0083] When the judgment unit establishes the feature set, it includes normalizing the data in each feature set.

[0084] S1: The judgment unit initializes K centroids in all feature sets and assigns the remaining feature sets to the nearest centroids to form K clusters.

[0085] S2: Recalculate the centroid of each cluster.

[0086] S3: Repeat S1 and S2 until the centroid no longer changes.

[0087] S4: When there is only one centroid, the judging unit judges that the abnormal type of all abnormal data is unique. When there are multiple centroids, the judging unit judges that the abnormal type of the abnormal data is not unique.

[0088] The centroid calculation formula is as follows:

[0089]

[0090] Among them, Mk represents the centroid of the kth cluster, represents the number of feature sets in the kth cluster, and Zi represents the feature set of the i-th abnormal data.

[0091] Specifically, the acquisition unit first identifies those abnormal data points with high temperatures according to the range and threshold of the temperature data, and separates these points from the normal data points to form two sets of data sets (abnormal temperature set and non-abnormal temperature set). K-Means clustering is performed on the environmental feature set of all abnormal data to divide them into multiple clusters. The clustering process continuously adjusts the position of the centroid until all data points are classified into the correct cluster. Each cluster represents a type of abnormality. By comparing the temperature mean of the abnormal data and the non-abnormal data with the highest temperature threshold, it is determined whether cooling measures need to be initiated and which cooling strategy to choose. The comparison of the temperature mean determines whether mixed cooling is required or only distributed cooling is initiated. When the judgment unit finds that all abnormal data belong to the same cluster, it determines that the abnormal type is unique, and then optimizes the cooling strategy. If there are multiple clusters of abnormal data, it means that there are different types of abnormalities, and more sophisticated cooling strategies are needed to deal with different types of abnormalities.

[0092] It is understandable that when hybrid cooling is adopted, the centralized cooling power can be determined in the manner described in the above embodiment. The abnormal temperature mean and the non-abnormal temperature mean are both greater than the maximum temperature threshold. This is the most typical case, which means that the temperature of the entire experimental roadbed is too high, and centralized cooling and distributed cooling (hybrid cooling) need to be enabled at the same time. The abnormal temperature mean is greater than the maximum temperature threshold, and the non-abnormal temperature mean is less than or equal to the maximum temperature threshold. In this case, only the temperature of the abnormal area exceeds the threshold, so only the abnormal area needs to be distributed cooled, and the non-abnormal area does not need to be cooled. Since the experimental method targeted by this scheme adopts gradual cooling, there is no one-time temperature drop.

[0093] In some embodiments of the present application, when the processing unit determines the operating power of the distributed cooling device according to the judgment result of the judgment unit, it includes:

[0094] When the judgment unit determines that the abnormal type of all abnormal data is unique, the processing unit compares the feature set with a historical feature set data set, where the historical feature set data set includes a historical feature set and a corresponding historical operating power of the historical distributed cooling device.

[0095] When the historical feature set data set contains the same data as the feature set, the processing unit uses the historical operating power as the operating power.

[0096] When there is no data identical to the feature set in the historical feature set data set, the processing unit obtains the operating power according to the feature set by using the following formula.

[0097]

[0098] Among them, P represents the operating power, Pmin represents the minimum power of the distributed cooling device, T represents the normalized result of temperature data, H represents the normalized result of humidity data, V represents the normalized result of wind speed data, T0 represents the normalized result of the maximum temperature threshold, and T0≠0.

[0099] In some embodiments of the present application, when the judgment unit determines that the abnormal type of all abnormal data is not unique, the processing unit obtains the number of feature sets in each abnormal type according to the clustering result, takes the abnormal type containing the largest number of feature sets as the main type, calculates the abnormal factors of the remaining abnormal types and the main type through the similarity calculation formula, obtains the operating power of the main type at the abnormal point according to the feature set of the main type, and determines the adjustment coefficient according to the abnormal factor to adjust the operating power to obtain the operating power at the remaining abnormal types.

[0100] In some embodiments of the present application, when the judgment unit determines the adjustment coefficient according to the abnormal factor to adjust the operating power to obtain the operating power at other abnormal types, it includes:

[0101] The abnormal factor is compared with the preset first abnormal factor and second abnormal factor respectively, and the adjustment coefficient is determined according to the comparison result to adjust the operating power to obtain the operating power of other abnormal types, and the first abnormal factor is smaller than the second abnormal factor.

[0102] When the abnormal factor is less than or equal to the first abnormal factor, the first adjustment coefficient is determined to adjust the operating power. When the abnormal factor is greater than the first abnormal factor and less than or equal to the second abnormal factor, the second adjustment coefficient is determined to adjust the operating power. When the abnormal factor is greater than the second abnormal factor, the third adjustment coefficient is determined to adjust the operating power. The first adjustment coefficient is less than the second adjustment coefficient, and the second adjustment coefficient is less than the third adjustment coefficient.

[0103] Specifically, when it is determined that the abnormal type of all abnormal data is unique, the processing unit compares the current feature set with the historical feature set data set. The historical data set includes past feature sets and the corresponding distributed cooling device operating power. Through comparison, if there is data in the historical data set that is the same as the current feature set, the historical operating power is directly used as the current operating power. If there is no matching historical data, the operating power is calculated by a formula based on parameters such as temperature, humidity, and wind speed of the current feature set. When the judgment unit determines that the abnormal type is not unique, the processing unit finds the abnormal type containing the largest number of feature sets as the main type based on the clustering results. Then, the abnormal factor of this type is calculated. The abnormal factor is obtained by comparing the similarity between the feature sets of other abnormal types and the feature set of the main type. The abnormal factor calculation formula is:

[0104]

[0105] Among them, Y represents the abnormal factor, U represents the number of features in the feature set, Eu represents the normalized result of the u-th feature data in the feature set, and E0 represents the normalized result of the u-th feature data in the main type.

[0106] It is understandable that a representative feature set is selected from the main type of anomaly to perform the above anomaly factor calculation. Position judgment can be used when selecting the representative feature set. For example, data in the main type of anomaly that is closer to the center area of ​​the experimental roadbed is used as the representative feature.

[0107] It is understandable that by comparing with historical data, past experience data can be used to quickly respond to current cooling needs. When matching historical data, redundant calculations are avoided, thereby improving the system response speed. When the anomaly type is not unique, the anomaly factor obtained based on K-Means clustering, combined with different adjustment coefficients, can accurately adjust the operating power, making the cooling of each abnormal area more accurate and adaptive. Through the hierarchical setting of the adjustment coefficient, the power can be flexibly adjusted according to the different degrees of anomaly types to optimize the cooling efficiency. In a complex environment, when there are multiple types of abnormal data, by introducing clustering and anomaly factor adjustment mechanisms, the operating power can be adaptively adjusted according to environmental changes without causing excessive or insufficient cooling.

[0108] In the above embodiment, by combining a centralized cooling device with a distributed cooling device, the problems of uneven temperature control and slow response in the traditional roadbed antifreeze experiment are solved. By laying out an array of resistive temperature sensors under the experimental roadbed and monitoring the temperature data of different areas in real time, the control device performs intelligent analysis of temperature anomalies, identifies the type of anomalies based on the clustering algorithm, and flexibly adjusts the cooling method. If a temperature anomaly is detected, a distributed cooling or mixed cooling strategy is initiated according to different environmental parameters to ensure accurate control and uniform distribution of temperature. The flexibility and accuracy of temperature regulation are improved, and the cooling power is dynamically adjusted according to different abnormal situations, effectively ensuring the stability and reliability of the experiment.

[0109] In another preferred embodiment based on the above embodiment, refer to Figure 2 As shown, this embodiment provides a roadbed surface temperature control method for roadbed antifreeze test, which is applied to the roadbed surface temperature control system for roadbed antifreeze test, and includes:

[0110] S100: Collect temperature data from the temperature sensor array and perform abnormal data analysis on the temperature data; when it is determined that there is no abnormal data, determine whether to start centralized cooling according to the mean value of the temperature data; when it is determined that there is abnormal data, determine whether to start distributed cooling or mixed cooling according to the abnormal data and non-abnormal data, and the mixed cooling includes centralized cooling and distributed cooling;

[0111] S200: When it is determined that distributed cooling is to be performed, the environmental parameters of the abnormal location are extracted to establish a feature set, all feature sets are processed based on K-Means clustering, and whether they are the same type of abnormalities is determined according to the clustering results;

[0112] S300: Determine the operating power of the distributed cooling device according to the judgment result of the judgment unit.

[0113] It is understandable that by combining centralized cooling devices with distributed cooling devices, the problems of uneven temperature control and slow response in traditional roadbed antifreeze experiments have been solved. By laying out an array of resistive temperature sensors under the experimental roadbed and monitoring the temperature data of different areas in real time, the control device conducts intelligent analysis of temperature anomalies, identifies the type of anomalies based on the clustering algorithm, and flexibly adjusts the cooling method. If a temperature anomaly is detected, a distributed cooling or mixed cooling strategy is initiated according to different environmental parameters to ensure accurate control and uniform distribution of temperature. The flexibility and accuracy of temperature regulation are improved, and the cooling power is dynamically adjusted according to different abnormal conditions, effectively ensuring the stability and reliability of the experiment.

[0114] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0115] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0116] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0117] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0118] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A roadbed surface temperature control system for roadbed antifreeze test, characterized in that: include: A centralized cooling device, a distributed cooling device, a resistive temperature sensor and a control device; wherein the centralized cooling device is connected to a cooling pipeline, the cooling pipeline is arranged above the experimental roadbed, the distributed cooling device is movably arranged on the experimental roadbed, the resistive temperature sensor is arranged under the experimental roadbed, and the resistive temperature sensor is provided with a plurality of them to form a temperature sensor array; The control device is connected to the centralized cooling device, the distributed cooling device and the resistive temperature sensor, and the control device includes a collection unit, a judgment unit and a processing unit, wherein: The acquisition unit is configured to acquire temperature data of the temperature sensor array and perform abnormal data analysis on the temperature data; when it is determined that there is no abnormal data, the acquisition unit determines whether to start centralized cooling according to the mean value of the temperature data; when it is determined that there is abnormal data, the acquisition unit determines whether to start distributed cooling or mixed cooling according to the abnormal data and non-abnormal data, and the mixed cooling includes centralized cooling and distributed cooling; The judgment unit is configured to extract environmental parameters of abnormal locations to establish feature sets when the acquisition unit determines to perform distributed cooling, process all feature sets based on K-Means clustering, and judge whether they are the same type of abnormalities according to the clustering results; The processing unit is configured to determine the operating power of the distributed cooling device according to the judgment result of the judgment unit.

2. The roadbed surface temperature control system for roadbed antifreeze test according to claim 1 is characterized in that: When the acquisition unit performs abnormal data analysis on the temperature data, it includes: The acquisition unit creates a two-dimensional temperature map based on the temperature data according to the distribution position of each resistive temperature sensor in the temperature sensor array; In the two-dimensional temperature map, any temperature data is determined as the origin ( ), with the origin as the center and r as the correction radius, determine the correction range; Calculating the correction temperature according to the temperature data of each coordinate point within the correction range, when the difference between the temperature data of the origin and the correction temperature is greater than the temperature difference threshold, determining the origin as an abnormal data point, and recording the coordinates of the abnormal data point; When the abnormal data point exists in the two-dimensional temperature map, the acquisition unit determines that abnormal data exists; The corrected temperature is calculated by the following formula: in, represents the correction temperature, r represents the correction radius, (x, ) represents the coordinates of the origin, Represents a two-dimensional temperature graph Temperature data of the point.

3. The roadbed surface temperature control system for roadbed antifreeze test according to claim 1 is characterized in that: When it is determined that there is no abnormal data, the acquisition unit determines whether to start centralized cooling according to the mean value of the temperature data, including: The acquisition unit obtains a temperature data mean value of the temperature sensor array according to the temperature data, compares the temperature data mean value with a maximum temperature threshold value, and determines whether to start centralized cooling according to the comparison result; When the average value of the temperature data is less than or equal to the maximum temperature threshold, the acquisition unit determines not to start centralized cooling; when the average value of the temperature data is greater than the maximum temperature threshold, the acquisition unit determines to start centralized cooling and determines the operating power of the centralized cooling device based on the temperature data.

4. The roadbed surface temperature control system for roadbed antifreeze test according to claim 3 is characterized in that: When the acquisition unit determines the operating power of the centralized cooling device according to the temperature data, it includes: The acquisition unit obtains a temperature difference based on the temperature data mean and the maximum temperature threshold, and the temperature difference is the difference between the temperature data and the maximum temperature threshold. The operating power of the centralized cooling device is determined based on the temperature difference, and the temperature difference is proportional to the operating power of the centralized cooling device.

5. The roadbed surface temperature control system for roadbed antifreeze test according to claim 3 is characterized in that: When it is determined that there is abnormal data, the acquisition unit determines to start distributed cooling or mixed cooling according to the abnormal data and the non-abnormal data, including: The acquisition unit divides the temperature data of the abnormal data points into an abnormal temperature set, and divides the temperature data of the non-abnormal data points into a non-abnormal temperature set, obtains an abnormal temperature mean according to the abnormal temperature set, obtains a non-abnormal temperature mean according to the non-abnormal temperature set, compares the abnormal temperature mean and the non-abnormal temperature mean with the maximum temperature threshold, and determines whether to start distributed cooling or mixed cooling according to the comparison result; When the abnormal temperature average and the non-abnormal temperature average are both greater than the maximum temperature threshold, the acquisition unit determines to start mixed cooling; When the abnormal temperature average is greater than the maximum temperature threshold and the non-abnormal temperature average is less than or equal to the maximum temperature threshold, the acquisition unit determines to start distributed cooling.

6. The roadbed surface temperature control system for roadbed antifreeze test according to claim 5, characterized in that: The judgment unit processes all feature sets based on K-Means clustering to obtain clustering results, including: the environmental parameters include temperature, humidity and wind speed; When the judgment unit establishes the feature set, it includes normalizing the data in each feature set; S1: The judgment unit initializes K centroids in all the feature sets, and distributes the remaining feature sets to the nearest centroids to form K clusters; S2: Recalculate the centroid of each cluster; S3: Repeat S1 and S2 until the center of mass no longer changes; S4: when there is only one centroid, the judgment unit determines that the abnormal type of all abnormal data is unique; when there are multiple centroids, the judgment unit determines that the abnormal type of the abnormal data is not unique; The centroid calculation formula is as follows: Among them, Mk represents the centroid of the kth cluster, represents the number of feature sets in the kth cluster, and Zi represents the feature set of the i-th abnormal data.

7. The roadbed surface temperature control system for roadbed antifreeze test according to claim 6, characterized in that: When the processing unit determines the operating power of the distributed cooling device according to the judgment result of the judgment unit, it includes: When the judgment unit determines that the abnormal type of all abnormal data is unique, the processing unit compares the feature set with a historical feature set data set, wherein the historical feature set data set includes a historical feature set and a corresponding historical operating power of a historical distributed cooling device; When the same data as the feature set exists in the historical feature set data set, the processing unit uses the historical operating power as the operating power; When there is no data identical to the feature set in the historical feature set data set, the processing unit obtains the operating power according to the feature set by the following formula; Among them, P represents the operating power, Pmin represents the minimum power of the distributed cooling device, T represents the normalized result of temperature data, H represents the normalized result of humidity data, V represents the normalized result of wind speed data, T0 represents the normalized result of the maximum temperature threshold, and T0≠0.

8. The roadbed surface temperature control system for roadbed antifreeze test according to claim 7, characterized in that: When the judgment unit determines that the abnormal type of all abnormal data is not unique, the processing unit obtains the number of feature sets in each abnormal type according to the clustering result, takes the abnormal type containing the largest number of feature sets as the main type, calculates the abnormal factors of the remaining abnormal types and the main type through a similarity calculation formula, obtains the operating power at the abnormal point of the main type according to the feature set of the main type, and determines the adjustment coefficient according to the abnormal factor to adjust the operating power to obtain the operating power at the remaining abnormal types.

9. The roadbed surface temperature control system for roadbed antifreeze test according to claim 8, characterized in that: When the judgment unit determines the adjustment coefficient according to the abnormal factor to adjust the operating power to obtain the operating power at other abnormal types, it includes: The abnormal factor is compared with a preset first abnormal factor and a preset second abnormal factor respectively, and an adjustment coefficient is determined according to the comparison result to adjust the operating power to obtain the operating power at other abnormal types, wherein the first abnormal factor is less than the second abnormal factor; When the abnormal factor is less than or equal to the first abnormal factor, the first adjustment coefficient is determined to adjust the operating power; when the abnormal factor is greater than the first abnormal factor and less than or equal to the second abnormal factor, the second adjustment coefficient is determined to adjust the operating power; when the abnormal factor is greater than the second abnormal factor, the third adjustment coefficient is determined to adjust the operating power; the first adjustment coefficient is less than the second adjustment coefficient, and the second adjustment coefficient is less than the third adjustment coefficient.

10. A method for controlling the surface temperature of a roadbed for a roadbed antifreeze test, applied to the roadbed surface temperature control system for a roadbed antifreeze test as claimed in any one of claims 1 to 9, characterized in that: include: Collecting temperature data from a temperature sensor array, and performing abnormal data analysis on the temperature data; When it is determined that there is no abnormal data, whether to start centralized cooling is determined according to the mean value of the temperature data; when it is determined that there is abnormal data, whether to start distributed cooling or mixed cooling is determined according to the abnormal data and non-abnormal data, and the mixed cooling includes centralized cooling and distributed cooling; When it is determined that distributed cooling is to be performed, the environmental parameters of the abnormal location are extracted to establish a feature set, all feature sets are processed based on K-Means clustering, and whether they are the same type of anomalies is determined based on the clustering results; The operating power of the distributed cooling device is determined according to the judgment result of the judgment unit.

Images