Systems and methods for compounding or evaluating construction admixtures - Patents.com

Abstract

Exemplary embodiments provide systems and methods for compounding and evaluating construction admixtures (such as admixtures for concrete, asphalt, mortar, etc.). According to exemplary embodiments, a predictive model, artificial intelligence, machine learning algorithm, etc. may be trained using historical performance data and current deployment information. Based on a construction specification that identifies various requirements for the construction composition and a set of available inputs (e.g., raw materials, mixing techniques, etc.), the model, AI, or algorithm may output one or more construction admixtures that meet or most closely approximate the requirements. The construction admixtures may be submitted to a simulation to estimate or predict their performance. The performance characteristics of the output construction admixtures may be displayed. Optionally, the system may control mixing machinery to produce the construction admixtures.

Description

[Technical field]

[0001] This application relates to improvements in the production of construction and engineering mixtures such as asphalt, concrete, mortar, and the like. [Background technology]

[0002] Certain materials used in construction and engineering are compositions of raw materials that are blended together to achieve desired properties. Typically, a construction composition comprises a construction mix, which is comprised of construction mix raw materials. Such a construction mix may be produced in a factory and includes all materials of the composition except for the construction admixtures, which represent the chemical additives used in the production of the combined construction composition. The construction admixtures are comprised of the construction admixture raw materials.

[0003] While the layman may conceptually envision a certain construction composition (e.g., "concrete"), in practice there are many different methods for formulating such construction compositions. For example, the types and amounts of construction mixture and admixture raw materials may be varied, the construction composition raw materials may be mixed to different degrees using different methods, more or less water may be used, etc. Different formulations may result in different properties that may be desirable in different situations.

[0004] In one example, a first construction team may require a relatively quick setting concrete, while a second team may require more time to lay the concrete. Setting times can be varied by using different amounts of moisture, different amounts of cement, different amounts of complementary cementing materials, different cement fineness, etc.

[0005] Construction compositions can vary for other reasons as well. It is often impractical to produce all of the construction compositions required for a large-scale construction project at a single location (e.g., a single concrete plant). Instead, many different plants may contribute to the project, with each plant shipping several batches at different times over the course of the project. Different construction mix raw materials with different properties (e.g., larger or smaller aggregate size) may be available at the different plants, resulting in low consistency among the construction compositions deployed at the construction site.

[0006] Furthermore, the ambient conditions at each factory may be different and may vary over time. The route from the factory to the building site may vary in driving time or distance, and different drivers may take different routes from the same factory. The expertise of the workers at each factory may also vary. It is therefore understood that only some of the conditions that affect the properties of the building composition are within the control of the producer.

[0007] For these and other reasons, different batches of construction compositions delivered to a work site may vary significantly. However, it is unacceptable that any of the construction compositions fail to meet the prescribed engineering requirements. If a certain minimum compressive or tensile strength is required, the factory producing the construction composition cannot select a combination of raw materials and / or techniques that results in less than the required strength. If it does, the structure being built may collapse.

[0008] Because of these considerations, construction compositions produced today tend to be over-engineered. In other words, various methods of adjusting the properties of the construction composition are selected so that the resulting construction composition has properties that exceed (sometimes significantly) the engineering requirements of the construction composition. This costs the producer (and thus the contractor, developer, and end user of the constructed structure) money and time, and unnecessarily wastes raw materials. Industry experts estimate that 80% of the concrete mixes produced today suffer from this problem.

[0009] Nevertheless, the goal of contractors using construction compositions is to achieve consistency between similar batches in terms of the performance of the construction composition, not necessarily in terms of the raw materials or mixing techniques used. For example, contractors are more likely to be concerned that each batch has a consistent set time, which may be achieved by adjusting the moisture content of the mix, by changing the percentage of complementary cementing materials, or by waiting to develop the mix until the desired ambient temperature is achieved. The particular method of achieving the desired set time is of less concern, so long as other properties of the construction composition (e.g., strength, aesthetic quality, slump, etc.) are not adversely affected.

[0010] Thus, some degree of variation in the raw materials or mixing techniques of each batch of construction compositions may be tolerated as long as the performance of each batch is consistent and meets the engineering requirements. This provides an opportunity to reduce costs and the amount of construction composition raw materials used to produce such construction compositions. Unfortunately, even the most advanced experts are unable to take into account the variety of available inputs, the rapidly changing conditions at the factory and construction site, and other factors that may affect the performance of the construction mix. Thus, these construction compositions continue to be unnecessarily over-engineered.

[0011] Furthermore, in some circumstances, the base construction mixture may be supplemented with additional materials, collectively sometimes referred to as construction admixtures, each of which may be selected to impart specific performance characteristics to the finished combination. Summary of the Invention [Means for solving the problem]

[0012] The invention includes a non-transitory computer readable medium storing instructions that, when executed by one or more processors, cause the one or more processors to receive a construction specification for a construction composition, the composition comprising a construction mixture and a construction admixture configured to be added to the construction mixture to alter one or more properties of the construction composition, the construction specification defining one or more performance requirements for the construction composition and accessing a set of inputs that affect one or more properties of the construction composition, providing the construction specification and a set of components to a predictive model, and using the predictive model to programmatically determine at least one construction admixture that meets or approximates the performance requirements of the construction specification, the construction admixture comprising a plurality of components mixed in a determined ratio, and outputting the at least one determined construction admixture.

[0013] The invention further includes any of the media described herein further storing instructions for producing the determined construction admixture, wherein producing includes adding a plurality of components for the construction admixture to a construction mix, producing a construction composition, and having the construction composition shipped to the construction site, producing the determined construction admixture separately from the construction mix, and having the determined construction admixture shipped to the construction site, or bundling the components for the construction admixture and having the components shipped to the construction site.

[0014] The invention further includes any of the media described herein, wherein the construction admixture is selected from the group of an asphalt admixture, a concrete admixture, a grout admixture, or a mortar admixture.

[0015] The invention further includes any of the media described herein, wherein the construction specification comprises one or more of the plastic or hardening properties of the construction composition.

[0016] The invention further includes any of the media described herein further storing instructions for receiving a priority for one or more of the performance requirements and taking the priority into account.

[0017] The invention further includes any of the media described herein, wherein the set of inputs comprises one or more of previous construction composition performance, factory specific construction composition performance, available materials, real-time sensor readings, ambient environmental conditions, job specific information, or contractor requirements.

[0018] The invention further includes any of the media described herein further storing instructions for outputting a plurality of construction admixtures that approximate the performance requirements of the construction specification, performing a simulation on each of the plurality of construction admixtures, predicting an expected performance of each individual construction admixture, and outputting the expected performance of each individual construction admixture.

[0019] The invention further includes any of the media described herein further storing instructions for selecting one or more performance characteristics with respect to which the plurality of construction admixtures differ, the one or more performance characteristics not specified as part of the construction specification, and outputting a comparison of the plurality of construction admixtures based on the selected performance characteristics.

[0020] The invention further includes any of the media described herein further storing instructions for receiving a notification that the set of inputs has changed and re-optimizing the determined construction admixture based on the notification.

[0021] The invention further includes any of the media described herein where the modified input comprises a different set of available raw materials and components than were available when the construction admixture was originally determined.

[0022] The present invention further includes a computer-implemented method comprising the steps of receiving a construction specification for a construction composition, the construction composition comprising a construction mixture and a construction admixture, the construction specification defining one or more properties for the construction composition, the construction admixture representing one or more components configured to be added to the construction mixture before the construction composition is applied at a construction site; accessing a component library comprising a plurality of components, each component providing a desired functional property to the construction mixture or the construction admixture; applying artificial intelligence to the component library based on the construction specification to select a combination of components that results in a determined construction admixture to be implemented for the construction specification; and outputting the determined construction admixture.

[0023] The invention further includes any of the methods described herein wherein the component library comprises a subset of a larger library.

[0024] The invention further includes any of the methods described herein wherein the components are divided into categories, the categories comprising one or more of dispersants, caking modifiers, air control agents, strength enhancers, workability retention agents, and rheology modifiers.

[0025] The invention further includes any of the methods described herein further comprising identifying, for one or more of the components, at least one of the following properties: operating range, side effects, positive interactions, or negative interactions.

[0026] The present invention further includes any of the methods described herein further comprising adjusting component ratios or amounts of construction admixture in real time based on changing conditions at the user site.

[0027] The invention further includes an apparatus comprising: a non-transitory computer readable storage medium storing logic for a machine learning algorithm configured to select an additive combination of raw materials and components configured to be added to a predefined building composition; a hardware interface configured to receive training data, the training data comprising a first building composition and associated performance characteristics for the first building composition; and a hardware processor circuit configured to train the machine learning algorithm based on the training data, receive via the interface one or more performance requirements for a new building composition, and use the machine learning algorithm to select a new additive combination of raw materials and components based on the received performance requirements, the new building composition being output using the interface.

[0028] The invention further includes any of the apparatus described herein, wherein the machine learning algorithm is configured to prioritize performance factors over cost factors.

[0029] The invention further includes any of the devices described herein, wherein the processor is further configured to receive a report of the performance of the new construction composition and retrain the machine learning algorithm based on the performance of the new construction composition.

[0030] The invention further includes any of the devices described herein, wherein the performance requirements include one or more of processability, pumpability, and workability.

[0031] The invention further includes any of the devices described herein, where the machine learning algorithm adapts one or more of ambient conditions, delivery distance, delivery time, pouring method, or contractor staffing. The present invention provides, for example, the following: (Item 1) A non-transitory computer readable medium having instructions stored thereon that, when executed by one or more processors, cause the one or more processors to: receiving a construction specification for a construction composition, the composition comprising a construction mixture and a construction admixture configured to be added to the construction mixture and modify one or more properties of the construction composition, the construction specification defining one or more performance requirements for the construction composition; accessing a set of inputs that affect one or more properties of the construction composition; providing the construction specification and set of components to a predictive model; programmatically determining, using the predictive model, at least one construction admixture that meets or approximates a performance requirement of the construction specification, the construction admixture comprising a plurality of components mixed in a determined ratio; and outputting said at least one determined construction admixture; and A non-transitory computer readable medium for causing (Item 2) and further storing instructions for producing the determined construction admixture, the production comprising: adding a plurality of components for said construction admixture to said construction mixture, producing said construction composition, and shipping said construction composition to a construction site; producing said determined construction admixture separately from said construction mixture and causing said determined construction admixture to be shipped to said construction site; or Assembling components for said construction admixture and shipping said components to said construction site. The medium according to item 1, comprising: (Item 3) 2. The medium of claim 1, wherein the construction admixture is selected from the group of asphalt admixtures, concrete admixtures, grout admixtures, or mortar admixtures. (Item 4) 2. The medium of claim 1, wherein the construction specifications comprise one or more of the plasticity or hardening properties of the construction composition. (Item 5) 2. The medium of claim 1, further storing instructions for receiving a priority for one or more of the performance requirements and taking the priority into account. (Item 6) 2. The medium of claim 1, wherein the set of inputs comprises one or more of previous construction composition performance, factory specific construction composition performance, available materials, real-time sensor readings, ambient environmental conditions, job specific information, or contractor requirements. (Item 7) outputting a plurality of construction admixtures that approximate the performance requirements of the construction specification; performing a simulation for each of the plurality of construction admixtures to predict expected performance of each individual construction admixture; Outputting the expected performance of each individual construction admixture; 2. The medium of claim 1, further storing instructions for performing the steps of: (Item 8) 8. The medium of claim 7, further storing instructions for: selecting one or more performance characteristics with respect to which the plurality of construction admixtures differ, the one or more performance characteristics not specified as part of the construction specification; and outputting a comparison of the plurality of construction admixtures based on the selected performance characteristics. (Item 9) receiving a notification that the set of inputs has changed; re-optimizing the determined construction admixture based on the notification; and 2. The medium of claim 1, further storing instructions for performing the steps of: (Item 10) 10. The medium of claim 9, wherein the modified input comprises a different set of available materials than were available when the construction admixture was originally determined. (Item 11) 1. A computer-implemented method, comprising: receiving a construction specification for a construction composition, the construction composition comprising a construction mixture and a construction admixture, the construction specification defining one or more properties for the construction composition, the construction admixture representing one or more components configured to be added to the construction mixture before the construction composition is applied at a construction site; accessing a component library comprising a plurality of components, each component providing a desired functional property to said construction mixture or construction admixture; applying artificial intelligence to the component library based on the construction specification to select a combination of components that results in a determined construction admixture to be implemented for the construction specification; outputting the determined construction admixture; A method comprising: (Item 12) Item 12. The method of item 11, wherein the component library comprises a subset of a larger library. (Item 13) 12. The method of claim 11, wherein the components are divided into categories, the categories comprising one or more of dispersants, caking modifiers, air control agents, strength enhancers, workability retention agents, and rheology modifiers. (Item 14) With respect to one or more of the above components, the following properties are met: Operating range, Side effects, Positive interactions, or Negative interactions, Item 12. The method of item 11, further comprising identifying at least one of: (Item 15) 12. The method of claim 11, further comprising adjusting the ratios of components or amounts of construction admixture in real time based on changing conditions at the user site. (Item 16) An apparatus comprising: a non-transitory computer readable storage medium storing logic for a machine learning algorithm configured to select additive combinations of raw materials and components configured to be added to a predefined building composition; a hardware interface configured to receive training data, the training data comprising a first building composition and associated performance characteristics related to the first building composition; A hardware processor circuit, the hardware processor circuit comprising: training the machine learning algorithm based on the training data; receiving, via the interface, one or more performance requirements for a new construction composition; using the machine learning algorithm to select new additive combinations of raw materials and components based on the received performance requirements; configured to: a hardware processor circuit, the new building composition being output using the interface; An apparatus comprising: (Item 17) Item 17. The apparatus of item 16, wherein the machine learning algorithm is configured to prioritize performance factors over cost factors. (Item 18) The processor further comprises: receiving a report of the performance of the new construction composition; retraining the machine learning algorithm based on the performance of the new building composition; Item 17. The apparatus of item 16, configured to perform the steps of: (Item 19) Item 17. The apparatus of item 16, wherein the performance requirements comprise one or more of processability, pumpability, and workability. (Item 20) 20. The apparatus of claim 16, wherein the machine learning algorithm adapts to one or more of ambient conditions, delivery distance, delivery time, pouring method, or contractor staffing. [Brief description of the drawings]

[0032] [Figure 1] FIG. 1 depicts a suitable environment for use with the illustrative embodiments.

[0033] [Diagram 2] FIG. 2 depicts an exemplary data structure suitable for use with the exemplary embodiment as a construction specification.

[0034] [Figure 3A] FIG. 3A depicts an example mapping of modifiable parameters and sources of requirements and construction composition properties that are defined by the requirements or that can be affected by adjustments to the parameters.

[0035] [Figure 3B] FIG. 3B depicts a mapping of exemplary desired performance parameters and corresponding properties of a construction composition.

[0036] [Figure 3C] FIG. 3C depicts an example mapping of modifiable variables and construction composition properties that are affected by changes in the modifiable variables.

[0037] [Figure 4] FIG. 4 is an exemplary input / output specification depicting the inputs to the optimization logic and the corresponding outputs generated by the optimization logic.

[0038] [Diagram 5] FIG. 5 is a block diagram depicting various hardware and digital components of devices in the environment of FIG. 1 in accordance with an exemplary embodiment.

[0039] [Figure 6A] FIG. 6A is a data flow diagram illustrating an exemplary exchange of information between digital components of an environment.

[0040] [Figure 6B] FIG. 6B is a flowchart illustrating significant operations in accordance with an exemplary embodiment.

[0041] [Figure 7] FIG. 7 depicts an exemplary computing system suitable for use with the exemplary embodiments.

[0042] [Figure 8] FIG. 8 depicts an exemplary network environment suitable for use with the exemplary embodiments. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0043] As explained above, formulating a construction composition to meet all the various requirements of an engineering project while considering other variables that may affect the availability or performance of the construction composition raw materials can be difficult. Developing an optimal set of construction composition raw material proportions for a given project requires a high level of familiarity with the properties of the materials being designed, translation of the project needs and details into a set of preferred properties, and familiarity with the raw materials available on-site.

[0044] Traditionally, one solution has been to develop a small number of building compositions with known performance ranges and choose from among the limited number of options available. However, this approach has several limitations. First, the building composition may not be optimally formulated for the conditions that will be present at the work site. Second, the building composition raw materials used in the original formulation may not be available to a particular producer, which would require the producer to either use a different building composition or modify the building composition, resulting in unknown or unpredictable results. Third, because a producer can only choose from a limited number of options to meet all of its engineering requirements, these formulations may be designed to exceed various requirements, some of which may not apply to a particular business plan, which leads to the "over-optimization" problem discussed above.

[0045] Another possibility would be to initiate an extensive experimental process, generate several construction compositions, deploy them in conditions similar to those that will be encountered at the intended construction site, cure them, and measure their properties. This would tend to be prohibitive in terms of time and cost. Moreover, the expertise required to develop and evaluate such a program may not be available at every production facility. Still further, such a procedure would not take into account changing conditions or performance validation as the compositions are deployed throughout the actual project.

[0046] With either option, it is difficult or impossible to achieve an optimal construction composition because every possible construction composition cannot possibly be produced and tested. Furthermore, these procedures tend to focus on the performance of the construction composition without considering the cost of the construction composition.

[0047] The use of construction admixtures offers advantages in terms of the ability to fine-tune the performance characteristics of the construction composition and are typically added to the construction mix at the production site, which can make it difficult to quickly account for changing conditions or variability observed in the combined construction composition.

[0048] Exemplary embodiments address these and other problems by providing techniques for compounding and evaluating construction admixtures (such as construction admixtures for concrete, asphalt, mortar, etc.). According to exemplary embodiments, predictive models, artificial intelligence, machine learning algorithms, etc. may be trained using historical performance data (which may be supplemented with recent data and performance evaluations on currently deployed concrete).

[0049] Once the model, AI, or algorithm is trained, a data structure may be received that represents a construction specification. The structure may include various requirements for the construction composition (i.e., both the base construction mixture and the construction admixtures), which may be optionally prioritized. Additionally, a set of available inputs (e.g., raw materials, mixing techniques, etc.) may be accessed. These inputs may be provided to the model, AI, or algorithm, which may output one or more combinations that meet or most closely approximate the requirements. The output may specify a list of raw materials that make up the construction mixture, the amounts or ratios of the raw materials, the amounts or ratios of the construction admixture components, and any mixing techniques to be used to mix and produce the construction composition.

[0050] As part of a model, AI, or algorithm, or separately therefrom, the formulation may be provided to a simulation to estimate or predict its performance (at the time of deployment and / or over time thereafter).

[0051] Based on the output of the AI, model, or algorithm (potentially supplemented by simulation data), the performance characteristics of the output construction compositions may be displayed. In some embodiments, only those characteristics that vary from composition to composition may be displayed. In some embodiments, parameters that are not specified by the original construction specifications but vary between compositions may be displayed. In addition to performance, the cost of the composition may also be estimated. In some embodiments, the compositions may be ranked by performance, cost, or a weighted combination of performance and cost (among other possibilities).

[0052] A user may select one of the construction compositions for use in the project. In some embodiments, the optimal construction composition may be automatically selected (based on a weighted combination of performance and / or cost). Optionally, the system may control mixing machinery to produce the construction composition (e.g., by transmitting instructions configured to cause the mixing machinery to obtain and mix raw materials in a prescribed amount or ratio for the construction composition). In some embodiments, the base construction mixture and the construction admixtures may be produced separately at a production facility (e.g., a concrete plant) and shipped separately to the construction site. At the construction site, the base construction mixture and the construction admixtures may be combined as desired. This embodiment allows the contractor to use more or less construction admixture depending on the site conditions and the observed performance of the combined construction composition (e.g., from a previous mixed batch). In a further embodiment, the base construction mixture may be produced at a production facility and shipped to the work site, and the components for the (separate) construction admixture may be shipped to the work site in uncombined form. This allows the composition of the construction admixture to be varied from batch to batch so that the individual performance properties associated with each component of the construction admixture can be more finely controlled.

[0053] In some embodiments, AI / models / ML algorithms and / or simulations may be deployed to evaluate the proposed construction composition (rather than proposing its own construction composition). The properties or estimated performance of the proposed construction composition may be displayed, and if deemed acceptable, the system may control the mixing machinery to produce the construction composition (and / or construction mixture and / or construction admixture).

[0054] These embodiments offer several advantages over the proposed conventional solutions described above.

[0055] First, the exemplary system significantly reduces or eliminates the number of experiments that need to be performed on a given mixture or set of construction compositions because the AI / model / algorithm may eliminate construction compositions that are unlikely to meet the construction requirements, and further, the use of simulation substitutes for or complements experimentation.

[0056] Second, the exemplary embodiments are better able to arrive at an optimized set of construction mix proportions because more variables can be considered in the process of designing the construction composition. Furthermore, different parameters can be weighted relative to one another so that improved combinations or synergies can be identified. Because cost can be considered as a factor, the resulting solutions may be less expensive and less subject to over-engineering.

[0057] Third, the exemplary embodiments allow for rapid optimization of the building composition for multiple different performance desires. The impact of changing the building composition can be quickly evaluated across multiple different performance variables, whereas evaluating these tradeoffs in conventional scenarios would typically require multiple experiments over a significant period of time.

[0058] Fourth, existing construction mixes can be rapidly re-optimized based on changing conditions (e.g., different available construction mix raw materials, changing conditions at the site or en route to the site, etc.) This allows for improved quality control and a more consistent product compared to traditional methods.

[0059] Fifth, because the construction admixture can be configured to be mixed and / or added at the point of deployment or at the production site, variability between different batches can be significantly reduced.

[0060] The following description of the embodiments provides non-limiting representative examples, particularly with reference to numbers to illustrate the features and teachings of different aspects of the present invention. It should be recognized that the described embodiments can be implemented separately or in combination with other embodiments from the description of the embodiments. The description of the embodiments is not specifically exhaustive, but should facilitate understanding of the present invention to the extent that other implementations within the knowledge of a person skilled in the art who has perused the description of the embodiments will be understood to be consistent with the application of the present invention.

[0061] It should be noted that, although the exemplary embodiments are described in relation to specific examples (construction compositions, in particular construction mixtures and construction admixtures), the invention is not limited to these examples.

[0062] FIG. 1 illustrates a building composition environment 100, according to an example embodiment.

[0063] At a high level, the building composition production process begins with a group 102 of engineers, architects, technical experts, etc. The experts 102 set the required parameters for the mix in the form of technical requirements 104. For example, in the case of concrete, an architect may require certain aesthetic properties for the finished concrete (color, texture, etc.). An engineer may evaluate the structural plan, applicable building codes, etc., and specify requirements in terms of strength, durability, stability, etc. A technical expert (e.g., an expert in rolling concrete) may specify required properties related to the behavior of the building composition as it is rolled out, such as workability, setting time, and viscosity.

[0064] The technical requirements 104 may be implemented in a building composition plant 108. The building composition plant 108 may include a raw material silo 110 that stores raw materials that may be combined to form a building mix. Examples of raw materials include cement, coarse and fine aggregates, and complementary cementing materials (SCMs). The raw materials may also include moisture.

[0065] In some embodiments, the construction mixture used in the construction composition may be supplemented with additional materials. For example, concrete (an example of a construction composition 118) is generally formed from a main general construction mixture 114 and construction admixtures 116 that modify various properties of the finished concrete. The construction admixtures 116 may include, for example, dispersants, setting modifiers (e.g., retarders and accelerators), air control agents (e.g., air entrainment and de-entrainment agents), strength modifiers, workability retention modifiers, and rheology modifiers. These materials may also be present in the silo 110, either individually or in combination.

[0066] The raw materials from the silo 110 may be mixed in a mixing facility 112. The mixing facility 112 may include mixing machinery controllable by a computer controller and may produce a building mixture 114, a construction admixture 116, and / or a finished building composition 118.

[0067] Once mixed, the finished building composition 118 may be loaded into a vehicle 126, such as a concrete truck. The vehicle 126 may transport the building composition 118 via a route 128 to a work site 130 where the building composition 118 will be spread. Different building composition plants 108 will necessarily need to use different routes 128 to the work site 130. Furthermore, different vehicles 126 may follow different routes 128 from a single building composition plant 108 to a single work site 130.

[0068] The work site 130 may be overseen by a contractor 132. The contractor 132 may be responsible for ensuring that each batch of building composition 118 delivered from each building composition plant 108 is of consistent quality and meets the requirements of the work. If the contractor 132 determines that a particular batch does not meet its specifications or is defective in any way, the contractor 132 may reject the batch and return it to the building composition plant 108.

[0069] The illustrative embodiments improve the building composition production process by deploying resources at locations throughout the environment 100 .

[0070] For example, a producer server 106 may be provided with a building composition plant 108. The producer server 106 may host optimization logic 122 for optimizing the building mixture 114, the building admixture 116, and / or the final building composition 118. The optimization logic 122 may be capable of selecting different available raw materials from the raw material silos 110 and defining their amounts or relative proportions, percentages, or ratios. The available materials may be represented in a component library 124, which may identify the material and may include further information about the material, such as the impact of the material on performance parameters, any certification that the component meets the concentrations of the material, etc.

[0071] The optimization logic 122 may include artificial intelligence, machine learning algorithms (e.g., neural networks, supervised learning processes, unsupervised learning processes, reinforcement learning processes, etc.), predictive models, etc. The optimization logic 122 may be trained using labeled training data, which may include historical or current data. The training data may identify ingredients of the construction composition and measured properties of the composition. Given sufficient training data, the optimization logic 122 may learn how various raw materials and components can be blended together to achieve target performance parameters.

[0072] To identify a construction composition that meets the technical requirements 104, the producer server 106 may access a construction specification 120, which may be a data structure that formulates the technical requirements 104 and represents them in a way that the optimization logic 122 can process.

[0073] The optimization logic 122 may be applied at the front end to identify the initial construction mixture 114 or construction admixture 116. The optimization logic 122 may also, or alternatively, be applied at the back end (after the construction composition 118 is produced) to modify the construction mixture 114 or construction admixture 116 in real time between successive batches of the construction composition. To this end, sensors may be deployed on the vehicle 126, along the route 128, or at the work site 130, among other possibilities. The sensors may generate sensor data 136, which may be provided to the producer server 106. The sensors may include, for example, an accelerometer (e.g., to measure the ruggedness of the route 128), a thermometer (to measure the ambient temperature), a barometer, a hygrometer, etc. The sensor data 136 may be fed to the optimization logic 122, which may adjust the materials to be used in the next batch of construction admixture 116 to be used (for example). Similarly, the contractor 138 may manually input information about the work site 130 conditions or the delivered building composition 118 (e.g., "set time too short," "viscosity too high," etc.). This information may also be provided to the optimization logic 122 via the contractor server 134 so that the building mix or admixture may be modified to take into account the contractor's feedback.

[0074] The construction specifications 120, optimization logic 122, and component library 124 may also, or alternatively, be hosted on a contractor server 134, allowing the contractor server 134 to make modifications to the construction admixture 116. In this embodiment, sensor data 136 and manual inputs 138 may be received and taken into account by the contractor server 134.

[0075] 2 depicts an example of a data structure representing a construction specification 120. Although the example construction specification 120 includes specific variables in a particular order, one skilled in the art will recognize that more, fewer, or different variables may be used depending on the application. If a value is not specified for a variable, a default value (e.g., a predefined minimum value, average value, etc.) may be used. Values ​​for variables may be expressed qualitatively, quantitatively, or both.

[0076] Values ​​may be specified as minimum or maximum values, a range of acceptable values, etc. Values ​​may be associated with a weighting or priority that indicates the importance of a particular performance characteristic relative to other performance characteristics. The weighting or priority may be zero, indicating that the performance characteristic is not important or should not be prioritized.

[0077] The construction specification 120 may define parameters related to fresh properties 202 of the construction composition. Fresh properties refer to properties of the fresh (i.e., unhardened) construction composition. Examples of fresh properties include workability 204, workability retention 206, air content 208, stability 210, uniformity 212, viscosity 214, workability 216, and set time 218.

[0078] The construction specification 120 may further define requirements for the strength 220 of the construction composition. The strength of the construction composition may be measured in a variety of ways, and separate parameters may be provided for (for example) compressive strength 222, flexural strength 224, and tensile strength 226.

[0079] The construction specification 120 may define quantitative or qualitative measurements regarding the appearance 228 of the building composition. The appearance 228 may define characteristics such as the color or texture of the finished building composition.

[0080] The construction specification 120 may further define cost or economic parameters 230. The cost or economics 230 may be defined by the cost of raw materials and may optionally take into account transportation costs, spreading costs, mixing costs, or other costs that affect the value of the building composition.

[0081] The construction specification 120 may define durability characteristics 232. Examples of durability characteristics 232 include freeze or thaw resistance 234, scaling 236, chemical attack 238, abrasion 240, or shrinkage 242.

[0082] The construction specification 120 may further define slab-on-grade properties and use activity 244. Examples of such activity may describe ease of constructability or effort 246, timing 248 (such as the amount of time for the product to cure or harden), and owner value 250.

[0083] To aid the optimization logic 122, a mapping may be provided from requirements or performance characteristics to variables that affect those requirements or performance characteristics. The variables may include variables that can be directly influenced by the producer (such as the amount of aggregate or moisture used, or the route used by the means of transportation) and variables that are not under the direct control of the producer (such as ambient weather conditions or statutory requirements) but must nevertheless be considered in determining the expected performance of the mix. FIG. 3A depicts an example mapping of modifiable parameters and sources of requirements and construction mix properties that are defined by the requirements or that can be influenced by adjustments to the parameters. Additionally, in some cases, performance requirements (such as workability or crack resistance) may be indirectly influenced by components under the producer's control.

[0084] As described above, the raw materials for the construction mixture and / or construction admixture may be selected from the component library 124. In this example, the components are divided into categories such as dispersants, set modifiers, air control agents, etc., as described in further detail in Tables 1 and 2.

[0085] FIG. 4 is an exemplary input / output specification depicting the inputs to the optimization logic 122 and the corresponding outputs generated by the optimization logic 122 .

[0086] As described above, the optimization logic 122 may take into account the construction specification 120. The optimization logic 122 may further take into account available materials 402 (or construction mixtures, construction admixtures, or combinations of construction mixtures and construction admixtures) that may be used to generate a finished construction composition. The available materials 402 may include raw materials 404 (e.g., available materials in a raw material silo), available pre-mixed construction admixtures 406, and / or construction admixtures 408 that may be newly generated using the available compositions. The components used to generate the new construction admixtures 408 may be specified in a component library 410, which specifies the construction admixture components available for the construction admixtures 408, and any properties of the finished product that may be affected by the inclusion of the construction admixture components. A library similar to 410 may be provided for the raw materials 404 used to create the initial construction mix.

[0087] The optimization logic 122 may select from among the available materials 402 and / or make adjustments to the materials based on a construction mixture / admixture / composition mapping 412, such as the mappings depicted in Figures 3A-3C. The mapping may define the degree to which adjusting one or more adjustable variables (e.g., the amount of available material 402) affects a performance parameter (e.g., a parameter defined in the construction specification 120).

[0088] The optimization logic 122 may take into account real-time sensor data 414 and / or contractor inputs 416. The sensor data 414 and / or contractor inputs 416 may be viewed as influencing the performance parameters a priori. In other words, the real-time sensor data 414 and contractor inputs 416 may prescribe values ​​for variables that may be viewed as assumptions (which may be non-adjustable), and values ​​for available materials 402 may be optimized with respect to the a priori data.

[0089] Based on the inputs to the optimization logic 122, the optimization logic 122 may output a construction mix formulation 418. The construction mix formulation may include identifiers for raw materials 420 to be included in the formulation, ratios / amounts / percentages 422 for each raw material 420, and any applicable mixing techniques 424 or requirements. Based on this information, the optimization logic 122 may optionally generate instructions for a mixing equipment (and / or a raw material inventory so that raw materials may be manually obtained and then provided to the mixing equipment) so that the identified construction mix can be automatically produced by the mixing equipment.

[0090] The optimization logic 122 may output a single construction composition formulation 418 that represents the formulation that best meets the requirements of the construction specification 120 given the available raw materials 402, real-time sensor data 414, and / or contractor input 416. Alternatively, the optimization logic 122 may output multiple candidate construction admixtures 418 that balance the requirements in different ways.

[0091] In some embodiments, the building mixtures and building admixtures 418 may achieve similar results with respect to different costs, which may be flagged in a display summarizing the various compositions. In some embodiments, the performance of the building compositions (base building mixtures and building admixtures) may be prioritized over the cost of the building compositions such that the optimization logic 122 preferentially recommends building compositions that meet the performance requirements of the construction specification 120 over mixtures that cannot meet these requirements but are less costly.

[0092] In some embodiments, performance requirements may be weighted higher than cost so that a balance can be maintained between performance and cost. For example, a construction admixture may need to achieve a certain minimum level of cost savings before an acceptable amount of performance degradation is permitted.

[0093] The optimization logic 122 may output, for each identified construction composition 418 (representing a combined construction mixture and construction admixture), a predicted performance 426 of the composition. The predicted performance 426 may specify estimated values ​​for parameters specified in the construction specification 120, or may include parameters not specified in the construction specification (particularly if different mixtures 418 differ in terms of parameters not specified). The predicted performance 426 may be based on historical data and / or on data obtained from a virtual simulation of the determined mixture 418.

[0094] The optimization logic 122 may further output an estimated cost 428 of each composition 418 (optionally outputting separate cost estimates for the component building mixtures and / or building admixtures that make up the combined composition 418). The estimated cost 428 may be derived from the cost of the available materials 408, any specialized techniques employed to mix the materials, the cost of transportation, and / or the cost for a team of contractors to deploy the building compositions.

[0095] The optimization logic 122 may include various components and may receive inputs throughout the environment 100, as depicted in further detail in the block diagram of FIG.

[0096] As described above, the construction composition design process may begin with a team of architects, technical experts, or engineers. These users may access the designer server 510, which may include an application supporting a user interface that allows users to enter technical requirements into the construction specification 120. The construction specification 120 may be stored in storage 512 (e.g., HDD, SSD, etc.) on the designer server 510. In some embodiments, the construction specification 120 may be a special-purpose custom document designed in a special-purpose application. In others, the construction specification 120 may be a formatted document, such as an XML document, word processing document, or spreadsheet, that uses keywords or predefined identifiers to identify performance requirements. In this case, the producer server 106 may parse the construction specification 120 upon receipt to load the requirements into a suitable data structure for processing by the optimization logic 122.

[0097] The designer server 510 may use a network interface 514 (e.g., a wireless card, a wired connection, etc.) to transmit the construction specification 120 to the producer server 106. The construction specification 120 may be transmitted over a network 526, such as a LAN, a WAN, or the Internet.

[0098] The construction specification 120 may be received by a corresponding network interface 528 on the producer server 106 and stored in a memory 530 of the producer server 106. The memory 530 may also hold optimization logic 122, which may include a model or algorithm 540 configured to receive as input the performance requirements of the construction specification 120 and provide as output one or more construction composition specifications that identify construction compositions that meet or most closely approximate the performance requirements. The model 540 may be, for example, a machine learning algorithm, an artificial neural network, a predictive model, a set of rules and corresponding trigger outputs, or the like.

[0099] In this context, a data-driven model, preferably a data-driven machine learning model or a simple data-driven model, refers to a mathematical model that is parameterized according to a parameterized training data set that reflects the reaction kinetics or physicochemical process of the system. An untrained mathematical model refers to a model that does not reflect the reaction kinetics or physicochemical process, for example, an untrained mathematical model is not derived from physical laws that provide scientific generalizations based on experimental observations. Thus, kinetics or physicochemical properties may not be inherent in an untrained mathematical model. An untrained model does not reflect such properties. Feature engineering and training using a separate training data set allows the parameterization of an untrained mathematical model. The result of such training is simply a data-driven model, preferably a data-driven machine learning model that reflects kinetics or physicochemical properties as a result of the training process, preferably as a result of the training process only.

[0100] The model 540 may be trained using historical training data 532. The training data 532 may include labeled training data that includes previously produced construction compositions and corresponding measured performance results for the construction compositions. The training data 532 may also include simulation data that estimates performance parameters for actual or hypothetical mixtures. The training data 532 may be obtained through experiments, simulations, or by measuring versions of mixtures deployed on a real-world construction site, among other possibilities.

[0101] The model or algorithm 540 may be trained using training data via training logic 534. The training logic 534 may be specific to the type of model or algorithm 540 being used. For example, if the model or algorithm 540 is a genetic algorithm, the training logic 534 may include heuristics for selecting the most suitable candidate in one generation and genetic operators for producing the next generation of candidates. If the model or algorithm 540 is a neural network, the training logic 534 may include a suitable propagation function. The training logic 534 may define initial weights and / or an initial structure for training the model or algorithm 540. Other examples of the training logic 534 include clustering functions, logistic regression functions, time series parameters for time series analysis, decision tree structures, etc.

[0102] The training data 532 may include all relevant performance parameters for a given construction admixture (e.g., those parameters shown in FIG. 2), or may include only a subset of such parameters. When only a subset of the parameters is included in a given entry in the training data 532, the training logic 534 may be configured to train only certain portions of the model / algorithm 540 on the available data, or may be configured to extrapolate missing data from similar examples or simulations.

[0103] The training logic 532 may be configured to assign weights or rankings to various performance parameters. The weights or rankings may be predetermined (e.g., defined by an engineer or expert) or may be assigned by the training logic 532 based on the training data 532. In some embodiments, the training logic 534 may be configured to consider the cost of the construction composition as one of the performance parameters, but prioritize the performance of the composition over the cost of the composition.

[0104] The optimization logic 122 may also include retraining logic 536. In contrast to the training logic 534, which operates on historical training data 532, the retraining logic may be configured to adapt the model or algorithm 540 on the fly based on newly received information (e.g., information from the sensors 516 or contractor server 134 that may not be reflected in the training data 532). The retraining logic 536 may be configured to adapt the model or algorithm 540 more slowly or conservatively than the initial training process, under the assumption that a properly trained model should not change rapidly in light of limited data. The speed of adaptation may be adjustable so that a user may modify the extent to which new data is considered. The speed of adaptation may also be automatically changed in certain circumstances. For example, if feedback is received from the contractor server 134 indicating that a delivered batch of concrete is unacceptable or does not meet certain performance parameters, then a fast adaptation is likely required and the model or algorithm 540 should be adjusted immediately.

[0105] A model or algorithm 540 may be constructed based, in part, on variables and mappings 538 that define the extent to which a particular change to the construction composition is likely to affect the performance parameters. Example variables and mappings are depicted in Figures 3A-3C.

[0106] When determining the raw materials available for inclusion within a given building mix or construction admixture, the optimization logic 122 may consult a component library 124. The component library 124 may consist of a number of entries 544, each associated with a given chemistry 546 or other material. For products comprised of building mixes and construction admixtures, separate component libraries 124 may be provided for the building mixes and construction admixtures.

[0107] The component library 124 may include a complete set of chemicals 546 that can be used to create the construction admixture, or may include only a subset of such chemicals 546. The selection of a smaller, more specific set of components can be tailored to best suit each application. Instead of individual chemicals 546 or other individual materials, the entries 544 in the component library 124 may be compositions of several materials (preserving known synergies for certain chemical combinations), or finished products as known today. When a component is a single material, the selection of a particular material may be made to take advantage of the maximum significant concentration of material available on-site.

[0108] Basing the components on individual chemicals allows the amounts and ratios to be varied and customized for each application, material set, or condition, such as high or low alkali cements or high or low temperatures. The amounts and ratios of the components can also be adjusted continuously on a sliding scale within the customer site as conditions or materials change.

[0109] Each chemical can be categorized by a category 548, which represents a base performance attribute (e.g., "strength," "setting modification," etc.), and a function 550, which describes the degree to which the chemical affects the performance attribute (e.g., "increases strength" or "accelerates setting time"). Chemicals may be further separated into primary and secondary classes 552, where a primary class chemical has as its primary purpose (or primary effect) modifying the function 550. A secondary class chemical may not be intended to perform the intended function 550 (e.g., have a greater effect with respect to some other function), but may act as a secondary effect. Table 1 provides a list of example attributes, functions, and classes that may be applied to various chemicals. [Table 1-1] [Table 1-2]

[0110] Preferred examples of chemistry options for each of the above categories are provided below in Table 2. Other chemistry options may also be used and the categories are not limited to the examples provided below. [Table 2-1] [Table 2-2]

[0111] Optionally, entry 544 may identify any certification 554 that the components would be suitable (e.g., C494 certification). Additionally, entry 544 may specify additional details 556 (e.g., available or recommended concentrations of chemicals 546, mixing recommendations, etc.).

[0112] The optimization logic 122 may further provide, for each identified construction admixture (or composition), the cost of the construction admixture, the estimated performance of the construction admixture, and a comparison between the admixtures with respect to prescribed or unspecified performance parameters. These items may be identified by simulating the performance of the construction admixture using the simulation logic 542. The simulation logic 542 may build a model of the structure being designed by the architect / engineer / technical expert using the construction admixture output by the optimization logic 122. The simulation logic 542 may evaluate the performance of the construction admixture with respect to the parameters specified in the construction specification (and other parameters that may not be specified in the construction specification but may be related to the performance of the construction admixture) based on historical performance information and / or mathematical models for similar construction admixtures.

[0113] Based on the simulation, the simulation logic 542 may output and / or display a report comparing the different construction admixtures in terms of performance and cost. In some embodiments, only those performance parameters that differ between the construction admixtures may be output or displayed. In some embodiments, the optimization logic 122 may evaluate and display the comparison based on performance parameters that differ between the construction admixtures but were not specified in the construction specification 120. Thus, if the construction admixtures output by the optimization logic 122 are considered similar in terms of specified performance requirements and cost, these similar construction admixtures may be differentiated based on other factors that would not have been considered otherwise.

[0114] Once a particular construction admixture formulation has been determined or selected, the producer server 106 may control a mixing device 560 at the construction composition plant to produce the construction admixture. For example, the mixing device 560 may include a controller 562 capable of operating the mixing machinery based on instructions. The controller 562 may control the unfolding of raw materials from a raw material silo or may output a requested amount of raw materials for manual addition to the mixing device 560. Once the raw materials are added to the mixing device 560, the controller 562 may activate the mixer for a defined amount of time (and potentially at a defined power or in a defined mixing pattern).

[0115] The producer server 106 may generate instructions for the controller 562 to perform the above activities according to the formulation defined by the optimization logic 122. For example, the controller 562 may expose an application programming interface (API) that allows the producer server 106 to invoke functions of the controller 562 to perform the activities. The producer server 106 may generate suitable instructions or function calls and transmit the instructions / calls via the producer server's interface 558 to the interface 564 of the mixing device 560. The interfaces 558, 564 may communicate directly, via wired or wireless communication, and / or over a network.

[0116] As batches of construction mixtures, admixtures, and / or compositions are made and shipped to the contractor, the producer server 106 may receive further feedback from the sensors 516 and / or the contractor server 134. This information may allow the product to be modified or reformulated based on real-time feedback describing current conditions and / or measured performance. For example, the contractor may generate a performance report 506 in the memory 504 of the contractor server 134. The performance report may specify quantitative measurements (e.g., output by sensors used by the contractor) and / or qualitative assessments from the contractor. The performance report 506 may be typed into the contractor server 134 via one or more input / output devices 502, such as a keyboard, microphone (for voice input), data port, etc. The performance report may be transmitted to the producer server 106 via a network interface 508.

[0117] Similarly, performance data and / or details about ambient conditions may also be transmitted to the producer server from one or more deployed sensors 516. The sensors 516 may be deployed, for example, on a transport vehicle that brings the mix to the work site, at the work site itself, or on structures along the route from the factory to the work site.

[0118] The sensors 516 may include measurement devices 518 such as accelerometers, anemometers, hygrometers, light meters, etc. Measurements from the measurement devices may be transmitted directly to the producer server 106 via a network interface 524 or may be aggregated in a buffer 522 stored in the memory 520 of the sensor 516. After a predetermined amount of time, a predetermined number of readings, or when the memory 520 has filled to a certain level, the buffered data may be transmitted to the producer server 106.

[0119] As an alternative or in addition to the producer server 106 formulating and generating the building mixture / admixture as described above, some or all of these tasks may be performed at the work site by the contractor server 134. Thus, some or all of the digital components depicted in FIG. 5 as being located on the producer server 106 may also or alternatively be located on the contractor server 134. This allows the contractor server 134 to independently generate the building mixture and / or admixture formulations. Alternatively or in addition, the components may be hosted on the producer server 106 and the contractor server 134 may communicate with the producer server 106 via the network 526 and request that the producer server 106 generate or modify the building mixture and / or admixture using inputs provided by the contractor server 134. Additionally, if mixing machinery is available on-site at the work site, the contractor server 134 may implement the functionality described above to generate instructions for and / or otherwise control the machinery to mix the admixture and / or ingredients for the construction mix on-site at the work site.

[0120] The exchange of data between the designer server 510, the contractor server 134, the sensors 516, and the manufacturer server 106 is explained in further detail in the data flow diagram depicted in FIG. 6A.

[0121] Initially, the producer server and / or contractor server may initiate a training process 602. The training logic described above may build models or algorithms for optimizing construction mixtures, admixtures, and / or compositions given the performance requirements in the construction specifications, with reference to historical data.

[0122] The construction specification 120 may then be transmitted from the designer server to the producer server. The construction specification 120 may also be forwarded to the contractor server so that the contractor server has the performance requirements available when mixing the construction admixture.

[0123] In response to receiving the construction specification 120, the producer server may initiate a construction mix formulation process 604, which applies an algorithmic model to the received construction specification 120 to generate one or more suitable construction mixes that meet or most closely approximate the requirements of the construction specification.

[0124] If multiple construction mixes are generated, the system may output a comparison of the construction mixes and allow one to be selected. Once a target construction mix is ​​identified, the producer server may initiate a mix production process 606, which may involve generating instructions and / or controlling mixing machinery to produce the identified mix.

[0125] Once mixed, the producer server may dispatch 607 the base construction mix produced in the construction mix production process 606 to the work site.

[0126] In some cases, the construction mix may be a general purpose construction mix whose properties are then modified by the construction admixture. During the construction admixture generation process, the sensor data 136 may be optionally read to identify ambient conditions to be considered. Based on the sensor data 136 and the requirements of the construction specification 120, the system may initiate a construction admixture formulation process 608 to generate a construction admixture formulation (similar to the construction composition formulation process 604, but likely with different raw materials). In the depicted embodiment, the producer server ships 609 the components used to make the formulated construction admixture to the construction site. In another embodiment, the construction admixture may be produced in the same factory as the construction mix formulation and then shipped to the construction site as a finished construction admixture.

[0127] The contractor server may then initiate a construction admixture production process 610 to generate the construction admixture (similar to the construction mix production process 606, but occurring at the construction site). The construction admixture may be added directly to the construction mix or may be generated separately and added to the construction mix at a later time.

[0128] At 612, the contractor server may initiate a combined building composition production process in which the building mix and the building admixtures are mixed together. This may involve operating mixing machinery and combining the building mix and the building admixtures.

[0129] During or after mixing of the construction mix, the contractor server may receive input from the sensors and / or performance reports 506. This data may provide real-time feedback that allows the contractor server to update the construction admixture formulation between batches, which may improve the consistency, performance, and / or cost of the construction mix as the work is performed. In response to this data, the contractor server may perform quality control, remix, or retraining processes that update the construction admixture generated at 610. The updated data may be provided to an optimization process, which may update models or algorithms, or alternatively, reapply existing models or algorithms with the new data provided by the sensors and / or contractor server.

[0130] These actions are described in further detail with respect to the flow chart shown in Figure 6B. The blocks of Figure 6B may be implemented as logic 650 or instructions stored on a non-transitory computer-readable medium for execution on (for example) a producer server, a contractor server, both, or split between the producer server and the contractor server.

[0131] Processing may begin at block 652 where the system receives training data. The training data may include historical data identifying construction compositions (including base construction mixtures and construction admixtures) and associated performance results measured when the compositions were deployed. Information about ambient conditions, location, etc. may also be provided as part of the historical data. The training data may also, or alternatively, include simulation data received as a result of computer simulations performed on hypothetical or actual compositions.

[0132] The training data may be associated with various performance parameters. In block 608, priorities associated with those parameters may be set or adjusted by adjusting the weightings of the parameters. For example, the cost of construction admixtures may be de-prioritized compared to the performance parameters. The user may also specify the relative performance of the various parameters (e.g., strength and durability are more important than aesthetics).

[0133] Based on the training data and the defined priorities, a model or algorithm may be trained by the training logic at block 654. Training may be performed until a set of training conditions are met. For example, a set of training data may be retained in preparation for testing the performance of the trained model or algorithm. The model or algorithm may be tested on the retained training data to determine whether the model or algorithm generates a suitable mix based on performance characteristics (a "suitable" mix would be considered a mix and / or admixture whose material proportions fall within a threshold amount of difference from the construction admixture defined in the training data).

[0134] If, at block 656, the system determines that the model is sufficiently trained, processing may proceed to block 568. If not, processing may return to block 652 and the system may incorporate additional training data into the model or algorithm.

[0135] The system may be capable of operating in several different modes, including a manual override mode. In an "evaluation" mode, the system may receive one or more compositions as input and perform a performance evaluation of the compositions. In a "formulation" mode, the system receives a set of requirements (e.g., construction specifications) and generates a composition (or set of compositions) that meets or approximates the requirements.

[0136] If the system is in evaluation mode at block 568, processing may proceed to block 660, where the system may receive a composition. The composition may be entered via an interface (e.g., by specifying amounts or percentages of identified ingredients) or may be received as a finished specification identified within a data structure. A single composition may be received for evaluation, or multiple compositions may be received for evaluation and comparison.

[0137] In block 662, the system may perform a simulation on the construction admixture using the simulation logic described above. The output of the simulation may be a set of performance characteristics, cost parameters, etc., which are estimated in block 664.

[0138] At block 666, the system determines whether multiple construction admixtures have been submitted for comparison. If not, the system outputs (at block 668) the estimated value determined at block 664. This may involve storing the estimated value in memory, transmitting the value over a network, and / or displaying the value on a display.

[0139] If the construction admixture was submitted for evaluation as part of a production process, the system may request approval to produce the evaluated construction admixture at block 670. If approval is received at block 670, processing proceeds to block 672 where the system commands mixing equipment to produce the construction admixture as described above.

[0140] Returning to block 666, if multiple construction admixtures were evaluated, the system may output a comparison of the evaluations in block 674. The comparison may provide a side-by-side overview of each construction admixture and may highlight differences in various performance characteristics of the construction admixtures. In some embodiments, all performance characteristics may be shown for comparison. In others, only performance characteristics that differ between the construction admixtures may be shown or highlighted. Still further, performance characteristics that were not specified as part of the original evaluation request may be considered and displayed if they differ from one another. In some embodiments, non-specified performance characteristics may be considered only if the specified performance characteristics are the same or differ by less than a predetermined threshold amount (thus allowing relatively similar construction admixtures to be differentiated for other reasons).

[0141] Based on the comparison, the system may receive a selection of one of the construction admixtures (either from a user or programmatically based on a weighting of the importance of various parameters) at block 676. Processing may then proceed to block 672, where the system may either mix the selected construction admixture or ship components for the admixture to the work site, as described above.

[0142] If at block 658 the system is in "formulation" mode, processing may proceed to block 678 where a set of construction specifications or performance requirements may be received. At block 680, the system may access a set of inputs, variables, or mappings that describe the extent to which the available compositions affect the parameters described in block 678 (this information may also or alternatively be incorporated into a model / AI / ML algorithm).

[0143] At block 682, the system may apply an artificial intelligence, machine learning algorithm, or model to generate a construction admixture based on the parameters received at block 678. The optimization logic may apply an algorithm or model to generate one or more output construction admixtures, as described above.

[0144] In some embodiments, the AI / ML / model may be allowed to be applied on a sustained basis until a fast stop command is received. In these embodiments, the optimization logic may continue to be run on the AI / ML / model for a predetermined number of iterations, for a predetermined period of time, or until the determined manufacturing compound characteristics fall within a predetermined threshold margin of the construction specifications. Other stopping conditions may also be applied.

[0145] After the stopping condition is met, processing may proceed to block 684 where the system determines whether to evaluate the construction admixture generated in block 682. If so, processing may return to block 662 and the system may perform a simulation on the construction admixture. If not, processing may proceed to block 686 where the construction admixture may be output (e.g., to a network, memory, or display). A construction admixture may be selected for use (or if a single construction admixture may be approved), and processing may proceed to block 672 where the construction admixture may be sent for mixing.

[0146] The methods described above may be embodied as instructions on a computer-readable medium or as part of a computing architecture. Figure 7 illustrates an embodiment of an exemplary computing architecture 700 suitable for implementing various embodiments as described above. In one embodiment, the computing architecture 700 may comprise or be implemented as part of an electronic device such as a computer 701. The embodiments are not limited in this context.

[0147] As used herein, the terms "system" and "digital component" are intended to refer to any computer-related entity, whether hardware, a combination of hardware and software, software, or software in an executable file, an example of which is provided by the exemplary computing architecture 700. For example, a digital component can be, but is not limited to, a process running on a processor, a processor, a hard disk drive, multiple storage drives (optical and / or magnetic storage media), an object, an executable file, a thread of execution, a program, and / or a computer. By way of example, a server and an application running on a server can both be digital components. One or more digital components can reside within a process and / or thread of execution, and the digital components can be localized on one computer and / or distributed among two or more computers. Furthermore, the digital components may be communicatively coupled to each other by various types of communication media to coordinate operations. The coordination may involve unidirectional or bidirectional exchange of information. For example, the digital components may communicate information in the form of signal communication over the communication media. The information can be implemented as signals distributed on various signal lines. In such an arrangement, each message is a signal. However, further embodiments may alternatively employ data messages. Such data messages may be transmitted across a variety of connections. Exemplary connections include parallel interfaces, serial interfaces, and bus interfaces.

[0148] Computing architecture 700 may include various common computing elements, such as one or more processors, multi-core processors, co-processors, memory units, chipsets, controllers, peripherals, interfaces, oscillators, timing devices, video cards, audio cards, multimedia input / output (I / O) components, power supplies, etc. However, embodiments are not limited to implementation with computing architecture 700.

[0149] As shown in Figure 7, computing architecture 700 includes a processing unit 702, a system memory 704, and a system bus 706. Processing unit 702 can be any of a variety of commercially available processors, including, but not limited to, AMD Athlon, Duron, and Opteron processors, ARM Applications, Embedded and Secure processors, IBM and Motorola DragonBall, and PowerPC processors, IBM and Sony Cell processors, Intel Celeron, Core(2) Duo, Itanium, Pentium, Xeon, and XScale processors, and similar processors. Dual microprocessors, multi-core processors, and other multi-processor architectures may also be employed as processing unit 702.

[0150] The system bus 706 provides an interface for system components, including but not limited to the system memory 704, to the processing unit 702. The system bus 706 can be any of several types of bus structures that may further interconnect to a memory bus (with or without a memory controller), a peripheral bus, and a local bus using any of a variety of commercially available bus architectures. Interface adapters may connect to the system bus 706 via a slot architecture. Exemplary slot architectures may include, but are not limited to, Accelerated Graphics Port (AGP), Card Bus, (Extended) Industry Standard Architecture ((E)ISA), Micro Channel Architecture (MCA), NuBus, Peripheral Component Interconnect (Extended) (PCI(X)), PCI Express, Personal Computer Memory Card International Association (PCMCIA), and the like.

[0151] Computing architecture 700 may comprise or be implemented in a variety of articles of manufacture. An article of manufacture may comprise a computer-readable storage medium for storing logic. Examples of computer-readable storage media may include any tangible medium capable of storing electronic data, including volatile or non-volatile memory, removable or non-removable memory, erasable or non-erasable memory, writable or re-writable memory, and the like. Examples of logic may include executable computer program instructions implemented using any suitable type of code, such as source code, compiled code, interpreted code, executable code, static code, dynamic code, object-oriented code, visual code, and the like. An embodiment may also be implemented, at least in part, as instructions contained in or on a non-transitory computer-readable medium, which may be read and executed by one or more processors to enable performance of the operations described herein.

[0152] The system memory 704 may be any of a variety of memory types, including read only memory (ROM), random access memory (RAM), dynamic RAM (DRAM), double-data-rate DRAM (DDRAM), synchronous DRAM (SDRAM), static RAM (SRAM), programmable ROM (PROM), erasable programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, polymer memory such as ferroelectric polymer memory, Ovonic memory, phase change or ferroelectric memory, silicon-oxide-nitride-oxide-silicon (SONOS) memory, magnetic or optical cards, Redundant Arrays of Independent The system memory 704 may include various types of computer readable storage media in the form of one or more faster memory units, such as array of disks (RAID) drives, solid state memory devices (e.g., USB memory, solid state drives (SSD), and any other type of storage media suitable for storing information. In the illustrated embodiment shown in FIG. 7, the system memory 704 may include non-volatile memory 708 and / or volatile memory 710. A basic input / output system (BIOS) may be stored in the non-volatile memory 708.

[0153] The computing architecture 700 may include various types of computer-readable storage media in the form of one or more slower memory units, including an internal (or external) hard disk drive (HDD) 712, a magnetic floppy disk drive (FDD) 714 for reading from and writing to a removable magnetic disk 716, and an optical disk drive 718 for reading from or writing to a removable optical disk 720 (e.g., a CD-ROM or DVD). The HDD 712, FDD 714, and optical disk drive 720 may be connected to the system bus 706 by a HDD interface 722, a FDD interface 724, and an optical drive interface 726, respectively. The HDD interface 722 for external drive implementations may include at least one or both of Universal Serial Bus (USB) and IEEE 694 interface technologies.

[0154] The drives and associated computer-readable media provide volatile and / or nonvolatile storage of data, data structures, computer-executable instructions, etc. For example, a number of program modules may be stored in the drives and memory units 708, 712, including an operating system 728, one or more application programs 730, other program modules 732, and program data 734. In one embodiment, the one or more application programs 730, other program modules 732, and program data 734 may include, for example, various applications and / or components of messaging system 500.

[0155] A user can enter commands and information into the computer 701 through one or more wired / wireless input devices, such as a keyboard 736 and a pointing device, such as a mouse 738. Other input devices may include a microphone, an infrared (IR) remote control, a radio frequency (RF) remote control, a game pad, a stylus pen, a card reader, a dongle, a fingerprint reader, a glove, a graphics tablet, a joystick, a keyboard, a retina reader, a touch screen (e.g., capacitive, resistive, etc.), a track ball, a track pad, a sensor, a stylus, and the like. These and other input devices are often connected to the processing unit 702 through an input device interface 740 that is coupled to the system bus 706, but can also be connected by other interfaces, such as a parallel port, an IEEE 694 serial port, a game port, a USB port, an IR interface, etc.

[0156] A monitor 742 or other type of display device is also connected to the system bus 706 via an interface, such as a video adapter 744. The monitor 742 may be internal or external to the computer 701. In addition to the monitor 742, computers typically include other peripheral output devices, such as speakers, printers, etc.

[0157] The computer 701 may operate in a networked environment using logical connections via wired and / or wireless communications to one or more remote computers, such as a remote computer 744. The remote computer 744 can be a workstation, a server computer, a router, a personal computer, a portable computer, a microprocessor-based entertainment appliance, a peer device, or other common network node, and typically includes many or all of the elements described relative to the computer 701, although for purposes of simplicity, only a memory / storage device 746 is illustrated. The depicted logical connections include wired / wireless connectivity to a local area network (LAN) 748 and / or larger networks, e.g., a wide area network (WAN) 750. Such LAN and WAN networking environments are commonplace in offices and enterprises to facilitate enterprise-wide computer networks, such as intranets, all of which may connect to a global communications network, e.g., the Internet.

[0158] When used in a LAN networking environment, the computer 701 is connected to the LAN 748 through a wired and / or wireless communication network interface or adapter 752. The adapter 752 can facilitate wired and / or wireless communication to the LAN 748, which may also include a wireless access point disposed thereon for communicating with the wireless functionality of the adapter 752.

[0159] When used in a WAN networking environment, the computer 701 may include a modem 754 or have other means for establishing communications over the WAN 750, such as connected to a communications server on the WAN 750 or via the Internet. The modem 754, which may be internal or external and a wired and / or wireless device, connects to the system bus 706 via the input device interface 740. In a networked environment, program modules depicted relative to the computer 701, or portions thereof, may be stored in a remote memory / storage device 746. It will be appreciated that the network connections shown are exemplary and other means of establishing a communications link between the computers may be used.

[0160] The computer 701 is operable to communicate with wired and wireless devices or entities using the IEEE 802 family of standards (e.g., IEEE 802.13 wireless communication modulation techniques), such as wireless devices operatively arranged in wireless communication. This includes at least Wi-Fi (or Wireless Fidelity), WiMax, and Bluetooth wireless technologies, among others. Thus, the communication can be of a predefined structure similar to a conventional network, or simply an ad-hoc communication between at least two devices. A Wi-Fi network provides secure, reliable, high-speed wireless connectivity using wireless technologies called IEEE 802.13x (a, b, g, n, etc.). A Wi-Fi network can be used to connect computers to each other, to the Internet, and to wired networks (using IEEE 802.3 related media and functions).

[0161] 8 is a block diagram depicting an exemplary communications architecture 800 suitable for implementing various embodiments as described above. Communications architecture 800 includes various common communications elements such as transmitters, receivers, transceivers, radios, network interfaces, baseband processors, antennas, amplifiers, filters, power supplies, etc. However, embodiments are not limited to implementation with communications architecture 800.

[0162] 8, the communications architecture 800 includes one or more clients 802 and servers 804. The clients 802 may implement client devices 510. The servers 804 may implement server devices 526. The clients 802 and servers 804 are operatively connected to one or more respective client data store(s) 806 and server data store(s) 808 that may be employed to store information, such as cookies and / or associated contextual information, local to the respective clients 802 and servers 804.

[0163] The clients 802 and the servers 804 may communicate information between each other using a communications framework 810. The communications framework 810 may implement any well-known communications techniques and protocols. The communications framework 810 may be implemented as a packet-switched network (e.g., a public network such as the Internet, a private network such as a corporate intranet, etc.), a circuit-switched network (e.g., the public switched telephone network), or a combination of packet-switched and circuit-switched networks (with suitable gateways and translators).

[0164] The communications framework 810 may implement various network interfaces arranged to admit, communicate, and connect to communications networks. A network interface may be considered a specialized form of an input-output interface. The network interfaces may employ connection protocols including, but not limited to, direct connection, Ethernet (e.g., thick, thin, twisted pair 10 / 100 / 1000 Base T, and the like), token ring, wireless network interfaces, cellular network interfaces, IEEE 802.8a-x network interfaces, IEEE 802.16 network interfaces, IEEE 802.20 network interfaces, and the like. Additionally, multiple network interfaces may be used to engage with various communications network types. For example, multiple network interfaces may be employed to enable communications over broadcast, multicast, and unicast networks. If processing requirements dictate higher speeds and more capacity, a distributed network controller architecture may be employed as well to pool, load balance, and otherwise increase the communications bandwidth requested by the clients 802 and servers 804. The communications network may be any one and combination of wired and / or wireless networks, including, but not limited to, direct interconnects, fixed custom connections, private networks (e.g., corporate intranets), public networks (e.g., the Internet), personal area networks (PANs), local area networks (LANs), metropolitan-wide networks (MANs), Operating Missions as Node on the Internet (OMNIs), wide area networks (WANs), wireless networks, cellular networks, and other communications networks.

[0165] The digital components and features of the devices described above may be implemented using any combination of discrete circuitry, application specific integrated circuits (ASICs), logic gates, and / or single chip architectures. Furthermore, the features of the devices may be implemented using microcontrollers, programmable logic arrays, and / or microprocessors, or any combination of the foregoing, where appropriate. It should be noted that hardware, firmware, and / or software elements may be collectively or individually referred to herein as "logic" or "circuitry."

[0166] It should be understood that the example devices shown in the block diagrams described above may represent one functional illustrative example of many potential implementations. Thus, the division, omission, or inclusion of block functions depicted in the accompanying figures does not infer that hardware components, circuits, software, and / or elements for implementing these functions will necessarily be divided, omitted, or included in the embodiment.

[0167] At least one computer-readable storage medium may contain instructions that, when executed, cause the system to perform any of the computer-implemented methods described herein.

[0168] Some embodiments may be described using the phrase "in one embodiment" or "an embodiment," along with its derivatives. These terms mean that a particular feature, structure, or characteristic described in connection with an embodiment is included in at least one embodiment. The appearances of the phrase "in one embodiment" in various places within the specification do not necessarily all refer to the same embodiment. Moreover, unless otherwise noted, it is recognized that the features described above can be used together in any combination. Thus, any features discussed separately may be employed in combination with each other, unless the features are stated to be mutually incompatible.

[0169]

[0023] Generally referring to the notation and nomenclature used herein, the detailed descriptions herein may be presented in terms of program procedures executed on a computer or network of computers. These procedural descriptions and representations are used by those skilled in the art to most effectively convey the substance of their work to others skilled in the art.

[0170] A procedure is herein generally conceived to be a self-consistent sequence of operations leading to a desired result. These operations require physical manipulations of physical quantities. Usually, though not necessarily, these quantities take the form of electrical, magnetic, or optical signals capable of being stored, transferred, combined, compared, and otherwise manipulated. It has proven convenient at times, principally for reasons of common usage, to refer to these signals as bits, values, elements, symbols, characters, terms, numbers, or the like. It should be noted, however, that all of these and similar terms are not necessarily associated with the appropriate physical quantities but are merely convenient labels applied to these quantities.

[0171] Further, the operations performed are often referred to in terms, such as adding or comparing, that are commonly associated with mental operations performed by a human operator. No such capability of a human operator is necessary, or desirable in most cases, in any of the operations described herein that form part of one or more of the embodiments. Rather, the operations are machine operations. Useful machines for performing the operations of various embodiments include general purpose digital computers or similar devices.

[0172] Some embodiments may be described using the phrases "coupled" and "connected," along with their derivatives. These terms are not necessarily intended as synonyms for each other. For example, some embodiments may be described using the terms "connected" and / or "coupled" to indicate that two or more elements are in direct physical or electrical contact with each other. However, the term "coupled" may also mean that two or more elements are not in direct contact with each other, but still co-operate or interact with each other.

[0173] Various embodiments also relate to apparatus or systems for performing these operations. The apparatus may be specially constructed for the required purposes, or may comprise a general-purpose computer as selectively activated or reconfigured by a computer program stored in the computer. The procedures presented herein are not inherently related to a particular computer or other apparatus. Various general-purpose machines may be used in conjunction with programs written in accordance with the teachings herein, or it may prove convenient to construct more specialized apparatus to perform the required method steps. The required structure for a variety of these machines will be apparent from the given description.

[0174] It should be emphasized that the Abstract is provided to enable the reader to quickly ascertain the nature of the technical disclosure. It should be considered with the understanding that it will not be used to interpret or limit the scope or meaning of the claims. In addition, in the foregoing detailed description, it can be seen that various features are grouped together in a single embodiment for the purpose of brevity of the disclosure. The method of disclosure should not be interpreted as reflecting an intention that the claimed embodiments require more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive subject matter lies in less than all features of a single disclosed embodiment. Accordingly, the following claims are hereby incorporated into the detailed description, with each claim standing on its own as a separate embodiment. In the appended claims, the terms "including" and "in which" are used as the plain English equivalents of the respective terms "comprising" and "wherein." Furthermore, the terms "first," "second," "third," etc. are used merely as labels and are not intended to impose numerical requirements on their objects.

[0175] What has been described above includes examples of the disclosed architecture. Of course, it is not possible to describe every conceivable combination of digital components and / or methodologies, but one of ordinary skill in the art will recognize that many further combinations and permutations are possible. Accordingly, the novel architecture is intended to embrace all such alterations, modifications, and variations that fall within the spirit and scope of the appended claims.

Claims

1. A non-transitory computer readable medium (530), the non-transitory computer readable medium (530) storing instructions (122, 650), the instructions (122, 650), when executed by one or more processors, causing the one or more processors to: receiving, at a producer server (106), a construction specification (120) for a building composition (118), said building composition (118) comprising a building mixture (114) and a construction admixture (116) configured to be added to said building mixture (114) and to modify one or more properties of said building composition (118), said construction specification (120) defining one or more performance requirements (202-250) for said building composition; accessing a set of inputs that affect one or more properties of the construction composition, the set of inputs comprising one or more of previous construction composition performance, factory specific construction composition performance, available materials, real-time sensor readings, ambient environmental conditions, job specific information, or contractor requirements; providing said construction specification (120) and a set of components (402) to a predictive model (540), each component of said set of components (402) providing a desired functional property to said construction mixture (114) or said construction admixture (116); programmatically determining at least one construction admixture (116) that meets or approximates the performance requirements of the construction specification (120); The construction admixture (116) comprises a plurality of components mixed in a determined ratio; the construction mixture (114) is formulated according to a construction mixture formulation process, and the at least one construction admixture (116) is determined according to a construction admixture formulation process separate from the construction mixture formulation process; said programmatically determining including using said predictive model (540) to select said plurality of constituents and said determined ratio; outputting said at least one determined construction admixture (116); and generating instructions configured to cause a mixing equipment to automatically produce a selected one of the at least one determined construction admixture (116) and transmitting the instructions to the mixing equipment; receiving, at the producer server (106), one or more measurements of changing conditions at a work site (130) from one or more deployed sensors (516) at the work site; adjusting ratios or amounts of components of the construction admixture (116) in real time based on the changing conditions at the construction site (130); and outputting a plurality of construction admixtures (116) that approximate the performance requirements of the construction specification (120); performing a simulation (542) for each of the plurality of construction admixtures (116) to predict an expected performance of each individual construction admixture (116); outputting said expected performance of each individual construction admixture (116); A non-transitory computer readable medium for causing

2. and further storing instructions for producing the determined construction admixture, the production comprising: adding a plurality of components for said construction admixture (116) to said construction mixture (114), producing said construction composition (118), and shipping said construction composition (118) to said construction site (130); producing the determined construction admixture (116) separately from the construction mixture (114) and shipping the determined construction admixture (116) to the construction site (130); or Assembling components for said construction admixture (116) and shipping said components to said construction site (130). The medium of claim 1 , comprising:

3. The medium of claim 1 , wherein the construction admixture (116) is selected from the group of an asphalt admixture, a concrete admixture, a grout admixture, or a mortar admixture.

4. The medium of claim 1 , wherein the construction specification (120) comprises one or more of a plasticity or hardening property of the construction composition.

5. A non-transitory computer readable medium (530), the non-transitory computer readable medium (530) storing instructions (122, 650), the instructions (122, 650), when executed by one or more processors, causing the one or more processors to: receiving, at a producer server (106), a construction specification (120) for a building composition (118), said building composition (118) comprising a building mixture (114) and a construction admixture (116) configured to be added to said building mixture (114) and to modify one or more properties of said building composition (118), said construction specification (120) defining one or more performance requirements (202-250) for said building composition; accessing a set of inputs that affect one or more properties of the construction composition, the set of inputs comprising one or more of previous construction composition performance, factory specific construction composition performance, available materials, real-time sensor readings, ambient environmental conditions, job specific information, or contractor requirements; providing said construction specification (120) and a set of components (402) to a predictive model (540), each component of said set of components (402) providing a desired functional property to said construction mixture (114) or said construction admixture (116); programmatically determining at least one construction admixture (116) that meets or approximates the performance requirements of the construction specification (120); The construction admixture (116) comprises a plurality of components mixed in a determined ratio; the construction mixture (114) is formulated according to a construction mixture formulation process, and the at least one construction admixture (116) is determined according to a construction admixture formulation process separate from the construction mixture formulation process; said programmatically determining including using said predictive model (540) to select said plurality of constituents and said determined ratio; outputting said at least one determined construction admixture (116); and generating instructions configured to cause a mixing equipment to automatically produce a selected one of the at least one determined construction admixture (116) and transmitting the instructions to the mixing equipment; receiving, at the producer server (106), one or more measurements of changing conditions at a work site (130) from one or more deployed sensors (516) at the work site; adjusting ratios or amounts of components of the construction admixture (116) in real time based on the changing conditions at the construction site (130); and receiving a priority for one or more of the performance requirements and taking the priority into account; A non-transitory computer readable medium for causing

6. 10. The medium of claim 1, further storing instructions for: selecting one or more performance characteristics with respect to which the plurality of construction admixtures (116) differ, the one or more performance characteristics not specified as part of the construction specification (120); and outputting a comparison of the plurality of construction admixtures (116) based on the selected performance characteristics.

7. A non-transitory computer readable medium (530), the non-transitory computer readable medium (530) storing instructions (122, 650), the instructions (122, 650), when executed by one or more processors, causing the one or more processors to: receiving, at a producer server (106), a construction specification (120) for a building composition (118), said building composition (118) comprising a building mixture (114) and a construction admixture (116) configured to be added to said building mixture (114) and to modify one or more properties of said building composition (118), said construction specification (120) defining one or more performance requirements (202-250) for said building composition; accessing a set of inputs that affect one or more properties of the construction composition, the set of inputs comprising one or more of previous construction composition performance, factory specific construction composition performance, available materials, real-time sensor readings, ambient environmental conditions, job specific information, or contractor requirements; providing said construction specification (120) and a set of components (402) to a predictive model (540), each component of said set of components (402) providing a desired functional property to said construction mixture (114) or said construction admixture (116); programmatically determining at least one construction admixture (116) that meets or approximates the performance requirements of the construction specification (120); The construction admixture (116) comprises a plurality of components mixed in a determined ratio; the construction mixture (114) is formulated according to a construction mixture formulation process, and the at least one construction admixture (116) is determined according to a construction admixture formulation process separate from the construction mixture formulation process; said programmatically determining including using said predictive model (540) to select said plurality of constituents and said determined ratio; outputting said at least one determined construction admixture (116); and generating instructions configured to cause a mixing equipment to automatically produce a selected one of the at least one determined construction admixture (116) and transmitting the instructions to the mixing equipment; receiving, at the producer server (106), one or more measurements of changing conditions at a work site (130) from one or more deployed sensors (516) at the work site; adjusting ratios or amounts of components of the construction admixture (116) in real time based on the changing conditions at the construction site (130); and receiving a notification that the set of inputs has changed; re-optimizing the determined construction admixture based on the notification; and A non-transitory computer readable medium for causing

8. 8. The medium of claim 7, wherein the modified input comprises a different set of available materials (420) than were available when the construction admixture (116) was originally determined.

9. A computer-implemented method (650), comprising: receiving, at a producer server (106), a construction specification (120) for a building composition (118), the building composition comprising a building mixture (114) and a building admixture (116), the construction specification (120) defining one or more properties for the building composition (118), the building admixture (116) comprising one or more components configured to be added to the building mixture (114) before the building composition (118) is applied at a construction site (130); accessing a set of components comprising a plurality of components (544), each component (544) providing a desired functional property to said construction mixture (114) or construction admixture (116); analyzing the set of components with artificial intelligence (540) and selecting combinations of components (554) that result in a plurality of construction admixtures (116) that approximate the construction specification (120); outputting said plurality of construction admixtures (116); performing a simulation (542) for each of the plurality of construction admixtures (116) to predict an expected performance of each individual construction admixture (116); outputting said expected performance of each individual construction admixture (116); receiving, at the producer server (106), one or more measurements of changing conditions at the work site (130) from one or more deployed sensors (516) at the work site (130); adjusting the ratios or amounts of components of the construction admixture (116) in real time based on changing conditions at the construction site (130); A method comprising:

10. 10. The method of claim 9, wherein the components (544) are divided into categories, the categories comprising one or more of dispersants, caking modifiers, air control agents, strength enhancers, workability retention agents, and rheology modifiers.

11. An apparatus (106), comprising: a non-transitory computer readable storage medium (503) storing logic for a machine learning algorithm (540) configured to select additive combinations of components configured to be added to a predefined building composition (118), the components providing desired functional properties to the building composition (118); a hardware interface (528) configured to receive training data (532), the training data (532) comprising a first building composition (118) and associated performance characteristics related to the first building composition (118); A hardware processor circuit (702), comprising: training the machine learning algorithm (540) based on the training data (532); receiving, at the device (106) via the hardware interface (528), one or more performance requirements for a new building composition (118); selecting, using the machine learning algorithm (540), a plurality of new additive combinations of components (544) based on the received performance requirements; outputting said plurality of new additional combinations; and performing a simulation (542) for each of the plurality of new additive combinations to predict expected performance of each individual new additive combination; outputting the expected performance of each individual new additive combination, the new building composition being output using the hardware interface (528); receiving, at the device (106), one or more measurements of changing conditions at the work site (130) from one or more deployed sensors (516) at the work site (130); adjusting in real time the ratios or amounts of admixture components in said building composition (118) based on said changing conditions at said construction site (130); A hardware processor circuit (702) configured to: An apparatus comprising:

12. The apparatus of claim 11 , wherein the machine learning algorithm (540) is configured to prioritize performance factors over cost factors.

13. The hardware processor circuit (702) receiving a report (506) of the performance of the new building composition (118); retraining the machine learning algorithm (540) based on the performance of the new building composition (118); The apparatus of claim 11 , further configured to:

14. The apparatus of claim 11 , wherein the performance requirements comprise one or more of processability, pumpability, and workability.

15. The apparatus of claim 11 , wherein the machine learning algorithm (540) adapts to one or more of ambient conditions, delivery distance, delivery time, pouring method, or contractor staffing.

Images