Ai-assisted soil compaction system and methods

Abstract

System and methods for modeling, planning, and monitoring soil compaction. Laboratory test and historical data establish an historical baseline. A predictive baseline is computed from the historical baseline and a predictive site model. During the soil compaction of a calibration area, a predictive compaction model is computed from providing compaction scores obtained from standard tests, loose measurement maps and a compacted vibration map. During the soil compaction vibration data is used in conjunction with the predictive compaction to compute a compaction value. Upon detecting that the compaction value is within the target compaction threshold, an operator is notified.

Description

AI-ASSISTED SOIL COMPACTION SYSTEM AND METHODSPRIORITY STATEMENT

[0001] This patent application claims priority on US patent application No. 63 / 648,733 filed on May 17, 2024.TECHNICAL FIELD

[0002] The present invention relates to soil compaction and, more particularly, to validating a state of soil compaction.BACKGROUND

[0003] Compacting machines used in various construction and landfill operations, serve to densify materials like soil, gravel, asphalt, and refuse, facilitating the achievement of specific engineering properties and structural stability. These machines operate on the principle that the application of mechanical forces, through processes such as rolling, vibration, and kneading, alters the arrangement of particles within a material, reducing void spaces and increasing density. The effectiveness of compaction is influenced by several factors including the type of material being compacted, the moisture content within the material, and the method of compaction employed. For soils, optimal moisture content is controlled for achieving maximum density; too little or too much moisture can inhibit compaction. The goal of compaction, across various applications, is to enhance material properties such as stability, load-bearing capacity, and resistance to water infiltration.

[0004] Monitoring and achieving the desired state of compaction requires not only the repeated passage of compacting machines over the material but also the application of specific methodologies to assess the degree of compaction achieved, ensuring that it meets the necessary specifications for the intended application.SUMMARY

[0005] This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the Detailed Description. This Summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used as an aid in determining the scope of the claimed subject matter.

[0006] In a first aspect, the technique described herein relates to a method for modeling a compaction site. From a sampling area of the compaction site comprising a subgrade and being filled with a fill material, soil samples comprising a subgrade sample may be collected from the subgrade. A laboratory test may be conducted on the soil samples to determine soil properties. A predicted baseline may be predicted from the soil properties and a predictive site model.

[0007] In embodiments, a historical baseline, descriptive of an anticipated vibration data response, may be established by comparing the soil properties against historical data. The predicted baseline may be predicted from the soil properties, the predictive site model, and the historical baseline.

[0008] In embodiments, the soil samples may further comprise a fill sample from the fill material.

[0009] In embodiments, a soil quantity, a compaction method, and a project scheduling may be identified.The soil samples may be collected in accordance with a sampling frequency and a sampling procedure based on the soil quantity, the compaction method, and the project scheduling.

[0010] In embodiments, the soil properties may comprise at least one of a gradation, a moisture, and an Atterberg limit.

[0011] In embodiments, the predictive site model may be configured from machine learning methods. The machine learning methods may include at least one of supervised learning, unsupervised learning, reinforcement learning, deep learning, a neural network, support vector machines, and k-nearest neighbors.

[0012] In embodiments, the predicted baseline may comprise an expected pass count.

[0013] In a second aspect, the technique described herein relates to a method for planning a soil compaction of a compaction site. A calibration area of the compaction site and a compaction target may be established. Sitespecific compaction parameters 19 may be established based on the compaction site. During a calibrating soil compaction of the calibration area using a compaction equipment equipped with measurement sensors, a loose measurement map indicative of a loose soil measurement at a plurality of calibration locations of the calibration area may be recorded. A compaction score of the calibration area may be measured by conducting one or more standard tests. Upon determination that the compaction score is within the compaction target, a compacted measurement map indicative of a compacted soil measurement at the plurality of calibration locations of the calibration area may be recorded. A predictive compaction model may be computed from the loose measurement map, the compacted measurement map, and the one or more standard tests, and may be configured to predict a predicted compaction score from a measurement.

[0014] In embodiments, the measurement sensors may comprise at least one of a vibration sensor, location sensor, a moisture sensor, an infra-red sensor, a barometer sensor, a magnetometer sensor, a gyroscope sensor, and a camera sensor. The loose soil measurement may comprise at least one of vibration measurement, a location measurement, a moisture measurement, a temperature measurement, a barometer measurement, a magnetometer measurement, a gyroscope measurement, and a camera measurement.

[0015] In embodiments, the one or more standard tests may comprise at least one of a Proctor compaction test, a moisture content test, a field density test, a sand cone test, a plate load test, and a lightweight deflectometer test.

[0016] In embodiments, the compaction equipment may comprise at least one of a compactor roller and a plate-tamper compactor.

[0017] In embodiments, the site-specific compaction parameters may comprise at least one of a lift thickness, a control strip size, and a moisture content.

[0018] In embodiments, the predictive compaction model may be obtained from a machine learning method. Optionally, the machine learning method may comprise at least one of supervised learning, unsupervised learning, reinforcement learning, deep learning, a neural network, support vector machines, and k-nearest neighbors.

[0019] In a third aspect, the technique described herein relates to a method for monitoring a soil compaction of a compaction site. During the soil compaction, compaction equipment equipped with measurement sensors may be used. A monitoring measurement may be collected at a monitoring location of the compaction equipment within the compaction site. A compaction value may be computed from the monitoring measurement using a scoring model. A target compaction threshold may be computed from the monitoring measurement using a target baseline. Upon detecting that the compaction value is within the target compaction threshold, a user may be notified of a soil compaction achievement at the monitoring location. Optionally, the user may be an operator of the compaction equipment, an on-site foreman, a geotechnical technician, or a geotechnical engineer.

[0020] In embodiments, the scoring model may be the predictive compaction model from the method of the second aspect described herein.

[0021] In embodiments, the target baseline may be the predicted baseline from the method of the first aspect described herein.

[0022] In embodiments, the target baseline may be computed by comparing the compaction value to an average stiffness within the compaction site.

[0023] In embodiments, upon detecting that the compaction value is outside of the target compaction threshold, the user may be notified of further remedial steps required at the monitoring location.

[0024] In embodiments, the measurement sensors may comprise at least one of a vibration sensor, a location sensor, a moisture sensor, an infra-red sensor, a barometer sensor, a magnetometer sensor, a gyroscope sensor, and a camera sensor. The monitoring measurement may comprise at least one of a vibration measurement, a location measurement, a moisture measurement, a temperature measurement, a barometer measurement, a magnetometer measurement, a gyroscope measurement, and a camera measurement.

[0025] In embodiments, the compaction value may be averaged over an averaging distance. Optionally, the averaging distance may be 1 meter. Optionally, the averaging distance may be configured according to at least one of a soil properties, a roller dimension, and a site characteristic.

[0026] In embodiments, the compaction value may be recorded into a compaction value map. Upon completing the soil compaction, the compaction value map may be communicated to an approving engineer.

[0027] In embodiments, communicating the compaction value map may comprise identifying areas on the compaction value map according to geotechnical rules. Optionally, the geotechnical rules may be evaluated using a geotechnical rule model trained with machine learning. Optionally, the geotechnical rules may include at least one of the following: areas with the compaction value below an acceptable threshold may be identified using an unacceptable identification scheme; areas with the compaction value between the acceptable threshold and an idealthreshold may be identified using an acceptable identification scheme; areas with the compaction value above the ideal threshold may be identified using an ideal identification scheme; under-passed areas may be identified using an under-passed identification scheme; and areas with an anomaly may be identified using an anomaly identification scheme. Optionally, communicating the compaction value map may include identifying improving areas using an improving identification scheme, wherein the improving areas may be identified based on a difference between the compaction value and the compaction value of the previous iteration. Optionally, completed areas may be identified using a completed identification scheme, where the completed areas may be identified based on an expected number of passes being completed, a low difference between the compaction value and the compaction value of the previous iteration, and the compaction value being above an ideal threshold. Optionally, the geotechnical rules may include evaluating a lift thickness.

[0028] In embodiments, the method may further include isolating a subgrade vibration influence from the monitoring measurement, thereby improving the compaction value of a fill material. Optionally, the subgrade vibration influence may be estimated from a calibration area.

[0029] In embodiments, communicating the compaction value map may further comprise at least one of the following: potential non-homogeneous areas may be identified using a potential non-homogeneous area identification scheme; potential moisture variation area may be identified using a moisture variation identification scheme; and potential weak spot areas may be identified using a potential weak spot identification scheme.

[0030] In embodiments, remote compaction data may be received from a second compaction equipment, thereby enabling a collaborative soil compaction on a plurality of subareas of the compaction site. Optionally, the plurality of subareas may be assigned to the compaction equipment based on at least one of a current location of the compaction equipment, the remote compaction data, the target compaction threshold, the target baseline, a scheduling constraint, a refueling need, a maintenance need, an observed compaction rate, an availability of equipment, and a planned activity on the plurality of subareas.

[0031] In a fourth aspect, the technique described herein relates to a system for monitoring a soil compaction of a compaction site. The system may comprise a compaction equipment, a compactor communication module, a user interface module, a compaction modeling module and a processor module. The compaction equipment may include one or more measurement sensors to collect monitoring measurements at a monitoring location of the compaction equipment within the compaction site. The compactor communication module may transmit the monitoring measurements and receive a compaction assessment. The user interface module may notify a user of the compaction assessment. The compaction modeling module may include a network interface module, a storage system and a processor module. The network interface module may receive the monitoring measurements from the compactor communication module and transmit the compaction assessment to the compactor communication module. The storage system may store a scoring model and store a target baseline. The processor module may compute a compaction value from the monitoring measurements using the scoring model. The processor module may also compute a target compaction threshold from the monitoring measurements using the target baseline. Theprocessor module may also compute the compaction assessment from the compaction value and the target compaction threshold.

[0032] In embodiments, the scoring model may be the predictive compaction model from the method of the second aspect described herein.

[0033] In embodiments, the target baseline may be the predicted baseline from the method of the first aspect described herein.

[0034] In embodiments, the target baseline may be computed by comparing the compaction value to an average stiffness within the compaction site.

[0035] In embodiments, measurement sensors may include at least one of a vibration sensor, a location sensor, a moisture sensor, an infra-red sensor, a barometer sensor, a magnetometer sensor, a gyroscope sensor, and a camera sensor. The monitoring measurements may include at least one of a vibration measurement, a location measurement, a moisture measurement, a temperature measurement, a barometer measurement, a magnetometer measurement, a gyroscope measurement, and a camera measurement.

[0036] In embodiments, the processor module may be configured to compute an average compaction value from a plurality of discrete compaction values over an averaging distance. The compaction assessment may be computed from the average compaction value. Optionally, the averaging distance may be 1 meter. Optionally, the averaging distance may be configured according to at least one of soil properties, an equipment dimension, and site characteristics.

[0037] In embodiments, the processor module may be further configured to compute the compaction value into a compaction value map, and the network interface module may be further configured to communicate the compaction value map to an approving engineer.

[0038] In embodiments, the processor module may be further configured to identify areas on the compaction value map according to geotechnical rules. Optionally, the geotechnical rules may be evaluated using a geotechnical rule model trained with machine learning. Optionally, the geotechnical rules may comprise at least one of the following: areas with the compaction value below an acceptable threshold may be identified using an unacceptable identification scheme; areas with the compaction value between the acceptable threshold and an ideal threshold may be identified using an acceptable identification scheme; areas with the compaction value above the ideal threshold may be identified using an ideal identification scheme; under-passed areas may be identified using an under-passed identification scheme; and areas with an anomaly may be identified using an anomaly identification scheme. Optionally, the processor module of the system may be configured to identify areas on the compaction value map according to the geotechnical rules after a previous iteration. Communicating the compaction value map may comprise identifying improving areas using an improving identification scheme, wherein the improving areas may be identified based on a difference between the compaction value and the compaction value of the previous iteration. Completed areas may be identified by using a completed identification scheme, wherein the completed areas may be identified based on an expected number of passes being completed, a low difference between thecompaction value and the compaction value of the previous iteration, and the compaction value being above an ideal threshold. Optionally, the geotechnical rules may comprise evaluating a lift thickness.

[0039] In embodiments, the processor module may be further configured to isolate a vibration influence from a subgrade, thereby improving vibration measurement of a fill material.

[0040] In embodiments, the network interface module may further be configured to relay a remote compaction data from a second compaction equipment, thereby enabling a collaborative soil compaction.

[0041] In a fifth aspect, the technique described herein relates to a non-transitory computer-readable medium storing a set of instructions for modeling a compaction site. When executed by one or more processors of a device, a predicted baseline may be predicted from a predictive site model and soil properties of a sampling area of the compaction site. The soil properties may be determined from soil samples comprising a subgrade sample from a subgrade of the compaction site.

[0042] In embodiments, the non-transitory computer-readable medium may include instructions which, when predicting the predicted baseline, further cause the device to establish a historical baseline. The historical baseline may be descriptive of an anticipated vibration data response and may be established by comparing the soil properties against historical data. The predicted baseline may be predicted from the soil properties, the predictive site model, and the historical baseline.

[0043] In embodiments, the compaction site may be filled with a fill material, and the soil samples may further comprise a fill sample from the fill material.

[0044] In embodiments, the non-transitory computer-readable medium may include instructions to identify a soil quantity, a compaction method, and a project scheduling. The soil samples may be collected in accordance with a sampling frequency and a sampling procedure based on the soil quantity, the compaction method, and the project scheduling.

[0045] In embodiments, the soil properties may comprise at least one of a gradation, a moisture, and an Atterberg limit.

[0046] In embodiments, the predictive site model may be configured from machine learning methods. The machine learning methods may include at least one of a supervised learning method, an unsupervised learning method, a reinforcement learning method, a deep learning method, a neural network, support vector machines, and k-nearest neighbors.

[0047] In embodiments, the predicted baseline may comprise an expected pass count.

[0048] In a sixth aspect, the technique described herein relates to a non-transitory computer-readable medium storing a set of instructions for planning a soil compaction of a compaction site. When executed by one or more processors of a device, site-specific compaction parameters may be recorded based on the compaction site. A loose measurement map, indicative of a loose soil measurement at a plurality of calibration locations of a calibration area, may be recorded. A compaction score of the calibration area may be measured from the results ofone or more standard tests. Upon determining that the compaction score is within the compaction target, a compacted measurement map indicative of a compacted soil measurement at the plurality of calibration locations of the calibration area may be recorded. A predictive compaction model may be computed from the loose measurement map, the compacted measurement map, and the one or more standard tests, to predict a predicted compaction score from a measurement.

[0049] In embodiments, the loose soil measurement may comprise at least one of the following: vibration measurement, location measurement, moisture measurement, temperature measurement, barometer measurement, magnetometer measurement, gyroscope measurement, and camera measurement.

[0050] In embodiments, the one or more standard tests may comprise at least one of a Proctor compaction test, a moisture content test, a field density test, a sand cone test, a plate load test, and a lightweight deflectometer test.

[0051] In embodiments, the site-specific compaction parameters may comprise at least one of a lift thickness, a control strip size, and a moisture content.

[0052] In embodiments, the predictive compaction model may be obtained from a machine learning method. Optionally, the machine learning method may comprise at least one of a supervised learning method, an unsupervised learning method, a reinforcement learning method, a deep learning, a neural network, support vector machines, and k-nearest neighbors.

[0053] In a seventh aspect, the technique described herein relates to a non-transitory computer-readable medium storing a set of instructions for monitoring a soil compaction of a compaction site during the soil compaction, using a compaction equipment equipped with measurement sensors. When executed by one or more processors of a device, a monitoring measurement may be collected at a monitoring location of the compaction equipment within the compaction site. A compaction value may be computed from the monitoring measurement using a scoring model. A target compaction threshold may be computed from the monitoring measurement using a target baseline. Upon detecting that the compaction value is within the target compaction threshold, a user may be notified of a soil compaction achievement at the monitoring location. Optionally, the user may be an operator of the compaction equipment, an on-site foreman, a geotechnical technician, or a geotechnical engineer.

[0054] In embodiments, the scoring model may be the predictive compaction model from the non-transitory computer-readable medium of the sixth aspect.

[0055] In embodiments, the target baseline may be the predicted baseline from the non-transitory computer- readable medium of the fifth aspect.

[0056] In embodiments, the target baseline may be computed by comparing the compaction value to an average stiffness within the compaction site.

[0057] In embodiments, upon detecting that the compaction value is outside of the target compaction threshold, the user may be notified of further remedial steps required at the monitoring location.

[0058] In embodiments, the monitoring measurement may comprise at least one of the following: a vibration measurement, a location measurement, a moisture measurement, a temperature measurement, a barometer measurement, a magnetometer measurement, a gyroscope measurement, and a camera measurement.

[0059] In embodiments, the compaction value may be averaged over an averaging distance. Optionally, the averaging distance may be 1 meter. Optionally, the averaging distance may be configured according to at least one of a soil properties, a roller dimension, and a site characteristic.

[0060] In embodiments, the non-transitory computer-readable medium may include instructions that further cause the device to record the compaction value into a compaction value map. Upon completion of the soil compaction, the compaction value map may be communicated to an approving engineer.

[0061] In embodiments, when communicating the compaction value map, the one or more instructions may cause the device to identify areas on the compaction value map according to geotechnical rules. Optionally, the geotechnical rules may be evaluated using a geotechnical rule model trained with machine learning. Optionally, the geotechnical rules may comprise at least one of the following: areas with the compaction value below an acceptable threshold may be identified using an unacceptable identification scheme; areas with the compaction value between the acceptable threshold and an ideal threshold may be identified using an acceptable identification scheme; areas with the compaction value above the ideal threshold may be identified using an ideal identification scheme; underpassed areas may be identified using an under-passed identification scheme; and areas with an anomaly may be identified using an anomaly identification scheme. Optionally, the one or more instructions may further cause the device to, when communicating the compaction value map after a previous iteration, identify improving areas using an improving identification scheme. The improving areas may be identified based on a difference between the compaction value and the compaction value of the previous iteration. Completed areas may be identified by using a completed identification scheme. The completed areas may be identified based on an expected number of passes being completed, a low difference between the compaction value and the compaction value of the previous iteration, and the compaction value being above an ideal threshold. Optionally, the geotechnical rules may comprise evaluating a lift thickness.

[0062] In embodiments, the non-transitory computer-readable medium may include instructions to isolate a subgrade vibration influence from the monitoring measurement, thereby improving the compaction value of a fill material. Optionally, the subgrade vibration influence may be estimated from a calibration area.

[0063] In embodiments, when communicating the compaction value map, potential non-homogeneous areas may be identified using a potential non-homogeneous area identification scheme. Potential moisture variation areas may be identified using a moisture variation identification scheme. Potential weak spot areas may be identified using a potential weak spot identification scheme.

[0064] In embodiments, the one or more instructions may further cause the device to receive a remote compaction data from a second compaction equipment, thereby enabling a collaborative soil compaction on a plurality of subareas of the compaction site. Optionally, the plurality of subareas may be assigned to the compactionequipment based on at least one of a current location of the compaction equipment, the remote compaction data, the target compaction threshold, the target baseline, a scheduling constraint, a refueling need, a maintenance need, an observed compaction rate, an availability of equipment, and a planned activity on the plurality of subareas.BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Further features and exemplary advantages of the present invention will become apparent from the following detailed description, taken in conjunction with the appended drawings, in which:

[0066] Figure 1 is a side view of an exemplary compactor roller in accordance with an embodiment of the present invention;

[0067] Figure 2 is an activity diagram depicting an exemplary embodiment of a method for modeling a compaction site in accordance with the teachings of the present invention;

[0068] Figure 3 is a block diagram depicting an exemplary embodiment of a system for modeling a compaction site in accordance with the teachings of the present invention;

[0069] Figure 4 is an activity diagram depicting an exemplary embodiment of a method for planning a soil compaction in accordance with the teachings of the present invention;

[0070] Figure 5 is a block diagram depicting an exemplary embodiment of a system for planning a soil compaction in accordance with the teachings of the present invention;

[0071] Figure 6 is a block diagram depicting an exemplary compactor equipment for planning a soil compaction in accordance with the teachings of the present invention;

[0072] Figure 7 is an activity diagram depicting an exemplary embodiment of a method for monitoring a soil compaction in accordance with the teachings of the present invention;

[0073] Figure 8 is a block diagram depicting an exemplary embodiment of a system for monitoring a soil compaction in accordance with the teachings of the present invention;

[0074] Figure 9 is a block diagram depicting an exemplary compactor equipment for monitoring a soil compaction in accordance with the teachings of the present invention;

[0075] Figure 10 is a modular representation of a system for monitoring a soil compaction in accordance with the teachings of the present invention; and

[0076] Figure 11 is a modular representation of a compaction modeling module in accordance with the teachings of the present invention.DETAILED DESCRIPTION OF PREFERRED EMBODIMENTS

[0077] Traditional soil compaction methods may rely on manual oversight and empirical rules to achieve desired compaction levels. The repeated passage of compacting machines over the material may be involved, wherewith the effectiveness of compaction may be influenced by factors such as the type of material beingcompacted, the moisture content within the material, and the method of compaction employed. However, these traditional approaches may result in a variety of outcomes according to site conditions and the difficulty in accurately assessing the degree of compaction achieved in real-time. The lack of precision in traditional methods may lead to either under-compaction, resulting in unstable and unsafe structures, or over-compaction, leading to unnecessary labor and resource expenditure. Relying on the judgment of the operator and control technician may yield unreliable, non-repeatable, or unpredictable results depending on their experience.

[0078] In the present disclosure, a compaction site refers to any area where soil, gravel, asphalt, or refuse is being compacted to achieve specific engineering properties and structural stability. Compaction sites may demonstrate variability in characteristics and requirements, such as construction sites, landfill operations, mining operations, and agricultural fields. Soil compaction may enhance stability and load-bearing capacity by increasing soil density through the reduction of air volume within the soil matrix. Compaction equipment 100, such as compactor rollers, may be used to achieve soil compaction, applying pressure and vibration specifically for this purpose. Typically, soil compaction may extend to depths of 30 cm to 1 meter below the surface, depending on the equipment used and the specific requirements of a project.

[0079] Compaction equipment 100 may comprise various types of compacting devices suitable for distinct compaction tasks and environments. For instance, a plate-tamper compactor may be employed to compact soil, gravel, or asphalt in areas that are confined and not easily accessible to a roller. Characterized by a base plate, a plate-tamper compactor may transfer vibrations into the ground, facilitating compaction through rapid impacts. Platetamper compactors may be effective in achieving high density in areas with limited maneuvering space. Different compacting equipment types may be chosen based on factors such as soil type, layer thickness, compaction targets, and specific project requirements. The methods and systems described may be adapted to other similar compacting equipment.

[0080] The use of artificial intelligence, including machine learning, may improve soil compaction methods by enabling the prediction, planning, and monitoring of compaction activities. Historical data 46 may be utilized to train a site model, wherewith characteristics of a new site may be predicted and a predicted baseline may be generated. Machine learning may also be employed in conjunction with data collected from a site area used for calibration to predict compaction of future areas of the site in real-time.

[0081] A first aspect of the teachings presented herein relates to a method for modeling a compaction site. Reference is now made to the drawings in which Figure 1 depicts a side view of an exemplary compactor equipment 100, Figure 2 depicts an activity diagram depicting an exemplary embodiment of a method 200 for modeling a compaction site, and Figure 3 depicts a block diagram of an exemplary embodiment of a system for modeling a compaction site in accordance with the teachings of the present invention.

[0082] From a sampling area 12 of the compaction site 10 comprising a subgrade 20 and being filled with a fill material 30, soil samples 40 comprising a subgrade sample 22 may be collected 220 from the subgrade 20.

[0083] A sampling area 12 may be defined as a specific section of a compaction site 10 from which soil samples 40 may be collected. The sampling area 12 may encompass components including a subgrade 20 and fill material 30. In the context of soil compaction, the sampling area 12 may function as a representative segment that facilitates the collection of soil samples 40, including a subgrade sample 22 from the subgrade 20.

[0084] The subgrade 20 may be identified as an underlying layer of soil situated beneath a surface layer or a fill material 30 at a compaction site 10. The subgrade 20 may serve as a foundation supporting materials above, including the fill material 30. Characteristics of the subgrade 20, such as strength, density, and moisture content, may influence the performance of a structure supported by the subgrade 20. The subgrade 20 may be composed of native soil, which may include naturally occurring clay, sandy soil, or a combination of different soil types present at the compaction site 10.

[0085] A fill material 30 may be identified as the material placed atop a subgrade 20 to adjust the elevation or grading of a construction surface. The fill material 30 may be used to raise areas, provide structural support, or prepare the site for future construction activities. Examples of the fill material 30 may include gravel, sand, crushed stone, or recycled materials such as crushed concrete or bricks. Proper compaction of the fill material 30 may be required to ensure stability and strength of the final structure.

[0086] Soil samples 40, including a subgrade sample 22, may be collected 220 by employing various sampling techniques from the subgrade 20 of the compaction site 10. Collecting these samples may support the analysis and determination of the soil properties 44 of the subgrade material, which may influence the compaction process and stability of the foundations of the project. To collect soil samples 40 from the subgrade 20, a range of methods may be employed based on site conditions and the required analysis. For example, a hand auger may be used. A hand auger may be a simple tool that allows boring into the ground to extract soil material. The collected subgrade sample 22 may be utilized for a laboratory test 42 to determine soil properties 44 such as gradation, moisture content, and Atterberg limits.

[0087] A mechanical auger may be used for soil sample collection 220, as it is motorized and capable of deep penetration into the subgrade 20. The mechanical auger may be preferred if the subgrade 20 is particularly deep or if a larger volume of sample is necessary for comprehensive analysis. In instances where undisturbed samples are required, a Shelby tube may be used. The Shelby tube, a long, cylindrical, thin-walled metal tube, may be driven into the ground to extract a core sample of subgrade 20 soil, thereby maintaining the integrity of the sample and allowing for accurate analysis of soil properties 44 such as density and moisture content in its natural state. A backhoe or an excavator may also be employed to dig a test pit for collecting soil samples 40 from the subgrade 20. The test pit may allow for direct visual inspection and manual collection of samples from various depths within the subgrade 20, being beneficial for examining the layering and composition of the soil, as well as for obtaining larger samples for testing. The choice of sampling method may be determined by factors including the depth of the subgrade 20, the nature of the soil, the equipment available, and the specific requirements of the analysis to be conducted. Insights provided by each method into the characteristics of the subgrade 20 may inform the predicted baseline 50 and aid in the construction planning process.

[0088] The soil samples 40 may comprise a fill sample 32 from the fill material 30. The fill sample 32 within the soil samples 40 may reveal characteristics and behaviors of the fill material 30 and may inform compaction processes, potentially ensuring that the material may fulfill structural requirements. The analysis of the fill sample 32 may aid in determining soil properties 44 such as gradation, moisture content, and density of the material.

[0089] A laboratory test 42 may be conducted 230 on soil samples 40 to determine soil properties 44 such as gradation, moisture content, and Atterberg limits. Gradation, which may be indicative of particle size distribution, may be determined utilizing methods such as sieve analysis for coarser particles and hydrometer analysis for finer particles. Gradation may influence soil density, permeability, and compaction characteristics, thereby guiding the selection of appropriate compaction equipment 100 and methods. Moisture content may be determined using tests such as the oven-dry method, wherewith the density of the soil and strength may be affected. Optimal moisture content may be identified as the level at which maximum density under compaction effort is achieved. The Atterberg limits, comprising the shrinkage limit, plastic limit, and liquid limit, may define the boundaries between different states of consistency in fine-grained soils. Methods such as the Casagrande Cup method and rolling thread method may be used to determine the Atterberg limits, assisting in understanding the behavior of soil when water content changes, which may inform predictions of performance under compaction and over time.

[0090] A predicted baseline 50 may be predicted 250 from soil properties 44 and a predictive site model 80. The predicted baseline 50 may serve as a reference for anticipated performance metrics in soil compaction, functioning as a benchmark for comparing actual compaction results and encompassing components such as site characteristics, the type of soil, and historical data 46 related to similar compaction sites. The predicted baseline 50 may be expressed as a numerical value, such as a target soil density or modulus of elasticity, indicating desired stiffness and compactness. The predictive site model 80 may be designed to simulate or forecast soil compaction outcomes using input parameters such as soil properties 44 and environmental conditions, operating utilizing machine learning techniques or statistical algorithms trained on historical data 46 from previous compaction projects. Methods such as supervised learning, unsupervised learning, and reinforcement learning may be employed, wherein the predictive site model 80 may recognize patterns and relationships between variables affecting soil compaction. The predictive site model 80 may incorporate factors such as soil gradation, moisture content, and Atterberg limits, or other relevant soil properties 44 obtained through laboratory test 42, analyzing these properties alongside additional data, including the subgrade 20 type, fill material 30 used, machinery specifications, compaction methods applied, and site-specific constraints.

[0091] A soil quantity, a compaction method, and a project scheduling may be identified 210 from an area of the compaction site 10 comprising a subgrade 20 and being filled with a fill material 30. The soil quantity may refer to the volume or amount of soil that may be compacted in a specific area of the compaction site 10. Determination of the soil quantity may involve calculations based on the dimensions of the site and the desired density after compaction. A compaction method may refer to the specific technique or machinery that may be used to achieve the desired soil compaction. Various compaction methods may be suitable for different soil types and project requirements; examples may include rolling by using smooth-drum or sheepsfoot rollers, vibration by using vibratingplate compactors or rollers, kneading, or a combination thereof. The choice of compaction method may depend on factors such as the type of soil, moisture content, depth of the layer lift thickness being compacted, and the required compaction density. Project scheduling, in the context of soil compaction, may involve planning the sequence and timing of compaction activities. The determination of when and how the compaction work may be performed, the coordination of availability of machinery and personnel, the setting of milestones for different phases of the project such as completing the compaction of specific sections, and the alignment of the project timeline with overall construction or landfill operation schedules may be conducted.

[0092] Soil samples 40 may be collected in accordance with a sampling frequency and a sampling procedure based on a soil quantity, a compaction method, and a project scheduling. The soil samples 40 may include material from either a subgrade 20 or a fill material 30. The subgrade 20 may function as the foundation for the fill material 30 and any constructed structure or compacted area, wherewith sampling of the subgrade 20 may provide insights into characteristics such as stability, moisture content, and load-bearing capacity. The fill material 30 may refer to soil or other materials added to a site to elevate ground level, adjust soil composition, or achieve desired compaction characteristics. Determining a sampling frequency may involve factors such as a size of the compaction site 10, variability of soil properties 44 across the site, and project or regulatory standards. A sampling procedure may specify methods for collecting soil samples 40 to ensure reliability and representation. Guidelines may indicate where soil samples 40 may be collected, a depth for collection, methods of handling and transportation to prevent contamination or alteration, and documentation of the sampling process. Implementing a standard procedure for collecting soil samples 40 may enhance method performance by generating input data in closer alignment with conditions of training data utilized during machine learning.

[0093] In embodiments, a historical baseline 52, descriptive of an anticipated vibration data response, may be established 240 by comparing the soil properties 44 against historical data 46. Historical data 46 may encompass records from past soil compaction projects, including soil properties 44, compaction methods, equipment involved, and vibration data observed during those projects. The process of comparing current soil properties 44 with historical data 46 may identify patterns, similarities, or differences between soil characteristics of current and past projects. By performing this comparison, reference points may be established within the historical baseline 52 for anticipated vibration responses under similar conditions encountered in previous projects.

[0094] The predicted baseline 50 may be predicted 250 from the soil properties 44, the predictive site model 80, and the historical baseline 52. The predicted baseline 50 may be generated using various modeling techniques, including traditional linear or non-linear models. Machine learning approaches may also be used to generate the predictive site model 80. Supervised learning may train an algorithm using a labeled dataset, whereby the resulting model may predict soil compaction outcomes based on known soil properties 44 and compaction results. In unsupervised learning, the model may be trained without labeled responses, enabling the algorithm to identify patterns and relationships within the dataset and discovering hidden patterns in soil properties 44 or compaction data. Reinforcement learning may involve training a model based on feedback from performance in a changing environment, using a trial-and-error approach to receive rewards or penalties, thereby refining a modelcreated by another method. Deep learning involving neural networks with multiple layers (deep neural networks) may model complex patterns in large datasets, providing advantages in analyzing large, complex, and highdimensional data typical of compaction sites 10. Support vector machines, k-nearest neighbors, or combinations of multiple approaches may also be used to compute a predictive site model 80 from a training dataset.

[0095] The predicted baseline 50 may comprise an expected pass count. Different baselines may yield varying pass counts based on predicted soil characteristics derived from soil properties 44 and the predictive site model 80. A baseline informed by historical data 46 may reflect past experiences with similar soil types and conditions, influencing the predicted number of passes required for optimal compaction. The generation of the predictive site model 80 using machine learning methods, such as supervised learning or deep learning, may contribute to distinct predicted pass counts. Variability in soil properties 44, including gradation, moisture content, and Atterberg limits, may affect the predicted baseline 50, leading to differing expected pass counts across different sections of the compaction site 10.

[0096] In embodiments, soil properties 44 may be compared with historical data 46 wherewith a historical baseline 52 descriptive of an anticipated vibration data response may be established 240. Patterns, similarities, or differences between the current soil properties 44 and soil properties 44 from past projects may be identified through this comparison. Historical data 46 may pertain to collected data and records from past soil compaction projects, encompassing information about soil properties 44 such as gradation, moisture content, and Atterberg limits, along with the compaction methods deployed, equipment used, and vibration data observed during those compaction efforts. By comparing current soil properties 44 with historical data 46, a historical baseline 52 may be established as a set of reference points for anticipated vibration responses when comparable soil types are compacted using similar methods and equipment. The vibration data response may pertain to patterns of vibration generated by compaction equipment 100, such as a roller, and how the vibrations influence the soil. Different soils may exhibit varying responses to vibration, impacting the compaction outcome. By establishing 240 a historical baseline 52 of anticipated vibration responses through the comparison of current soil properties 44 with historical data 46, past experiences may be used to inform the prediction and optimization of current compaction projects.

[0097] A second aspect of the teachings presented herein relates to a method 300 for planning a soil compaction of a compaction site 10. Reference is now made to the drawings in which Figure 4 depicts an activity diagram of an exemplary method 300 for planning a soil compaction, Figure 5 depicts a block diagram of an exemplary system for planning a soil compaction, and Figure 6 depicts a block diagram of an exemplary compactor equipment for planning a soil compaction in accordance with the teachings of the present invention.

[0098] A calibration area 14 of the compaction site 10 and a compaction target 16 may be established 310. The establishment of a calibration area 14 may involve selecting a part of the compaction site 10 that may be representative of a broader expanse concerning soil type, moisture content, and additional pertinent characteristics. The calibration area 14 may function as a reference for regulating the compaction process wherewith compaction across the entire compaction site 10 may align with specified targets. Furthermore, the calibration area 14 maycontribute input beneficial for configuring a predictive compaction model 82 that may be utilized to predict compaction on different sections of the compaction site 10.

[0099] Site-specific compaction parameters 19 may be established 320 based on the site characteristics 18 of the compaction site 10. The site-specific compaction parameters 19 may include at least one of a lift thickness, a control strip size, and a moisture content. The site-specific compaction parameters 19 may serve to direct the compaction process to support the attainment of target soil properties 44 and project goals. The lift thickness may denote the height of the soil layer to be compacted with a single pass of the compaction equipment 100. The ideal lift thickness may differ according to the soil type, the compaction equipment 100 employed, and the desired compactness level. An improper lift thickness may result in insufficient compaction of the bottom layer or inefficient utilization of time. The control strip size may specify the dimensions or area of a segment within the calibration area 14 where site-specific compaction parameters 19 may be evaluated and optimized. The control strip may function as a test zone where the efficacy of the compaction process, using the selected lift thickness and moisture content, may be evaluated. The selection of the control strip size may aim to reflect the broader compaction site 10 while remaining feasible for efficient testing and adjustment of compaction techniques. The moisture content may influence the compaction characteristics of the soil, facilitating pliability and ease of compaction to the desired density. Establishing the moisture content may require determining the quantity of water needed by the soil to reach or approach its optimal compaction condition and may involve tests, for example, the Proctor compaction test.

[0100] A loose measurement map 90 indicative of a loose soil measurement 160 at a plurality of calibration locations 164 of the calibration area 14 may be recorded 330 during calibrating soil compaction of the calibration area 14 using a compaction equipment 100 equipped with measurement sensors 150.

[0101] The measurement sensors 150 may include a vibration sensor 151 , a location sensor 152, a moisture sensor 153, an infra-red sensor 154, a barometer sensor 155, a magnetometer sensor 156, a gyroscope sensor 157, and / or a camera sensor 158. The loose soil measurement 160 may involve a vibration measurement 141, a location measurement 142, a moisture measurement 143, a temperature measurement 144, a barometer measurement 145, a magnetometer measurement 146, a gyroscope measurement 147, and / or a camera measurement 148.

[0102] For example, the compaction equipment 100 may be equipped with a vibration sensor 151 , a location sensor 152, and a moisture / temperature sensor 153. A vibration sensor 151 may be employed to measure the vibration levels generated by the roller during soil compaction. During the compaction process, vibration levels of the soil may be recorded prior to reaching full compaction, thereby acquiring data indicative of a "loose" state. When this data is combined with precise location information from the location sensor 152, it may be used to record 330 a loose measurement map 90. The loose measurement map 90 may visually represent the initial compaction state of the soil across various parts of the calibration area 14, illustrating varying density and compaction effectiveness. Documenting vibration levels at multiple distinct locations within the calibration area 14 may be included in the recording 330 process.

[0103] A location sensor 152, for example, a global positioning system (GPS) or similar positioning system, may be used to track the precise location of the compaction equipment 100 as the equipment moves across the calibration area 14. The use of the location sensor 152 may enable the accurate mapping of data collected by the vibration sensor 151 to specific locations within the calibration area 14.

[0104] A moisture sensor 153 may provide real-time measurements of soil moisture level and temperature. The soil moisture may influence the density and stability of compacted material. A temperature measurement 144 may affect the strength, stiffness, and density of compacted soil. The moisture measurement 143 and / or temperature measurement 144 samples may be recorded 330 to complement the vibration measurement 141 of soil.

[0105] In one embodiment, a geotechnical rules engine may be used to infer moisture content instead of, or in addition to, using a moisture sensor. Vibration readings may be used to infer moisture content from soil by using historical data and machine learning techniques. Models may be trained on historical compaction projects, where moisture data is available, to predict moisture content from the vibration readings.

[0106] An infra-red sensor 154 may be used to measure thermal emissions from the soil surface, to provide an indirect assessment of soil temperature. Temperature variations across the compaction site 10 that may impact soil properties 44 and compaction quality may thus be identified.

[0107] A barometer sensor 155 may be used to monitor variations in elevation at different locations within the compaction site 10. By measuring atmospheric pressure and referencing it against standard atmospheric pressure at sea level, the barometer sensor 155 may facilitate elevation estimation. As atmospheric pressure generally decreases with elevation gain, the data provided by the barometer sensor 155 may enable the identification of subtle elevation changes within the site. Measurement of atmospheric pressure may aid in determining the need for additional fill material at specific locations without surpassing maximum elevation thresholds established for the site. Monitoring variations in elevation may support management of compaction processes and adherence to elevation limits relevant to project specifications and regulatory compliance.

[0108] In one embodiment, a magnetometer sensor 156 may be used to identify and measure the orientation of the compaction equipment 100 relative to the magnetic field of the Earth. Detection of the magnetic fields may assist in determining directional alignment of the compaction equipment 100, thereby facilitating a consistent application of compaction forces by the compaction equipment 100.

[0109] The vertical and lateral orientation of the compaction equipment 100 may be measured using a gyroscope sensor 157. Measuring the vertical orientation may provide insights into the stability and movement of the compaction equipment 100 during operation, as well as assessing the slopes of the compaction site 10.

[0110] In embodiments, a camera sensor 158 may be employed to capture visual data of a compaction site 10. The visual data captured by the camera sensor 158 may be processed to detect surface cracks, soil displacement, or other irregularities during the compaction process. The visual data may assist in the real-timeadjustment of compaction strategies and may support site assessment and documentation for further analysis and reporting.

[0111] The system may integrate measurement sensors, including at least one of a vibration sensor, a location sensor, a moisture sensor, an infra-red sensor, a barometer sensor, a magnetometer sensor, a gyroscope sensor, and a camera sensor. The measurement sensors may include inertial measurement units (I Mils), barometer sensors, and location sensors, such as Global Positioning System (GPS) units, to improve tracking accuracy of the movement of a roller used in soil compaction. The movement tracking may cover orientation, position, and elevation aspects of the roller. IMUs may be included as a type of measurement sensor to measure changes in the orientation and movement dynamics of the roller, thereby providing data on factors such as angular velocity and linear acceleration, aiding in the precise tracking of the roller's motion along various axes.

[0112] A barometer sensor 155 may be used to gauge atmospheric pressure variations, wherewith these readings may help deduce changes in elevation. Generally, atmospheric pressure decreases with a rise in elevation, potentially enabling the capturing of vertical movement across the compaction site 10. A location sensor 152, such as a GPS unit, may be incorporated to calculate the precise geographic position of the roller and ensure alignment of its path with site specifications. The location measurement 142 from the GPS data may offer an overview of the position and trajectory of the roller within the compaction site 10. To enhance GPS accuracy and provide more precise location data, the GPS units may use Real-Time Kinematic (RTK) corrections. RTK may be an advanced positioning technology that corrects standard GPS signals for local atmospheric conditions and satellite signal variances. The RTK corrections may come from an onsite base station specifically installed to support operations or from an RTK network provider offering corrections over a broader area.

[0113] Combining data sources in a sensor fusion algorithm may lead to a more accurate depiction of the movement of a roller. By considering multiple environmental and operational factors, the effectiveness of the compaction process may be ensured.

[0114] A compaction score 94 of the calibration area 14 may be measured 340 by conducting one or more standard tests 96. The standard tests 96 may include a Proctor compaction test, a moisture content test, a field density test, a sand cone test, a plate load test, and a lightweight deflectometer test. The Proctor compaction test may determine the optimal moisture content for achieving maximum density for a given soil type. The moisture content test may measure the amount of water present in the soil during testing. The field density test may be conducted on-site to determine the density of the soil after compaction. The measurements from the field density test may be compared to the compaction target 16 to assess the effectiveness of the compaction effort. The sand cone test may involve digging a hole in the compacted soil, filling it with calibrated sand from a cone device, and calculating the density based on the volume and weight of the sand required to fill the hole. The plate load test may assess the bearing capacity and deformation of the soil under a specified load by applying a load to a steel plate placed on the ground and measuring the settlement of the plate. The lightweight deflectometer test may evaluate the compaction quality and bearing capacity of soil by measuring the surface deflection as a load is applied through a falling weight to a ground-placed plate.

[0115] A compacted measurement map 98 indicative of a compacted soil measurement 162 at the plurality of calibration locations 164 of the calibration area 14 may be recorded 360 upon determination 350 that the compaction score 94 is within the compaction target 16. The determination 350 may occur once a compaction score 94 is measured 340 from one or more standard tests 96. The compaction score 94 may quantitatively represent the effectiveness of soil compaction within the calibration area 14. The compaction score 94 may be determined 350 to be above or below a predefined compaction target 16 criteria to assess if the soil is adequately compacted for the project purposes.

[0116] When determination 352 is made that the compaction score 94 is inadequate, compaction of the calibration area 14 is repeated, and a new loose measurement map 90 indicative of a loose soil measurement 160 at a plurality of calibration locations 164 of the calibration area 14 may be recorded 330. Upon determination 354 that the compaction score 94 is adequate, a new set of vibration data indicative of a compacted soil measurement 162 may be recorded 360 across the same calibration locations 164. This compacted measurement map 98 now reflects the vibration levels of the compacted soil, as opposed to the initial loose state. In some embodiments, the vibration data may be recorded as the compaction is achieved, and the data may be gathered from the last collected samples. The resulting dataset may visually represent the vibration characteristics of the soil after compaction.

[0117] The predictive compaction model 82 may be computed 370 using the loose measurement map 90, the compacted measurement map 98, and the one or more standard tests 96. The predictive compaction model 82 may be configured to predict a predicted compaction score 95 from a monitoring measurement 140. The predictive compaction model 82 may serve as a computational or algorithmic construct developed through data analysis or machine learning techniques. The predictive compaction model 82 may predict a predicted compaction score 95 as an outcome of soil compaction efforts based on input variables. The predictive compaction model 82 may be calibrated or trained on datasets that record vibration levels of soil exhibiting its initial, un-compacted state at various locations within the calibration area 14. Additionally, vibration levels of the soil after compaction may be recorded, providing a post-compaction snapshot of vibration characteristics across the same set of locations within the calibration area 14. When multiple compaction runs are needed to achieve compaction, the map of each run may be used to enhance the precision of the predictive compaction model 82. The predictive compaction model 82 may also incorporate data from the standard tests 96, which may include a Proctor compaction test, a moisture content test, a field density test, a sand cone test, a plate load test, a lightweight deflectometer test, and / or other relevant tests. The standard tests 96 may provide quantitative measures of soil properties 44 relevant to compaction, such as field density, moisture content, and load-bearing capacity. The predictive compaction model 82 may estimate the predicted compaction score 95 from a monitoring measurement 140, such as vibration measurement 141. Inputs, including soil properties 44 or location measurement 142, may also be considered. The predicted compaction score 95 may reflect the effectiveness of the compaction process and may indicate whether the soil has been compacted to the desired degree according to project specifications. Temperature measurement 144 and / ormoisture measurement 143 may be used when recorded 330 to improve the accuracy of the predictive compaction model 82.

[0118] Configuring the predictive compaction model 82 may be achieved by analyzing the relationship between measured vibration levels, recorded both before and after compaction, and outcomes of the standard tests 96. Patterns and correlations may be identified in the data, allowing the predictive compaction model 82 to predict a predicted compaction score 95 based on new vibration measurement 141. The predictive compaction model 82 may provide a tool for assessing soil compaction quality in real-time or in future projects or runs on other areas of the current project. Machine learning methods for obtaining the predictive compaction model 82 may include supervised learning, unsupervised learning, reinforcement learning, deep learning, a neural network, support vector machines, k-nearest neighbors, and combinations thereof.

[0119] A third aspect of the teachings presented herein relates to a method for monitoring a soil compaction of a compaction site 10. Reference is now made to the drawings in which Figure 7 depicts an activity diagram of an exemplary method 400 for monitoring a soil compaction, Figure 8 depicts a block diagram of an exemplary system 2000 for monitoring a soil compaction, and Figure 9 depicts a block diagram of an exemplary compactor equipment 100 for monitoring a soil compaction in accordance with the teachings of the present invention.

[0120] During the soil compaction, compaction equipment 100 equipped with measurement sensors 150 may be used. In embodiments, the measurement sensors 150 may comprise at least one of a vibration sensor 151, a location sensor 152, a moisture sensor 153, an infra-red sensor 154, a barometer sensor 155, a magnetometer sensor 156, a gyroscope sensor 157, and a camera sensor 158. The monitoring measurement 140 may comprise at least one of a vibration measurement 141 , a location measurement 142, a moisture measurement 143, a temperature measurement 144, a barometer measurement 145, a magnetometer measurement 146, a gyroscope measurement 147, and a camera measurement 148.

[0121] During the soil compaction, compaction equipment 100 equipped with measurement sensors 150 comprising a vibration sensor 151 and a location sensor 152 may be used to collect 410 monitoring measurements 140 at a monitoring location 166. The compaction equipment 100 may be used on soil within a compaction site 10 to achieve desired engineering properties. Mechanical forces may be applied to the soil as the compaction equipment 100 moves, thereby potentially altering the density and structural properties thereof. The vibration sensor 151 may be employed to potentially monitor and optimize this process.

[0122] The intensity and characteristics of vibrations generated by the compaction equipment 100 as it compacts soil may be measured by a vibration sensor 151 . Insights into the compactness level of the soil may be provided by the vibration measurement 141. Different types of soil may respond differently to compaction, and vibration patterns may help assess whether the soil has been adequately compacted or may require further passes. Various parameters, such as amplitude, frequency, and acceleration of the vibrations, may be measured by the vibration sensor 151.

[0123] A moisture sensor 153 may be used to measure moisture during compaction. The geographical position of the compaction equipment 100 as it moves across the site may be tracked by a location sensor 152.

[0124] The mapping of compaction efforts to specific locations may be enabled by the location sensor 152, which may help ensure uniform treatment across the entire area, potentially preventing any sections from being overlooked. The location sensor 152 may utilize a global positioning system (GPS) or a global navigation satellite system (GNSS). Other positioning systems that may be used by the location sensor 152 include, for example, the BeiDou Navigation Satellite System (BDS), local positioning systems (LPS), ultra-wideband (UWB) technology, radio-frequency identification (RFID), optical positioning systems, inertial navigation systems (INS), or a combination of multiple systems, which may enhance accuracy. The choice of positioning system may depend on project-specific requirements, such as desired accuracy, environmental conditions of the compaction site 10, and technology accessibility.

[0125] A vibration sensor 151 may be directly affixed to the drum of the compaction equipment 100. The vibration levels may be recorded by the vibration sensor 151 as the drum traverses the soil. Such a method may provide direct feedback on the effectiveness of the compaction process at specific locations. In embodiments, a wireless vibration sensor 151 may be positioned on the drum or body of the compaction equipment 100, transmitting real-time data to a monitoring system. Alternatively, or additionally, vibration data loggers with accelerometers may be used to store data for later analysis when real-time data transmission is unreliable or impractical. Certain compaction equipment 100 may come with integrated systems that combine vibration sensor 151 and location sensor 152.

[0126] The moisture sensor 153 may measure the water content within the soil in real-time, providing information on how moisture levels may affect soil compaction and structural stability. The moisture sensor 153 may help identify the moisture content 143 for achieving maximum density. In one embodiment, a geotechnical rules engine may be used to infer moisture content instead of, or in addition to, using a moisture sensor. Vibration readings may be used to infer moisture content from soil by leveraging historical data and machine learning techniques. Models may be trained on historical compaction projects, where moisture data is available, to predict moisture content from the vibration readings.

[0127] An infra-red sensor 154 may be employed to measure thermal emissions from the surface of the soil, thereby potentially providing an indirect assessment of the soil temperature. An infra-red sensor 154 may be used to detect temperature variations across the compaction site 10 that may affect soil properties 44 and compaction outcomes.

[0128] A barometer sensor 155 may measure atmospheric pressure, providing elevation data about different locations within the compaction site 10. Variations in elevation within the site may impact compaction needs and control of the compaction equipment 100. Monitoring atmospheric pressure may provide an assessment of the need for additional fill material 30 at specific locations to maintain consistent elevation levels throughout the compaction site 10.

[0129] A magnetometer sensor 156 may detect the magnetic field of the Earth and may measure the orientation of the compaction equipment 100 relative to the magnetic field of the Earth. A gyroscope sensor 157 may provide data regarding the orientation and stability of the compaction equipment 100, thereby potentially maintaining the alignment of the compaction equipment 100 and informing potential effects of terrain changes on compaction.

[0130] A camera sensor 158 may capture visual images or video of the compaction process. The visual data, captured by the camera sensor 158, may be processed to detect surface anomalies, for example, cracks or uneven compaction. The visual data may assist in real-time adjustments in compaction strategies and may serve purposes of documentation and further analysis.

[0131] A monitoring measurement 140 may be collected 410 at a monitoring location 166 of the compaction equipment 100 within the compaction site 10. Data from various measurement sensors 150 integrated into the compaction equipment 100 may include parameters such as vibration measurement 141 , temperature measurement 144, moisture measurement 143, and location measurement 142 during a compaction activity. The compaction equipment 100 at a monitoring location 166, functioning as a reference point on the compaction site 10, may use such monitoring measurements 140 to generate a detailed map of compaction quality across the site, enabling uniform coverage and identification of areas requiring additional attention. Measurement sensors 150 within the compaction equipment 100 may capture the detailed monitoring measurements 140. For example, a vibration sensor 151 may gauge soil compactness, a location sensor 152 may enable positional tracking, a moisture sensor 153 may assess soil moisture levels, a temperature sensor 154 may record surface heat readings, and advanced sensors such as an infra-red sensor 154 or a camera sensor 158 may provide a comprehensive evaluation. The selection of measurement sensors 150 may depend on specific project requirements and desired data for assessing soil compaction efforts.

[0132] A compaction value 60 may be computed 420 from the monitoring measurement 140 using a scoring model 84. The compaction value 60 may be determined from the vibration measurement 141 and the location measurement 142 by employing the scoring model 84. This compaction value 60 may serve as a numerical representation indicative of the state of compaction of the soil at a specific location. The compaction value 60 may quantify the degree to which the soil has been compacted based on the collected data. A higher compaction value 60 may suggest a more compacted state, whereas a lower compaction value 60 may suggest that the soil is less dense and potentially necessitates further compaction, removal, or replacement. The compaction value 60, computed using the vibration measurement 141, may be valid in a small area around the location from which the compaction value 60 was derived. When available, temperature and moisture information from a temperature measurement 144 and a moisture measurement 143 may also be used to compute 420 the compaction value 60.

[0133] In one embodiment, a subgrade vibration influence may be isolated 470 from the monitoring measurement 140 to improve the compaction value 60 of a fill material 30. A subgrade vibration influence may be filtered from the vibration measurement 141 , thereby enhancing the accuracy of the compaction value 60 of a fill material 30. The subgrade 20 may function as the foundation layer of soil upon which the fill material 30 is placed.The subgrade vibration influence may be the inherent contribution of the subgrade 20 to the measured vibration measurement 141. Properties of the subgrade 20, for example, moisture content and density, may impact vibration measurements. By considering properties of the subgrade 20 during data collection, the method may isolate the vibration response of the fill material 30, which may enhance the quality and reliability of the vibration data used for compaction assessment and modeling. Geotechnical reports may provide detailed information on subgrade material properties, including composition, moisture content, and load-bearing capacity. The subgrade vibration influence may be estimated by reviewing geotechnical reports. Alternatively, or additionally, the subgrade vibration influence may be measured from the calibration area 14. Vibration measurement 141 collected from the subgrade 20 during calibration may be used to incorporate the subgrade vibration influence into the predictive compaction model 82, potentially leading to more accurate predictions of compaction outcomes. The data collected may serve as a baseline or reference point for understanding the inherent vibration characteristics of the subgrade 20. The subgrade vibration influence may be isolated 470 from the measured vibration using various techniques including, for example, frequency analysis, wave propagation modeling, and machine learning algorithms.

[0134] In one embodiment, a subgrade vibration influence may be estimated from a calibration area 14 to enhance the monitoring measurement 140 during soil compaction. The calibration area 14 may serve as a controlled section of the compaction site 10 to characterize vibration responses intrinsic to the subgrade 20. Baseline vibration data specific to the subgrade 20, collected within the calibration area 14, may facilitate isolating the impact of the subgrade on overall vibration measurement 140 during subsequent compaction activities. This approach may enable the refinement of vibration measurement 140 interpretations to account for the contribution of the subgrade when assessing fill material 30 compaction. Estimating the subgrade vibration influence may involve systematically applying compaction forces within the calibration area 14 and meticulously capturing corresponding vibration behaviors, thereby informing models for real-time compaction monitoring and decision-making.

[0135] The scoring model 84 may include a set of rules designed to interpret vibration data and other relevant parameters to calculate a compaction value 60. Various data sources may be employed for configurations such as soil properties 44, including a gradation, moisture content, and Atterberg limits, obtained from a laboratory test 42 on soil samples 40. Configuration data may also include a historical baseline 52 and / or a predicted baseline 50 from methods previously described, which may assist in refining the scoring model 84 by providing a context for how similar soil types and conditions may respond to compaction efforts. Site-specific compaction parameters 19 including lift thickness, control strip size, and moisture content may be incorporated into the scoring model 84. Sitespecific compaction parameters 19 may influence the efficacy of the compaction process and may tailor the scoring model 84 to conditions specific to a compaction site 10. Results from standard tests 96 such as a Proctor compaction test, a moisture content test, a field density test, a sand cone test, a plate load test, and a lightweight deflectometer test, may provide quantitative measures of the compaction state of the soil. The loose measurement map 90 and the compacted measurement map 98 may be used to configure the scoring model 84, providing records of vibration measurements 141 before and after compaction at various locations of the calibration area 14. The scoring model 84 may incorporate configuration data through machine learning or correlation with results fromstandard tests 96. Configuration of the scoring model 84 may include employing the predictive compaction model 82 obtained by the method 300. Various configuration datasets may be combined into the scoring model 84 through traditional statistical methods or machine learning.

[0136] The predictive compaction model 82 may be computed 370 from data obtained in the method 300 for planning a soil compaction of a compaction site 10. A calibration area 14 and a compaction target 16 may be established 310 to serve as a reference for the compaction process. Site-specific compaction parameters 19 may be established 320 based on the compaction site 10. During a calibrating soil compaction of the calibration area 14 using a compaction equipment 100 equipped with measurement sensors 150, a loose measurement map 90 indicative of a loose soil measurement 160 at a plurality of calibration locations 164 of the calibration area 14 may be recorded 330. A compaction score 94 of the calibration area 14 may be measured 340 by conducting one or more standard tests 96. Upon determination 350 that the compaction score 94 is within the compaction target 16, a compacted measurement map 98 indicative of a compacted soil measurement 162 at the plurality of calibration locations 164 of the calibration area 14 may be recorded 360. The predictive compaction model 82 may be computed 370 from the loose measurement map 90, the compacted measurement map 98, and the one or more standard tests 96, and may be configured to predict a predicted compaction score 95 from a measurement. The predictive compaction model 82 may be obtained from a machine learning method comprising at least one of a supervised learning method, an unsupervised learning method, a reinforcement learning method, a deep learning method, a neural network, support vector machines, and k-nearest neighbors.

[0137] In embodiments, an averaging approach may be applied to compaction values 60 over an averaging distance. The averaging distance may be configured as 1 meter, considered a balance between resolution and complexity. Applying averaging over a specified distance may address sensor imprecision and outlier soil conditions. For averaging compaction values 60, a denser sampling frequency may be used. Configuration of the averaging distance may depend on factors such as soil properties 44, a roller dimension 108, and site characteristics 18. During aggregation, information such as minimum, maximum, variance, standard deviations, and multimodal analysis may be extracted. Confidence in the aggregated compaction value 60 and the sampling area may be enhanced. A moving average method may be used to facilitate the averaging process.

[0138] Specific locations of the compaction site 10 may require different target compaction thresholds 56. A target compaction threshold 56 may be computed 430 using a monitoring measurement 140 and a target baseline 54. The target baseline 54, for example, may be the predicted baseline 50 from the method 200 for modeling a compaction site 10. Differing target compaction thresholds 56 may be required for specific site locations according to intended use. For instance, areas designated for future buildings or roads may necessitate denser compaction than areas for landscaping, thereby requiring different target compaction thresholds 56. The target compaction threshold 56 may indicate a target density or other relevant metric that compaction efforts aim to achieve, ensuring the soil has the necessary properties for its intended function. Elements such as target dry density, moisture content, relative compaction, bearing capacity— such as the California Bearing Ratio— and penetration resistance may be considered when determining the target compaction threshold 56. The baseline used incomputing the target compaction threshold 56 may be derived from methods described herein, such as a historical baseline 52 from historical data 46 or a predicted baseline 50 resulting from predictive modeling. The baseline may provide a benchmark reflecting the expected capabilities of compaction efforts.

[0139] In one embodiment, the predicted baseline 50 may be obtained using method 200 for modeling a compaction site 10. A sampling area 12 that includes a subgrade 20 and is filled with a fill material 30 may be used to collect 220 soil samples 40 comprising a subgrade sample 22 from the subgrade 20. A laboratory test 42 may be conducted 230 on the soil samples 40 to determine soil properties 44, which may include a gradation, a moisture, and an Atterberg limit. Once the soil properties 44 are determined, the predicted baseline 50 may be predicted 250 from the soil properties 44 and a predictive site model 80. The predictive site model 80 may include machine learning methods such as a supervised learning method, an unsupervised learning method, a reinforcement learning method, a deep learning method, a neural network, support vector machines, and k-nearest neighbors. In some embodiments, a historical baseline 52 may be established 240 by comparing the soil properties 44 against historical data 46, which may contribute towards predicting the predicted baseline 50 along with the predictive site model 80.

[0140] In one embodiment, the target baseline 54 may be computed by comparing the compaction value 60 to an average stiffness within the compaction site 10. The target baseline 54 may be established by contrasting the compaction value 60, which may indicate the density of soil compaction at a specific location, with the average stiffness, which may indicate resistance to deformation under similar conditions across the site. By aligning the compaction value 60 with this average stiffness, the target baseline 54 may represent local site conditions. This comparison may provide insights into the conformity of achieved compaction with broader site characteristics and may guide revisions to compaction processes upon detecting discrepancies from anticipated stiffness. Techniques such as the plate load test or instrumented in-situ tests like the lightweight deflectometer may be used to derive the average stiffness, potentially allowing the modeling or monitoring processes to establish accurate benchmarks for soil compaction efforts.

[0141] Different actions may be undertaken depending on whether the compaction value 60 is within the target compaction threshold 56. Upon detecting 440 that the compaction value 60 is within 444 the target compaction threshold 56, a user 102 may be notified 460 of a soil compaction achievement at the monitoring location 166. The user 102 may be, for example, an operatorof the compaction equipment 100, an on-site foreman, a geotechnical technician, or a geotechnical engineer.

[0142] Upon detecting 440 that the compaction value 60 is outside 442 of the target compaction threshold 56, a user 102 may be notified 450 of further remedial steps required at the monitoring location 166. The user 102 may be, for example, an operator of the compaction equipment 100, an on-site foreman, a geotechnical technician, or a geotechnical engineer. The remedial steps may include additional compaction or actions such as replacing existing material with a drier material. The compaction value 60 may be continuously monitored and compared against the target compaction threshold 56 within the compaction equipment 100 or remotely, by transmitting the data to computer software operating on remote compute hardware.

[0143] The compaction value 60 on-site may be monitored using compute hardware available within the compaction equipment 100 or within its vicinity to compute the compaction value 60 from the sensor data. The scoring model 84 and the target compaction threshold 56 may have been loaded in a memory module of the compute hardware prior to the compaction run. On-site analysis may allow for offline monitoring and may be practical in situations where a wide area network is unreliable or impractical.

[0144] The compaction value 60 may be computed and monitored remotely through the use of a wide area network. Data collected on-site may be transmitted to a remote location for analysis, possibly through a cloud-based system. Remote processing may enable centralized monitoring scenarios wherewith multiple compaction sites 10 or multiple construction activities may be monitored and aggregated with or without the involvement of experts. Aggregation of data coming from multiple compaction sites 10 or multiple construction activities may enable further monitoring activities such as real-time planning, monitoring, or real-time optimization of resource allocation. Various approaches may be used to transfer data between the compaction equipment 100 and a remote processing service, including cellular networks (for example, 4G / 5G), Wi-Fi, satellite communications, or low-power wide-area network (LPWAN) technologies requiring low power consumption and providing long-range connectivity.

[0145] Various communication protocols may be used to continuously transmit and receive remote compaction data. These protocols may include message queuing telemetry transport (MQTT), hypertext transfer protocols / hypertext transfer protocol secure (HTTP / HTTPS), constrained application protocol (CoAP), and advanced message queuing protocol (AMQP).

[0146] Notification options for the user 102 may vary according to the system complexity and construction project preferences. Notifications may display on user interfaces of tablets or mobile devices, as many modern compaction equipment 100 may include such display screens. A user interface module 180 may present detailed information about the compaction process, for example, maps of the compaction site 10 with areas marked where the compaction value 60 is sufficient or insufficient based on the target compaction threshold 56. Notification forms may include textual notifications, visual cues such as color-coding, and recommendations for future steps.

[0147] When a notification relates to a soil compaction area necessitating further remedial steps, coordinates or a map representation of the area may be provided. The area may comprise a region within the compaction site 10 where the compaction value 60 may not meet the target compaction threshold 56.

[0148] Notifications may be presented in the form of color-coded lights, such as using a color scheme comparable to a traffic light system. For example, a green light may signal areas of adequate compaction, a red light may indicate inadequate compaction, and a yellow light may represent marginal areas. Audible alerts, including sounds or spoken messages, may be used in conjunction with or as an alternative to visual notifications, providing auditory cues when compaction thresholds 56 are met or not met.

[0149] When communicating the compaction value map 99, areas on the compaction value map 99 may be identified according to geotechnical rules. The geotechnical rules may be defined as a set of guidelines or standards used in civil engineering to evaluate and determine the properties and behaviors of soil and rock in relation toconstruction and soil compaction activities. The geotechnical rules may aim to guide decisions, predictions, and evaluations related to the mechanical and physical properties of geotechnical materials, ensuring that construction projects or soil compaction efforts achieve desired safety, stability, and structural performance. The geotechnical rules may be informed by a combination of empirical knowledge, scientific research, and industry best practices. The geotechnical rules may evaluate different aspects of soil behavior and properties, such as load-bearing capacity, compaction density, soil gradation, moisture content, Atterberg limits, slope stability, ground settlement potential, and response to dynamic or seismic loads. The geotechnical rules may be expressed in numerical thresholds, pass / fail criteria, recommended compaction techniques, or safety factors. The geotechnical rules may be developed and maintained by various standards organizations, governmental agencies, engineering bodies, or construction industry associations.

[0150] In the compaction value map 99, geotechnical rules may be used to identify areas warranting followup actions or additional analysis. Classification of regions may occur based on the compaction value 60, categorizing them as acceptable, unacceptable, or requiring further assessment. Evaluation of geotechnical rules may be enhanced through machine learning or other algorithmic models, allowing for more precise and data-driven identification of soil characteristics within the compaction site 10. Geotechnical rules may consider site-specific compaction parameters 19, regulatory requirements, and project-specific objectives, aimed at ensuring the structural integrity of compacted soil in alignment with the intended design and purpose of the site.

[0151] The geotechnical rules may be evaluated using a geotechnical rule model trained with machine learning. The geotechnical rule model may facilitate the interpretation and application of these rules in soil compaction processes. Developing the geotechnical rule model may involve the utilization of large datasets containing information about previous compaction projects, soil properties 44, and their respective outcomes. Through this data, the model may identify and predict complex patterns and relationships inherent in geotechnical processes. Supervised learning and unsupervised learning techniques may be employed for data parsing and function enhancement over time. The trained geotechnical rule model may assist in identifying areas on a compaction value map 99 where specific geotechnical criteria have been met or may need attention, potentially automating the evaluation process and enabling more rapid and precise assessments than manual evaluation methods.

[0152] The geotechnical rules may include several identification schemes designed to categorize different soil compaction conditions based on the compaction value 60. These identification schemes may aid in determining the necessary actions to achieve desired soil compaction. For example, areas with the compaction value 60 below an acceptable threshold may be identified using an unacceptable identification scheme. Areas with the compaction value 60 between the acceptable threshold and an ideal threshold may be identified using an acceptable identification scheme. Areas with the compaction value 60 above the ideal threshold may be identified using an ideal identification scheme. Under-passed areas may be identified using an under-passed identification scheme. Areas with an anomaly may be identified using an anomaly identification scheme.

[0153] An unacceptable identification scheme may be used to identify areas where the compaction value 60 is below an acceptable threshold. The acceptable threshold may represent the minimum compaction criteria necessary for the area to be deemed structurally sound or suitable for the intended use. Using the unacceptable identification scheme to designate areas may signal the need for remedial compaction efforts or further analysis to ensure that the soil is adequately compacted.

[0154] An acceptable identification scheme may indicate areas where the compaction value 60 is situated between the acceptable threshold and an ideal threshold. The compaction in these areas may be deemed satisfactory, yet not optimal. Identifying these zones may aid in prioritizing them for monitoring, ensuring that they persist within safe and functional boundaries.

[0155] An ideal identification scheme may identify areas where compaction values 60 are above an ideal threshold, indicating a state of optimal compaction. Areas where the compaction value 60 is above an ideal threshold may indicate that the compaction has exceeded standard expectations for structural support, potentially requiring limited or no further action.

[0156] An under-passed identification scheme may identify areas where insufficient passes of compaction equipment 100 may have been applied. Insufficient soil density may relate to inadequate coverage or effort regarding compaction passes. Identified areas may be scheduled for additional compaction to reach the desired compaction levels.

[0157] An anomaly identification scheme may focus on areas exhibiting abnormal or unexpected deviations in compaction values 60. Anomalies within the soil compaction process may be attributed to irregularities such as variations in soil composition, soil properties 44, unexpected subsurface features, or inconsistencies in the compaction process. Identifying these areas may prompt further investigation to uncover the root cause and adjust the compaction strategy where adjustments may be needed.

[0158] The completed identification scheme may include specific criteria to determine when an area within the compaction site 10 is regarded as fully compacted to the desired specifications. For example, completed areas may be identified based on the expected number of passes being completed, a low difference between the compaction value 60 and the compaction value 60 of the previous iteration, and / or the compaction value 60 being above an ideal threshold.

[0159] Identification schemes may be applied during the evaluation of a compaction value map 99 to facilitate targeted intervention measures and the monitoring of site-specific compaction performance. Identification schemes may serve various functions in assessing results of soil compaction activities according to predefined criteria and may employ a variety of techniques to convey information effectively. For example, a color scheme may employ color-coding to represent different compaction states. Green may indicate an ideal identification scheme, yellow may denote an acceptable identification scheme yet not ideal threshold, and red may signify an unacceptable identification scheme requiring further action. Pattern schemes may leverage geometric or texture patterns, for example, stripes and / or dots, to signify various compaction results on a compaction value map 99. Patterns mayoverlay areas to offer a visual cue regarding the compaction status without using colors. Filter schemes may be implemented where specific areas may be highlighted or filtered out using an unacceptable identification scheme or other predefined schemes. Filters may be applied to focus on areas requiring attention or verification, such as zones where a compaction value 60 is below an acceptable threshold. Notifications may be generated by an alert system, wherewith visual, auditory, or both types of feedback may be used to inform users 102 or approving engineer 104 of the compaction results. For example, when the compaction value 60 falls below an acceptable threshold, an alert system may emit a sound or display a message, thereby prompting remedial actions. The collection of identification schemes, including unacceptable identification scheme, acceptable identification scheme, ideal identification scheme, under-passed identification scheme, or anomaly identification scheme, may facilitate decision-making, enhance communication of results, and streamline monitoring of compaction efforts by transforming intricate data into straightforward formats that users may easily interpret.

[0160] Communicating the compaction value map 99 may include identifying improving areas using an improving identification scheme. The improving areas may be identified based on a difference between the compaction value 60 and the compaction value 60 of the previous iteration. The improving identification scheme may assign a classification or status to these areas, indicating that improvements have been realized within the compaction process. Identifying improving areas may guide subsequent compaction actions and adjustments, recognizing regions where methods have effectively enhanced compaction outcomes over time. Highlighting these areas may enable decision-makers to focus on maximizing compaction efficiency and achieving compaction targets across the compaction site 10.

[0161] An expected number of passes may refer to a predetermined quantity of movements of the compaction equipment 100 across a specific area required to attain the intended soil density. The expected number may be established during the planning phase or derived from the predicted baseline 50 and the project requirements. Upon reaching the expected number of passes, the area may be considered potentially completed, subject to additional evaluation metrics.

[0162] The identification process may assess the variability in compaction values 60 obtained from the monitoring measurements 140. A low difference between a current compaction value 60 and the compaction value 60 of a previous iteration may suggest consistency in compaction quality and may indicate that further compaction may be unnecessary. By comparing these compaction values 60, a determination may be made that the area has reached a stable state of compaction.

[0163] The ideal threshold may be determined as the minimum compaction value 60 needed to conform to project and structural specifications. Upon surpassing this threshold, the compaction value 60 derived from the monitoring measurement 140 may indicate that the area has reached an acceptable level of compaction quality. Factors such as type of soil, project specifications, and regulatory standards may influence this threshold.

[0164] The completed identification scheme may be used to identify completed areas where the compaction value 60 has met the requisite compaction standards. By including criteria such as an expected number of passes,a low difference between the compaction value 60 and the compaction value 60 of the previous iteration, and the compaction value 60 being above an ideal threshold, the completed identification scheme may provide a structured approach to verify that the compaction meets the required specifications. This may ensure efficiency and quality control in the compaction process.

[0165] In one embodiment, the geotechnical rules may include evaluating a lift thickness. The evaluation of lift thickness within the geotechnical rules may refer to the analysis of the thickness of the soil layer compacted in a single pass of the compaction equipment 100. The effectiveness of evaluating lift thickness may impact the compaction process, affecting the density and structural integrity of the soil. The lift thickness may vary depending on the type of soil, compaction equipment 100 employed, and desired compaction density. Evaluating lift thickness may ensure that each layer is properly compacted, preventing issues such as inadequate compaction at the bottom of a thick lift or inefficient compaction from excessively thin lifts. Adjustments to the compaction approach may be informed by evaluating the lift thickness as part of the geotechnical rules, contributing to achieving the intended compaction results.

[0166] In one embodiment, the compaction value 60 may be recorded into a compaction value map 99. Upon completing the soil compaction, the compaction value map 99 may be communicated to an approving engineer 104. A visual representation of compaction values 60 across different locations of the compaction site 10 may be provided by the compaction value map 99. Components such as areas reaching the target compaction threshold 56 and areas necessitating further work may be indicated. Generation of the map may occur using GIS (Geographic Information Systems), CAD (Computer-Aided Design) software, or construction management software offering an overview of soil compaction status. Verification that the compaction work aligns with project specifications and regulatory standards may be conducted by the approving engineer 104 without an in-person site visit. The compaction value map 99 may present data necessary for assessing the quality and uniformity of compaction efforts. Based on received data and expertise of the approving engineer 104, annotations may indicate the requirement for further compaction in specific areas. Upon such annotation, the target compaction thresholds 56 may be updated, potentially indicating that the soil compaction remains incomplete.

[0167] Completion of the soil compaction may be achieved automatically when the compaction value 60 reaches the target compaction threshold 56 over the entire compaction site 10. In some embodiments, soil compaction may also be manually marked as complete by the user 102 upon observation that further compaction effort does not improve the compaction value 60.

[0168] In one embodiment, remote compaction data may be received 480 from a second compaction equipment 101 , thereby enabling a collaborative soil compaction on a plurality of subareas 11 of the compaction site 10. By receiving and transmitting the remote compaction data between two or more compaction equipment 100, a coordinated compaction effort may be achieved. By storing the remote compaction data together with the compaction value 60, real-time visibility of the compaction status of the entire compaction site 10 may be provided to the compaction equipment 100. This visibility of the compaction status may allow an operator of the compaction equipment 100 to concentrate compaction efforts on a subarea 11 of the compaction site 10. Once compaction ofthe subarea 11 is achieved, the visibility of the compaction status may enable the operator to move to another unfinished subarea 11 .

[0169] Wireless communication technologies, for example, Wi-Fi, Bluetooth, or cellular networks, may be used to exchange information directly between compaction equipment 100 in a peer-to-peer configuration. In embodiments, the information may be relayed across a central service configured to receive and relay the information to connected compaction equipment 100. The compaction data may also be shared with other equipment, for instance, dump trucks or pavers responsible for layering or laying base material on the compacted soil. Similarly, the compaction equipment 100 may receive information from other equipment on the compaction site 10, including connected sensors.

[0170] The plurality of subareas 11 may be assigned to the compaction equipment 100 based on considerations that may include the current location of the compaction equipment 100, the remote compaction data, the target compaction threshold 56, the target baseline 54, a scheduling constraint, a refueling need, a maintenance need, an observed compaction rate, an availability of equipment, and a planned activity on the plurality of subareas 11 .

[0171] The real-time geographical position of the compaction equipment 100 on the compaction site 10 may be included in determining its current location. Assignments may be made based on the current location to ensure engagement with the nearest subarea 11, potentially minimizing transit time and enhancing operational efficiency. In delegating tasks across subareas 11 , remote compaction data may be used as an additional factor. Remote compaction data may comprise information collected by various compaction equipment 100, providing insights into soil properties 44, compaction values 60, and existing conditions at potential assignments. Real-time ground conditions may be better addressed with this data, thereby increasing the precision of assignment.

[0172] The target compaction threshold 56 may specify the required compaction level within each subarea 11 . The assignment based on this target compaction threshold 56 may direct specific equipment efforts toward areas necessitating particular compaction intensity, which may be determined through scientific methods or regulatory standards. The target baseline 54 may be a performance indicator for compaction outcomes within a subarea 11 , informed by integrating a historical baseline 52 and data from a predictive site model 80.

[0173] Scheduling constraints may refer to predefined timelines and deadlines dictating the sequence and urgency of compaction assignments across the plurality of subareas 11 . Sorting assignments based on scheduling constraints may ensure alignment of the project timeline with higher-level project goals and / or legal requisites. Logistical considerations related to refueling needs may involve ensuring that the compaction equipment 100 is adequately fueled, potentially enabling the machinery to operate without interruption for scheduled assignments. Maintenance needs may be aligned with compaction assignments and maintenance schedules to prevent equipment downtime and ensure reliability. Observed compaction rates may reflect real-time monitoring and past performance data of the compaction equipment 100, thereby offering operational insights and ensuring that the capabilities of the equipment are appropriately matched with requirements of the plurality of subareas 11. Theavailability of equipment may consider which machinery and resources are presently operational and ready for assignment, thereby potentially preventing the idling or overloading of resources. Planned activities may encompass concurrent or future operations within the plurality of subareas 11, which may prescribe prioritization based on overarching project timelines or interdependencies across different site functions.

[0174] In certain embodiments, a central service may orchestrate the work across multiple compaction equipment 100 and compaction site 10. For example, subsequent to the completion of compaction of a subarea 11, the central service may assign a new subarea 11 to a compaction equipment 100 utilizing remote compaction data aggregated from multiple compaction equipment 100. Assignment of the subarea 11 may be optimized based on the current location of the compaction equipment 100, the remote compaction data, and the target baseline 54.

[0175] Additional factors may be considered, such as schedule constraints of compaction equipment operators, refueling needs of the compaction equipment 100, observed compaction rates, maintenance requirements, or availability of equipment. The assignment of the subareas 11 may also be prioritized to accommodate planned activities on the compaction site 10, such as upcoming construction in the subareas 11 or nearby areas.

[0176] The remote compaction data may be used to estimate remaining work efforts. The estimation of work may be adjusted in real time. For example, a first pass on a subarea 11 may yield lower or higher than anticipated compaction values 60, leading to a decrease or increase in estimated remaining work effort. The dispatching of the plurality of subareas 11 may be reorganized to optimize the utilization of resources and minimize the estimated remaining work effort.

[0177] Communicating the compaction value map 99 may include identifying areas necessitating further attention or analysis due to specific characteristics or conditions that signify potential concerns for soil stability or performance. Identification processes may evaluate compaction values 60 in relation to target compaction thresholds 56 and geotechnical rules, recognizing variations in soil composition, detecting anomalous compaction values 60, and assessing moisture or temperature inconsistencies. Resulting actions may include further compaction, soil amendment, and / or preventive measures to address identified issues. Guidance provided by these processes may ensure structural integrity and longevity of a project.

[0178] In one embodiment, a potential non-homogeneous area identification scheme may address the identification of potential non-homogeneous areas within the compaction value map 99. A focus may be placed on detecting variations in soil compaction or soil properties 44 across a specified area, highlighting sections where the composition, density, or performance of the soil may differ significantly from surrounding regions. Potential non- homogeneous areas of soil compaction may impact the overall structural integrity and load distribution of a construction project, thereby necessitating personalized interventions to ensure consistency in soil behavior.

[0179] The identification of potential moisture variation areas may involve using a potential moisture variation identification scheme to pinpoint regions exhibiting higher levels of moisture measurement 143. Moisture variation detection may detect areas that are too wet or too dry. Moisture variation may alter characteristics of soil compactionand decrease the load-bearing capacity of the material. Identifying moisture variation may allow an assessment of drainage needs or other remedial measures, such as additional compaction passes or the incorporation of drainage systems, to manage moisture levels effectively. In one embodiment, instead of, or in addition to, using direct moisture measurements 143, vibration readings may be used to infer moisture content from soil by using historical data and machine learning techniques. Models may be trained on historical compaction projects, where moisture data is available, to predict moisture content from the vibration readings.

[0180] A potential weak spot identification scheme may be used to locate areas within the compaction value map 99 that indicate reduced compaction values 60 or lower than expected soil strength. Identifying these weak spots may allow for the recognition of areas that could potentially compromise the uniform distribution of loads on the structure, potentially increasing the risk of settling or failure. By acknowledging these weak areas, planners and engineers may consider undertaking preventative measures, including additional passes with the compaction equipment 100 or applying reinforcement techniques, to enhance the durability and resilience of the compacted soil.

[0181] Incorporating multiple identification schemes into the compaction value map 99 communication may improve visualization and prioritization of areas needing additional investigation and treatment. Data-driven insights may be leveraged to guide decisions and optimize resource allocation across the compaction site 10.

[0182] In a collaborative soil compaction approach, efforts of individual compaction equipment 100 may be aligned towards achieving overall compaction objectives, potentially reducing the risk of inconsistent soil compaction and enhancing structural integrity of the project. Increasing efficiency in time and resources may be achieved by minimizing redundant compaction efforts and enabling targeted compaction activities based on collective intelligence of all compaction equipment 100 present on the compaction site 10.

[0183] The plurality of subareas 11 may be designated as distinct sections within a larger compaction site 10, where individual soil compaction activities may be carried out. In certain scenarios, these subareas 11 within a compaction site 10 may be strategically assigned to various compaction equipment 100. Assignment may consider diverse factors for efficient allocation of resources and scheduling.

[0184] A fourth aspect of the teachings presented herein relates to a system 2000 for monitoring a soil compaction of a compaction site 10. The monitoring of the soil compaction may be achieved in accordance with the method 400 disclosed hereinabove. Reference is now made to the drawings in which Figure 10 depicts a modular representation of a system 2000 for monitoring a soil compaction, and Figure 11 depicts a modular representation of a compaction modeling module 2100 in accordance with the teachings of the present invention.

[0185] The compaction equipment 100 may include a location sensor 152, a vibration sensor 151 , a compactor communication module 170, and a user interface module 180. In addition, a moisture sensor 153 and / or temperature sensor 144 may be included within the compaction equipment 100. A location measurement 142 of the compaction equipment 100 may be recorded by the location sensor 152. Vibration measurement 141 of the soil being compacted by the compaction equipment 100 may be recorded by the vibration sensor 151. The location measurement 142 of the compaction equipment 100 and the vibration measurement 141 of the soil beingcompacted may be transmitted by the compactor communication module 170. A compaction assessment 77 may be received by the compactor communication module 170. The compaction assessment 77 may be communicated to a user 102 by the user interface module 180. The user 102 may be, for example, an operator of the compaction equipment 100, an on-site foreman, a geotechnical technician, or a geotechnical engineer. The actual stacks of protocols used by the physical network interface(s) and / or logical network interface(s) 172, 174, 176, and 178 of the compactor communication module 170 do not affect the teachings of the present invention.

[0186] In collaborative configurations, the compactor communication module 170 may receive from a second compactor communication module 170' of a second compaction equipment 101' the remote location measurement 142 of the second compaction equipment 101' and remote compaction data, including remote vibration measurement 141 and remote compaction value 60 of the soil being compacted, thereby enabling a collaborative soil compaction.

[0187] Communication between the compaction equipment 100 and a second compaction equipment 101' may be achieved directly as peer-to-peer communication or across a central service such as the compaction modeling module 2100, wherewith the network interface module 2170 may be configured to relay the remote compaction data to the compaction equipment 100.

[0188] When deployed as a network node within a network 2200, the compaction modeling module 2100 may comprise a network interface module 2170, a storage system 2300, and a processor module 2120. The network interface module 2170 may be used to receive the location measurement 142 and vibration measurement 141 from the compactor communication module 170 and may transmit the compaction assessment 77 to the compactor communication module 170. The storage system 2300 may be used to store a scoring model 84 configured from a calibration area 14 and may store a target baseline 54 computed from historical data 46 and a plurality of soil properties 44. The processor module 2120 may be employed to compute a compaction value 60 from the vibration measurement 141 and the location measurement 142 using the scoring model 84 and may compute a target compaction threshold 56 from the location measurement 142 using the target baseline 54.

[0189] In embodiments, the processor module 2120 may compute an average compaction value 60 from a plurality of discrete compaction values 60 collected over an averaging distance. The averaging distance may be configured as 1 meter.

[0190] In embodiments, the processor module 2120 may compute the compaction value 60 into a compaction value map 99, and the network interface module 2170 may communicate the compaction value map 99 to an approving engineer 104.

[0191] The compaction modeling module 2100 may comprise a memory module 2160, a processor module 2120, a predictive module 2130, and a network interface module 2170. The compaction modeling module 2100 may include a management interface module 2150.

[0192] The compaction modeling module 2100 may comprise a storage system 2300 for storing and accessing long-term (i.e., non-transitory) data and may further log data while the compaction modeling module 2100is being used. Figure 10 shows examples of the storage system 2300 as a distinct database system 2300A, a distinct module 2300C of the compaction modeling module 2100 or a sub-module 2300B of the memory module 2160 of the compaction modeling module 2100. The storage system 2300 may be distributed over different systems 2300A, 2300B, and 2300C. The storage system 2300 may comprise one or more logical or physical as well as local or remote hard disk drive (HDD) (or an array thereof). The storage system 2300 may further comprise a local or remote database made accessible to the compaction modeling module 2100 by a standardized or proprietary interface or via the network interface module 2170.

[0193] The network interface module 2170 represents at least one physical interface that can be used to communicate with other network nodes. The network interface module 2170 may be made visible to the other modules of the compaction modeling module 2100 through one or more logical interfaces. The actual stacks of protocols used by the physical network interface(s) and / or logical network interface(s) 2172, 2174, 2176, and 2178 of the network interface module 2170 do not affect the teachings of the present invention.

[0194] The processor module 2120 may represent a single processor with one or more processor cores or an array of processors, each comprising one or more processor cores. The memory module 2160 may comprise various types of memory, including different kinds of Random Access Memory (RAM) modules, memory cards, Read-Only Memory (ROM) modules, and programmable ROM.

[0195] A bus 2180 is depicted as an example of means for exchanging data between the different modules of the compaction modeling module 2100. The teachings presented herein are not affected by the way the different modules exchange information. For instance, the memory module 2160 and the processor module 2120 could be connected by a parallel bus, but could also be connected by a serial connection or involve an intermediate module (not shown) without affecting the teachings of the present invention.

[0196] A predictive module 2130 provides services for computing compaction scores based on inputs which may include vibration measurement 141 , location measurement 142, soil properties 44, historical baseline 52 data, predictive site model 80, site-specific compaction parameters 19, standard tests 96 results, loose measurement map 90, compacted measurement map 98, and predictive compaction model 82. The compaction scores are transmitted using the compaction modeling module 2100, as further described in more details hereinabove and hereinbelow.

[0197] The management interface module 2150 may be used to oversee, configure, and interact with the compaction modeling module 2100. Management of operations of the compaction modeling module 2100 may include updating configurations, monitoring performance, accessing stored data within the storage system 2300, and adjusting parameters of the scoring model 84. The interface provided by the management interface module 2150 may facilitate integration of additional data inputs and the fine-tuning of predictive and evaluation models.

[0198] In one embodiments, a management interface module 2150 may be implemented as a remote management interface module 2152. The remote management interface module 2152 may enable users to interactwith a compaction modeling module 2100 from a location separate from where the compaction modeling module 2100 is physically installed. This remote capability may be accessed through network connections, allowing for real-time adjustments and monitoring from afar. The remote management interface module 2152 may extend the accessibility and flexibility of managing the compaction modeling module 2100, thereby offering users the ability to control and update system functionalities without needing direct physical access to hardware components of the compaction modeling module 2100.

[0199] The variants of processor module 2120, storage system 2300 and network interface module 2170 usable in the context of the present invention will be readily apparent to persons skilled in the art. Likewise, even though explicit mentions of the user interface module 180, the storage system 2300, the compactor communication module 170 and / or the processor module 2120 are not made throughout the description of the present examples, persons skilled in the art will readily recognize when such modules are used in conjunction with other modules of the compaction modeling module 2100 to perform routine as well as innovative elements presented herein.

[0200] Various network links may be implicitly or explicitly used in the context of the present invention. While a network link may be depicted as a wireless link, it could also be embodied as a wired link using a coaxial cable, an optical fiber, a category 5 cable, and the like. A wired or wireless access point (not shown) may be present on the network link. Likewise, any number of routers (not shown) may be present and part of the network link, which may further pass through the Internet.

[0201] The present invention is not affected by the way the different modules exchange information between them. For instance, the memory module and the processor module could be connected by a parallel bus, but could also be connected by a serial connection or involve an intermediate module (not shown) without affecting the teachings of the present invention.

[0202] A fifth aspect of the teachings presented herein relates to an adaptation of the method 200 of the first aspect into a non-transitory computer-readable medium storing a set of instructions for modeling a compaction site 10. When executed by one or more processors of a device, a predicted baseline 50 may be predicted 250 from a predictive site model 80 and soil properties 44 of a sampling area 12 of the compaction site 10. As with the method 200 described hereinabove, the soil properties 44 may be determined from soil samples 40 comprising a subgrade sample 22 from a subgrade 20 of the compaction site 10.

[0203] The non-transitory computer-readable medium may include instructions which, when predicting 250 the predicted baseline 50, further cause the device to establish 240 a historical baseline 52. The historical baseline 52 may be descriptive of an anticipated vibration data response and may be established by comparing the soil properties 44 against historical data 46. The predicted baseline 50 may be predicted 250 from the soil properties 44, the predictive site model 80, and the historical baseline 52. In embodiments, the compaction site 10 may be filled with a fill material 30, and the soil samples 40 may further comprise a fill sample 32 from the fill material 30.

[0204] As with the method 200 of the first aspect, the non-transitory computer-readable medium may include instructions to identify 210 a soil quantity, a compaction method, and a project scheduling. The soil samples 40 may be collected in accordance with a sampling frequency and a sampling procedure based on the soil quantity, the compaction method, and the project scheduling.

[0205] As with the method 200 of the first aspect, the soil properties 44 may comprise at least one of a gradation, a moisture, and an Atterberg limit. In embodiments, the predictive site model 80 may be configured from machine learning methods. The machine learning methods may include at least one of a supervised learning method, an unsupervised learning method, a reinforcement learning method, a deep learning method, a neural network, support vector machines, and k-nearest neighbors.

[0206] As with the method 200 of the first aspect, the predicted baseline 50 may comprise an expected pass count.

[0207] A sixth aspect of the teachings presented herein relates to an adaptation of the method 300 of the second aspect into a non-transitory computer-readable medium storing a set of instructions for planning a soil compaction of a compaction site 10. When executed by one or more processors of a device, site-specific compaction parameters 19 may be recorded based on the compaction site 10. A loose measurement map 90, indicative of a loose soil measurement 160 at a plurality of calibration locations 164 of a calibration area 14, may be recorded 330. A compaction score 94 of the calibration area 14 may be measured 340 from the results of one or more standard tests 96. Upon determining 350 that the compaction score 94 is within the compaction target 16, a compacted measurement map 98 indicative of a compacted soil measurement 162 at the plurality of calibration locations 164 of the calibration area 14 may be recorded 360. A predictive compaction model 82 may be computed 370 from the loose measurement map 90, the compacted measurement map 98, and the one or more standard tests 96, to predict a predicted compaction score 95 from a measurement.

[0208] As with the method 300 of the second aspect, the loose soil measurement 160 may comprise at least one of the following: vibration measurement 141, location measurement 142, moisture measurement 143, temperature measurement 144, barometer measurement 145, magnetometer measurement 146, gyroscope measurement 147, and camera measurement 148.

[0209] As with the method 300 of the second aspect, the one or more standard tests 96 may comprise at least one of a Proctor compaction test, a moisture content test, a field density test, a sand cone test, a plate load test, and a lightweight deflectometer test.

[0210] As with the method 300 of the second aspect, the site-specific compaction parameters 19 may comprise at least one of a lift thickness, a control strip size, and a moisture content.

[0211] As with the method 300 of the second aspect, the predictive compaction model 82 may be obtained from a machine learning method.

[0212] As with the method 300 of the second aspect, the machine learning method may comprise at least one of a supervised learning method, an unsupervised learning method, a reinforcement learning method, a deep learning, a neural network, support vector machines, and k-nearest neighbors.

[0213] A sixth aspect of the teachings presented herein relates to an adaptation of the method 400 of the third aspect into a non-transitory computer-readable medium storing a set of instructions for monitoring a soil compaction of a compaction site 10 during the soil compaction, using a compaction equipment 100 equipped with measurement sensors 150. When executed by one or more processors of a device, a monitoring measurement 140 may be collected 410 at a monitoring location 166 of the compaction equipment 100 within the compaction site 10. A compaction value 60 may be computed 420 from the monitoring measurement 140 using a scoring model 84. A target compaction threshold 56 may be computed 430 from the monitoring measurement 140 using a target baseline 54. Upon detecting 440 that the compaction value 60 is within 444 the target compaction threshold 56, a user 102 may be notified 460 of a soil compaction achievement at the monitoring location 166. The user may be, for example, an operator of the compaction equipment 100, an on-site foreman, a geotechnical technician, or a geotechnical engineer.

[0214] As with the method 400 of the third aspect, the scoring model 84 may be the predictive compaction model 82 from the non-transitory computer-readable medium of claim 58.

[0215] As with the method 400 of the third aspect, the target baseline 54 may be the predicted baseline 50 from the non-transitory computer-readable medium of claim 51.

[0216] As with the method 400 of the third aspect, the target baseline 54 may be computed by comparing the compaction value 60 to an average stiffness within the compaction site 10.

[0217] As with the method 400 of the third aspect, upon detecting 440 that the compaction value 60 is outside 442 of the target compaction threshold 56, the user 102 of the compaction equipment 100 may be notified 450 of further remedial steps required at the monitoring location 166.

[0218] As with the method 400 of the third aspect, the monitoring measurement 140 may comprise at least one of the following: a vibration measurement 141 , a location measurement 142, a moisture measurement 143, a temperature measurement 144, a barometer measurement 145, a magnetometer measurement 146, a gyroscope measurement 147, and a camera measurement 148.

[0219] As with the method 400 of the third aspect, the compaction value 60 may be averaged over an averaging distance.

[0220] As with the method 400 of the third aspect, the averaging distance may be 1 meter.

[0221] As with the method 400 of the third aspect, the averaging distance may be configured according to at least one of a soil properties 44, a roller dimension, and a site characteristic.

[0222] As with the method 400 of the third aspect, the non-transitory computer-readable medium may include instructions that further cause the device to record the compaction value 60 into a compaction value map 99. Upon completion of the soil compaction, the compaction value map 99 may be communicated to an approving engineer 104.

[0223] As with the method 400 of the third aspect, when communicating the compaction value map 99, the one or more instructions may cause the device to identify areas on the compaction value map 99 according to geotechnical rules.

[0224] As with the method 400 of the third aspect, the geotechnical rules may be evaluated using a geotechnical rule model trained with machine learning.

[0225] As with the method 400 of the third aspect, the geotechnical rules may comprise at least one of the following: areas with the compaction value 60 below an acceptable threshold may be identified using an unacceptable identification scheme; areas with the compaction value 60 between the acceptable threshold and an ideal threshold may be identified using an acceptable identification scheme; areas with the compaction value 60 above the ideal threshold may be identified using an ideal identification scheme; under-passed areas may be identified using an under-passed identification scheme; and areas with an anomaly may be identified using an anomaly identification scheme.

[0226] As with the method 400 of the third aspect, the one or more instructions may further cause the device to, when communicating the compaction value map 99 after a previous iteration, identify improving areas using an improving identification scheme. The improving areas may be identified based on a difference between the compaction value 60 and the compaction value 60 of the previous iteration. Completed areas may be identified by using a completed identification scheme. The completed areas may be identified based on an expected number of passes being completed, a low difference between the compaction value 60 and the compaction value 60 of the previous iteration, and the compaction value 60 being above an ideal threshold.

[0227] As with the method 400 of the third aspect, the geotechnical rules may comprise evaluating a lift thickness.

[0228] As with the method 400 of the third aspect, the non-transitory computer-readable medium may include instructions to isolate 470 a subgrade vibration influence from the monitoring measurement 140, thereby improving the compaction value 60 of a fill material 30.

[0229] As with the method 400 of the third aspect, the subgrade vibration influence may be estimated from a calibration area 14.

[0230] As with the method 400 of the third aspect, when communicating the compaction value map 99, potential non-homogeneous areas may be identified using a potential non-homogeneous area identification scheme. Potential moisture variation areas may be identified using a potential moisture variation identification scheme. Potential weak spot areas may be identified using a potential weak spot identification scheme.

[0231] As with the method 400 of the third aspect, the one or more instructions may further cause the device to receive 480 a remote compaction data from a second compaction equipment 101, thereby enabling a collaborative soil compaction on a plurality of subareas 11 of the compaction site 10.

[0232] As with the method 400 of the third aspect, the plurality of subareas 11 may be assigned to the compaction equipment 100 based on at least one of a current location of the compaction equipment 100, the remote compaction data, the target compaction threshold 56, the target baseline 54, a scheduling constraint, a refueling need, a maintenance need, an observed compaction rate, an availability of equipment, and a planned activity on the plurality of subareas 11 .

[0233] The invention described herein is not to be limited to the particular embodiments described hereinabove, as variations of these embodiments may be made and still fall within the scope of the appended claims. It is also to be understood that the terminology employed is for the purpose of describing particular embodiments; and is not intended to be limiting. Instead, the scope of the present invention will be established by the appended claims.

[0234] In order to provide a clear and consistent understanding of the terms used in the present specification, a number of definitions are provided below. Moreover, unless defined otherwise, all technical and scientific terms as used herein have the same meaning as commonly understood to one of ordinary skill in the art to which this disclosure pertains.

[0235] Use of the word “a” or “an” when used in conjunction with the term “comprising” in the claims and / or the specification may mean “one”, but it is also consistent with the meaning of “one or more”, “at least one”, and “one or more than one”. Similarly, the word “another'’ may mean at least a second or more.

[0236] As used in this specification and claim(s), the expression “at least one of” followed by a set of elements suggests that any combination of the elements from the set is being considered, including a single element from the set, and all elements from the set. For clarity, “at least one of” followed by a set does not strictly refer to having at least the whole set once, and possibly multiple times.

[0237] As used in this specification and claim(s), the words “comprising” (and any form of comprising, such as “comprise” and “comprises”), “having” (and any form of having, such as “have” and “has”), “including” (and any form of including, such as “include” and “includes”) or “containing” (and any form of containing, such as “contain” and “contains”), are inclusive or open-ended and do not exclude additional, unrecited elements or process steps.

[0238] As will be understood by a skilled person, other variations and combinations may be made to the various embodiments of the invention as described herein above. The scope of the claims should not be limited by the preferred embodiments set forth; but should be given the broadest interpretation consistent with the description as a whole.

[0239] A method is generally conceived to be a self-consistent sequence of steps leading to a desired result. These steps require physical manipulations of physical quantities. Usually, though not necessarily, these quantitiestake the form of electrical or magnetic / electromagnetic signals capable of being stored, transferred, combined, compared, and otherwise manipulated. It is convenient at times, principally for reasons of common usage, to refer to these signals as bits, values, parameters, items, elements, objects, symbols, characters, terms, numbers, or the like. It should be noted, however, that all of these terms and similar terms are to be associated with the appropriate physical quantities and are merely convenient labels applied to these quantities. The description of the present invention has been presented for purposes of illustration but is not intended to be exhaustive or limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art. The embodiments were chosen to explain the principles of the invention and its practical applications and to enable others of ordinary skill in the art to understand the invention in order to implement various embodiments with various modifications as might be suited to other contemplated uses.

[0240] A system may generally be conceived as an arrangement of multiple components that work together to achieve a particular function or result. These components each may have distinct roles and contribute to the overall operation of the system. It is convenient to describe these components as units, modules, parts, or elements. Components may be physical or logical in nature. In practice, systems may be implemented in various forms. While systems are typically comprised of multiple distinct components, in some embodiments, all or some components may coexist within a single device. This integration does not alter the fundamental understanding of the operation but rather represents an embodiment where functionality is consolidated. Such a configuration may be advantageous for specific applications where space, efficiency, or other considerations are paramount. Regardless of configuration, systems are understood to operate through physical interactions, which may, in some embodiments, be achieved through electronic components such as RAM, buses and processors.

Claims

CLAIMS1. A method (200) for modeling a compaction site (10), the method (200) comprising: from a sampling area (12) of the compaction site (10) comprising a subgrade (20) and being filled with a fill material (30):- collecting (220) soil samples (40) comprising a subgrade sample (22) from the subgrade (20);- conducting (230) a laboratory test (42) on the soil samples (40) to determine soil properties (44); and- predicting (250) a predicted baseline (50) from the soil properties (44) and a predictive site model (80).

2. The method (200) of claim 1 , wherein predicting (250) the predicted baseline (50) comprises: establishing (240) a historical baseline (52), descriptive of an anticipated vibration data response, by comparing the soil properties (44) against historical data (46); and wherein the predicted baseline (50) is predicted (250) from the soil properties (44), the predictive site model (80), and the historical baseline (52).

3. The method (200) of claim 1 or claim 2, wherein the soil samples (40) further comprise fill sample (32) from the fill material (30).

4. The method (200) of any one of claims 1 to 3, further comprising: identifying (210) a soil quantity, a compaction method, and a project scheduling; and wherein collecting the soil samples (40) is performed in accordance with a sampling frequency and a sampling procedure based on the soil quantity, the compaction method and the project scheduling.

5. The method (200) of any one of claims 1 to 4, wherein the soil properties (44) comprise at least one of a gradation, a moisture and an Atterberg limit.

6. The method (200) of any one of claims 1 to 5, wherein the predictive site model (80) is configured from machine learning methods comprising at least one of a supervised learning, an unsupervised learning, a reinforcement learning, a deep learning, a neural network, a support vector machines, and a k-nearest neighbors.

7. The method (200) of any one of claims 1 to 6, wherein the predicted baseline (50) comprises an expected pass count.

8. A method (300) for planning a soil compaction of a compaction site (10), the method (300) comprising: establishing (310) a calibration area (14) of the compaction site (10) and a compaction targetestablishing (320) site-specific compaction parameters (19) based on the compaction site (10); during a calibrating soil compaction of the calibration area (14) using a compaction equipment (100) equipped with measurement sensors (150):- recording (330) a loose measurement map (90) indicative of a loose soil measurement (160) at a plurality of calibration locations (164) of the calibration area (14); measuring (340) a compaction score (94) of the calibration area (14) by conducting one or more standard tests (96); upon determination (350) that the compaction score (94) within the compaction target (16):- recording (360) a compacted measurement map (98) indicative of a compacted soil measurement (162) at the plurality of calibration locations (164) of the calibration area (14); and computing (370) a predictive compaction model (82) from the loose measurement map (90), the compacted measurement map (98) and the one or more standard tests (96), configured to predict a predicted compaction score (95) from a measurement.

9. The method (300) of claim 8, wherein the measurement sensors (150) comprise at least one of a vibration sensor (151), location sensor (152), a moisture sensor (153), an infra-red sensor (154), a barometer sensor (155), a magnetometer sensor (156), a gyroscope sensor (157), and a camera (158) sensor, and wherein the loose soil measurement (160) comprises at least one of vibration measurement (141), a location measurement (142), a moisture measurement (143), a temperature measurement (144), a barometer measurement (145), a magnetometer measurement (146), a gyroscope measurement (147), and a camera measurement (148).

10. The method (300) of claim 8 or claim 9, wherein the one or more standard tests (96) comprise at least one of a Proctor compaction test, a moisture content test, a field density test, a sand cone test, a plate load test, and a lightweight deflectometer test.

11. The method (300) of any one of claims 8 to 10, wherein the compaction equipment (100) comprises at least one of a compactor roller and a plate-tamper compactor.

12. The method (300) of any one of claims 8 to 11 , wherein the site-specific compaction parameters (19) comprise at least one of a lift thickness, a control strip size, and a moisture content.

13. The method (300) of any one of claims 8 to 12, wherein the predictive compaction model (82) is obtained from a machine learning method.

14. The method of claim 13, wherein the machine learning method comprises at least one of a supervised learning, unsupervised learning, a reinforcement learning, a deep learning, a neural network, a support vector machines, and a k-nearest neighbors.

15. A method (400) for monitoring a soil compaction of a compaction site (10), the method (400) comprising: during the soil compaction, using a compaction equipment (100) equipped with measurement sensors (150):- collecting (410) a monitoring measurement (140) at a monitoring location (166) of the compaction equipment (100) within the compaction site (10);- computing (420) a compaction value (60) from the monitoring measurement (140) using a scoring model (84);- computing (430) a target compaction threshold (56) from the monitoring measurement (140) using a target baseline (54); and- upon detecting (440) that the compaction value (60) is within (444) the target compaction threshold (56):- notifying (460) a user (102) of the compaction equipment (100) of a soil compaction achievement at the monitoring location (166).

16. The method (400) of claim 15, wherein the scoring model (84) is the predictive compaction model (82) from the method (300) of claim 8.

17. The method (400) of claim 15 or claim 16, wherein the target baseline (54) is the predicted baseline (50) from the method (200) of claim 1 .

18. The method (400) of any one of claims 15 to 17, wherein the target baseline (54) is computed by comparing the compaction value (60) to an average stiffness within the compaction site (10).

19. The method (400) of any one of claims 15 to 18, further comprising: upon detecting (440) that the compaction value (60) is outside (442) of the target compaction threshold (56):- notifying (450) the user (102) of the compaction equipment (100) of further remedial steps required at the monitoring location (166).

20. The method (400) of any one of claims 15 to 19, wherein the measurement sensors (150) comprise at least one of a vibration sensor (151), location sensor (152), a moisture sensor (153), an infra-red sensor (154), a barometer sensor (155), a magnetometer sensor (156), a gyroscope sensor (157), and a camera (158) sensor, and wherein the monitoring measurement (140) comprise at least one of vibration measurement (141), a location measurement (142), a moisture measurement (143), a temperature measurement (144), a barometer measurement (145), a magnetometer measurement (146), a gyroscope measurement (147), and a camera measurement (148).

21. The method (400) of any one of claims 15 to 20, wherein the compaction value (60) is averaged over an averaging distance.

22. The method (400) of claim 21 , wherein the averaging distance is 1 meter.

23. The method (400) of claim 21 , wherein the averaging distance is configured according to at least one of a soil properties (44), a roller dimension, and a site characteristic.

24. The method (400) of any one of claims 15 to 23, further comprising: recording the compaction value (60) into a compaction value map (99); and upon a completion of the soil compaction:- communicating the compaction value map (99) to an approving engineer (104).

25. The method (400) of claim 24, wherein communicating the compaction value map (99) further comprises at least one of: identifying potential non-homogeneous areas using a potential non-homogeneous area identification scheme; identifying potential moisture variation areas using a potential moisture variation identification scheme; and identifying potential weak spot areas using a potential weak spot identification scheme.

26. The method (400) of claim 24 or claim 25, wherein communicating the compaction value map (99) comprises: identifying areas on the compaction value map (99) according to geotechnical rules.

27. The method (400) of claim 26, wherein the geotechnical rules are evaluated using a geotechnical rule model trained with machine learning.

28. The method (400) of claim 26 or claim 27, wherein the geotechnical rules comprise at least one of: identifying areas with the compaction value (60) below an acceptable threshold using an unacceptable identification scheme; identifying areas with the compaction value (60) between the acceptable threshold and an ideal threshold using an acceptable identification scheme; identifying areas with the compaction value (60) above the ideal threshold using an ideal identification scheme; identifying areas under-passed using an under-passed identification scheme; and identifying areas with an anomaly using an anomaly identification scheme.

29. The method (400) of any one of claims 26 to 28, performed after a previous iteration, wherein communicating the compaction value map (99) comprises at least one of: identifying improving areas using an improving identification scheme, wherein the improving areas are identified based on a difference between the compaction value (60) and the compaction value (60) of the previous iteration; and identifying completed areas by using a completed identification scheme, wherein the completed areas are identified based on an expected number of pass being completed, a low difference between the compaction value (60) and the compaction value (60) of the previous iteration, and the compaction value (60) being above an ideal threshold.

30. The method (400) of any one of claims 26 to 29, wherein the geotechnical rules comprise evaluating a lift thickness.31 . The method (400) of any one of claims 15 to 30, further comprising: isolating (470) a subgrade vibration influence from the monitoring measurement (140), thereby improving the compaction value (60) of a fill material (30).

32. The method (400) of claim 31, wherein the subgrade vibration influence is estimated from a calibration area (14).

33. The method (400) of any one of claims 15 to 32, further comprising: receiving (480) a remote compaction data from a second compaction equipment (101), thereby enabling a collaborative soil compaction on a plurality of subareas (11) of the compaction site (10).

34. The method (400) of claim 33, wherein the plurality of subareas (11) is assigned to the compaction equipment (100) based on at least one of a current location of the compaction equipment (100), the remote compaction data, the target compaction threshold (56), the target baseline (54), a scheduling constraint, a refueling need, a maintenance need, an observed compaction rate, an availability of equipment and a planned activity on the plurality of subareas (11).

35. A system (2000) for monitoring a soil compaction of a compaction site (10), the system (2000) comprising: a compaction equipment (100) comprising:- one or more measurement sensors (150) configured to:- collect (410) monitoring measurements (140) at a monitoring location (166) of the compaction equipment (100) within the compaction site (10);- a compactor communication module (170) configured to:- transmit the monitoring measurements (140); and- receive a compaction assessment (77);a user interface module (180) configured to:- notify (460) a user (102) of the compaction equipment (100) of the compaction assessment (77); a compaction modeling module (2100) comprising:- a network interface module (2170) configured to:- receive the monitoring measurements (140) from the compactor communication module (170); and- transmit the compaction assessment (77) to the compactor communication module (170);- a storage system (2300) configured to:- store a scoring model (84); and- store a target baseline (54); and- a processor module (2120) configured to:- compute (420) a compaction value (60) from the monitoring measurements (140) using the scoring model (84);- compute (430) a target compaction threshold (56) from the monitoring measurements (140) using the target baseline (54); and- compute the compaction assessment (77) from the compaction value (60) and the target compaction threshold (56).

36. The system (2000) of claim 35, wherein the scoring model (84) is the predictive compaction model (82) from the method (300) of claim 8.

37. The system (2000) of claim 35 or claim 36, wherein the target baseline (54) is the predicted baseline (50) from the method (200) of claim 1 .

38. The system (2000) of any one of claims 35 to 37, wherein the target baseline (54) is computed by comparing the compaction value (60) to an average stiffness within the compaction site (10).

39. The system (2000) of any one of claims 35 to 38, wherein the measurement sensors (150) comprise at least one of a vibration sensor (151), location sensor (152), a moisture sensor (153), an infra-red sensor (154), a barometer sensor (155), a magnetometer sensor (156), a gyroscope sensor (157), and a camera (158) sensor, and wherein the monitoring measurements (140) comprise at least one of vibration measurement (141), a location measurement (142), a moisture measurement (143), a temperature measurement (144), a barometer measurement (145), a magnetometer measurement (146), a gyroscope measurement (147), and a camera measurement (148).

40. The system (2000) of any one of claims 35 to 39, wherein the processor module (2120) is further configured to compute an average compaction value from a plurality of discrete compaction values over an averaging distance, and wherein the compaction assessment (77) is computed from the average compaction value.41 . The system (2000) of claim 40, wherein the averaging distance is 1 meter.

42. The system (2000) of claim 40, wherein the averaging distance is configured according to at least one of a soil properties (44), an equipment dimension (108), and site characteristics (18).

43. The system (2000) of any one of claims 35 to 42, wherein the processor module (2120) is further configured to compute the compaction value (60) into a compaction value map (99) and the network interface module (2170) is further configured to communicate the compaction value map (99) to an approving engineer (104).

44. The system (2000) of claim 43, wherein the processor module (2120) is further configured to identify areas on the compaction value map (99) according to geotechnical rules.

45. The system (2000) of claim 44, wherein the geotechnical rules are evaluated using a geotechnical rule model trained with machine learning.

46. The system (2000) of claim 44 or claim 45, wherein the geotechnical rules comprise at least one of: identifying areas with the compaction value (60) below an acceptable threshold using an unacceptable identification scheme; identifying areas with the compaction value (60) between the acceptable threshold and an ideal threshold using an acceptable identification scheme; identifying areas with the compaction value (60) above the ideal threshold using an ideal identification scheme; identifying areas under-passed using an under-passed identification scheme; and identifying areas with an anomaly using an anomaly identification scheme.

47. The system (2000) of any one of claims 44 to 46, wherein the processor module (2120) is configured to identify areas on the compaction value map (99) according to the geotechnical rules after a previous iteration, and wherein communicating the compaction value map (99) comprises at least one of: identifying improving areas using an improving identification scheme, wherein the improving areas are identified based on a difference between the compaction value (60) and the compaction value (60) of the previous iteration; and identifying completed areas by using a completed identification scheme, wherein the completed areas are identified based on an expected number of pass being completed, a low difference between the compaction value (60) and the compaction value (60) of the previous iteration, and the compaction value (60) being above an ideal threshold.

48. The system (2000) of any one of claims 44 to 47, wherein the geotechnical rules comprise evaluating a lift thickness.

49. The system (2000) of any one of claims 35 to 48, wherein the processor module (2120) is further configured to isolate (470) a vibration influence from a subgrade (20), thereby improving vibration measurement of a fill material (30).

50. The system (2000) of any one of claims 35 to 49, wherein the network interface module (2170) is further configured to relay a remote compaction data from a second compaction equipment (101), thereby enabling a collaborative soil compaction.

51. A non-transitory computer-readable medium storing a set of instructions for modeling a compaction site (10), the set of instructions comprising: one or more instructions that, when executed by one or more processors of a device, cause the device to:- predict (250) a predicted baseline (50) from a predictive site model (80) and soil properties (44) of a sampling area (12) of the compaction site (10); and wherein the soil properties (44) are determined from soil samples (40) comprising a subgrade sample (22) from a subgrade (20) of the compaction site (10).

52. The non-transitory computer-readable medium of claim 51, wherein the one or more instructions, when predicting (250) the predicted baseline (50), further cause the device to: establish (240) a historical baseline (52), descriptive of an anticipated vibration data response, by comparing the soil properties (44) against historical data (46); and wherein the predicted baseline (50) is predicted (250) from the soil properties (44), the predictive site model (80), and the historical baseline (52).

53. The non-transitory computer-readable medium of claim 51 or claim 52, wherein the compaction site (10) is being filled with a fill material (30) and wherein the soil samples (40) further comprise fill sample (32) from a fill material (30).

54. The non-transitory computer-readable medium of any one of claims 51 to 53, wherein the one or more instructions further cause the device to: identify (210) a soil quantity, a compaction method, and a project scheduling; and wherein the soil samples (40) are collected in accordance with a sampling frequency and a sampling procedure based on the soil quantity, the compaction method and the project scheduling.

55. The non-transitory computer-readable medium of any one of claims 51 to 54, wherein the soil properties (44) comprise at least one of a gradation, a moisture and an Atterberg limit.

56. The non-transitory computer-readable medium of any one of claims 51 to 55, wherein the predictive site model (80) is configured from machine learning methods comprising at least one of a supervised learning method, an unsupervised learning method, a reinforcement learning method, a deep learning method, a neural network, a support vector machines, and a k-nearest neighbors.

57. The non-transitory computer-readable medium of any one of claims 51 to 56, wherein the predicted baseline (50) comprises an expected pass count.

58. A non-transitory computer-readable medium storing a set of instructions for planning a soil compaction of a compaction site (10), the set of instructions comprising: one or more instructions that, when executed by one or more processors of a device, cause the device to:- record site-specific compaction parameters (19) based on the compaction site (10);- record (330) a loose measurement map (90) indicative of a loose soil measurement (160) at a plurality of calibration locations (164) of a calibration area (14);- measure (340) a compaction score (94) of the calibration area (14) from results of one or more standard tests (96);- upon determination (350) that the compaction score (94) within the compaction target (16):- record (360) a compacted measurement map (98) indicative of a compacted soil measurement (162) at the plurality of calibration locations (164) of the calibration area (14); and- compute (370) a predictive compaction model (82) from the loose measurement map (90), the compacted measurement map (98) and the one or more standard tests (96), configured to predict a predicted compaction score (95) from a measurement.

59. The non-transitory computer-readable medium of claim 58, wherein the loose soil measurement (160) comprises at least one of vibration measurement (141), a location measurement (142), a moisture measurement (143), a temperature measurement (144), a barometer measurement (145), a magnetometer measurement (146), a gyroscope measurement (147), and a camera measurement (148).

60. The non-transitory computer-readable medium of claim 58 or claim 59, wherein the one or more standard tests (96) comprise at least one of a Proctor compaction test, a moisture content test, a field density test, a sand cone test, a plate load test, and a lightweight deflectometer test.

61. The non-transitory computer-readable medium of any one of claims 58 to 60, wherein the site-specific compaction parameters (19) comprise at least one of a lift thickness, a control strip size, and a moisture content.

62. The non-transitory computer-readable medium of any one of claims 58 to 61, wherein the predictive compaction model (82) is obtained from a machine learning method.

63. The non-transitory computer-readable medium of claim 62, wherein the machine learning method comprises at least one of a supervised learning method, unsupervised learning method, a reinforcement learning method, a deep learning, a neural network, a support vector machines, and a k-nearest neighbors.

64. A non-transitory computer-readable medium storing a set of instructions for monitoring a soil compaction of a compaction site (10) during the soil compaction, using a compaction equipment (100) equipped with measurement sensors (150), the set of instructions comprising: one or more instructions that, when executed by one or more processors of a device, cause the device to:- collect (410) a monitoring measurement (140) at a monitoring location (166) of the compaction equipment (100) within the compaction site (10);- compute (420) a compaction value (60) from the monitoring measurement (140) using a scoring model (84);- compute (430) a target compaction threshold (56) from the monitoring measurement (140) using a target baseline (54); and- upon detecting (440) that the compaction value (60) is within (444) the target compaction threshold (56):- notify (460) a user (102) of the compaction equipment (100) of a soil compaction achievement at the monitoring location (166).

65. The non-transitory computer-readable medium of claim 64, wherein the scoring model (84) is the predictive compaction model (82) from the non-transitory computer-readable medium of claim 58.

66. The non-transitory computer-readable medium of claim 64 or claim 65, wherein the target baseline (54) is the predicted baseline (50) from the non-transitory computer-readable medium of claim 51 .

67. The non-transitory computer-readable medium of any one of claims 64 to 66, wherein the target baseline (54) is computed by comparing the compaction value (60) to an average stiffness within the compaction site (10).

68. The non-transitory computer-readable medium of any one of claims 64 to 67, wherein the one or more instructions further cause the device to: upon detecting (440) that the compaction value (60) is outside (442) of the target compaction threshold (56):- notify (450) the user (102) of the compaction equipment (100) of further remedial steps required at the monitoring location (166).

69. The non-transitory computer-readable medium of any one of claims 64 to 68, wherein the monitoring measurement (140) comprises at least one of vibration measurement (141), a location measurement (142), a moisture measurement (143), a temperature measurement (144), a barometer measurement (145), a magnetometer measurement (146), a gyroscope measurement (147), and a camera measurement (148).

70. The non-transitory computer-readable medium of any one of claims 64 to 69, wherein the compaction value (60) is averaged over an averaging distance.71 . The non-transitory computer-readable medium of claim 70, wherein the averaging distance is 1 meter.

72. The non-transitory computer-readable medium of claim 70, wherein the averaging distance is configured according to at least one of a soil properties (44), a roller dimension, and a site characteristic.

73. The non-transitory computer-readable medium of any one of claims 64 to 72, wherein the one or more instructions further cause the device to: record the compaction value (60) into a compaction value map (99); and upon a completion of the soil compaction:- communicate the compaction value map (99) to an approving engineer (104).

74. The non-transitory computer-readable medium of claim 73, wherein the one or more instructions, when communicating the compaction value map (99), cause the device to: identify potential non-homogeneous areas using a potential non-homogeneous area identification scheme; identify potential moisture variation areas using a potential moisture variation identification scheme; and identify potential weak spot areas using a potential weak spot identification scheme.

75. The non-transitory computer-readable medium of claim 73, wherein the one or more instructions, when communicating the compaction value map (99), cause the device to: identify areas on the compaction value map (99) according to geotechnical rules.

76. The non-transitory computer-readable medium of claim 75, wherein the geotechnical rules are evaluated using a geotechnical rule model trained with machine learning.

77. The non-transitory computer-readable medium of claim 75 or claim 76, wherein the geotechnical rules comprise at least one of: identifying areas with the compaction value (60) below an acceptable threshold using an unacceptable identification scheme; identifying areas with the compaction value (60) between the acceptable threshold and an ideal threshold using an acceptable identification scheme; identifying areas with the compaction value (60) above the ideal threshold using an ideal identification scheme; identifying areas under-passed using an under-passed identification scheme; and identifying areas with an anomaly using an anomaly identification scheme.

78. The non-transitory computer-readable medium of any one of claims 75 to 77, wherein the one or more instructions further cause the device to:when communicating the compaction value map (99) is performed after a previous iteration:- identify improving areas using an improving identification scheme, wherein the improving areas are identified based on a difference between the compaction value (60) and the compaction value (60) of the previous iteration; and- identify completed areas by using a completed identification scheme, wherein the completed areas are identified based on an expected number of pass being completed, a low difference between the compaction value (60) and the compaction value (60) of the previous iteration, and the compaction value (60) being above an ideal threshold.

79. The non-transitory computer-readable medium of any one of claims 75 to 78, wherein the geotechnical rules comprise evaluating a lift thickness.

80. The non-transitory computer-readable medium of any one of claims 64 to 79, wherein the one or more instructions further cause the device to: isolate (470) a subgrade vibration influence from the monitoring measurement (140), thereby improving the compaction value (60) of a fill material (30).81 . The non-transitory computer-readable medium of claim 80, wherein the subgrade vibration influence is estimated from a calibration area (14).

82. The non-transitory computer-readable medium of any one of claims 64 to 81 , wherein the one or more instructions further cause the device to: receive (480) a remote compaction data from a second compaction equipment (101), thereby enabling a collaborative soil compaction on a plurality of subareas (11) of the compaction site (10).

83. The non-transitory computer-readable medium of claim 82, wherein the plurality of subareas (11) is assigned to the compaction equipment (100) based on at least one of a current location of the compaction equipment (100), the remote compaction data, the target compaction threshold (56), the target baseline (54), a scheduling constraint, a refueling need, a maintenance need, an observed compaction rate, an availability of equipment and a planned activity on the plurality of subareas (11).

Images