Abstract: In various example embodiments, techniques are provided for efficient and reliable anomaly detection and evaluation in a water distribution system (e.g., a smart water distribution system) using both flow and pressure time series data from sensors of the system. The techniques may implement a multi-step workflow that involves decomposing the time series data to remove seasonality and rendering the time series data stationary, detecting outliers of the stationary time series data, classifying sensor events in response to flow or pressure of detected outliers exceeding high or low thresholds for at least a given number of time steps, classifying anomaly events by correlating one or more sensor events related to flow with one or more sensor events related to pressure or by clustering a plurality of sensor events in temporal proximity, and determining a quantitative score for each of the detected anomaly events that indicates a level of significance or importance.

Abstract: Systems and methods are described for modeling and analyzing utility structures according to applied loads. Particularly, a model engine can utilize inputs related to a utility structure, environmental conditions to which the utility structure is subjected, and engineering standards expected of the utility structure, and analyze the structure's loading and performance based on analysis configuration inputs. An engine or multiple engines can be run locally, or can be instantiated in a cloud to assist with multiple or complex calculations. Hybrid and geometric non-linear analyses and outputs can be performed or provided.

Abstract: In an embodiment, a process may divide elements of a mesh into sub-elements utilizing field nodes. The process may determine if each field node is inside or outside a material point cloud. The process may calculate a distance from each outside field node to a surface of the material point cloud based on a surface vector in a normal direction and a deformed volume of a material point. The process may calculate a distance from each inside field node to the surface of the material point cloud based on a surface vector, in a normal direction and associated with an outside field node closest to the inside field node, that takes into account a deformed volume of a material point. The process may utilize the distances to generate a signed distance field that may be used to perform calculations to simulate a behavior of a physical material/object that exhibit deformations.

Abstract: In example embodiments, techniques are described for using workspace databases to provide workspace resources to customize sessions of applications. File-based workspace databases are maintained in workspace files in a local file system. Cloud-based workspace databases are maintained in a cloud-based blob storage container of a storage account of a cloud storage system. Each cloud-based blob storage container may hold multiple cloud-based workspace databases, including multiple versions of the same database. To use a cloud-based workspace database, a backend module of an application may create an in-memory cloud container object that represents a connection to the cloud-based blob storage container. It may be attached to an in-memory object configured to manage a local cache of blocks of workspace databases. Access to the cloud-based blob storage container may be managed by access tokens provided by a container authority.

Abstract: In example embodiments, techniques are described for using workspace databases to provide workspace resources to customize sessions of applications. To write workspace resources a backend module of an application may obtain a write lock on a cloud-based blob storage container, and ensure a block of a workspace database to be modified is local in a cloud cache. It may execute one or more database commands to modify the block in the cloud cache, and change an identifier of the block in a local copy of a manifest that includes a list of the blocks of the cloud-based blob storage container. It may further upload the modified block and the local copy of the manifest to the cloud-based blob storage container, wherein the uploaded local copy of the manifest replaces the manifest in the cloud-based blob storage container.

Abstract: In example embodiments, a shortest path first-based isolation trace function is provided to determines what switchable elements need to be closed to stop flow of a quality to a location in an infrastructure model arranged as a network. The shortest path first-based isolation trace function may perform shortest-path traces from the location to each source. For each successful shortest-path trace finding one or more switchable elements, the first switchable element encountered on the path of the trace is added to a solution set, and marked as active to prevent further traversal in subsequent shortest-path traces. When all the shortest-path traces are complete, the solution set may be returned as a result. If no switchable element is found on a path of one of the shortest-path traces, it may be concluded that the location cannot be isolated and such conclusion returned as the result instead of the solution set.

Abstract: A method may be implemented to prioritize and analyze data exchanged in a connected vehicle transit network. The method may include receiving, at a roadside unit, vehicle data from a connected vehicle. The method may further include prioritizing the vehicle data received from the connected vehicle based on a level of urgency, network latency or available computing resources.

Abstract: In example embodiments, techniques are provided for efficiently labeling, reviewing and correcting predictions for P&IDs in image-only formats. To label text boxes in the P&ID, the labeling application executes an OCR algorithm to predict a bounding box around, and machine-readable text within, each text box, and displays these predictions in its user interface. The labeling application provides functionality to receive a user confirmation or correction for each predicted bounding box and predicted machine-readable text. To label symbols in the P&ID, the labeling application receives user input to draw bounding boxes around symbols and assign symbols to classes of equipment. Where there are multiple occurrences of specific symbols, the labeling application provides functionality to duplicate and automatically detect and assign bounding boxes and classes.

Abstract: Techniques are provided for generating score(s) and/or correction(s) for a digital twin representing a utility network. One or more bridges transform data, from a plurality of system and associated with a utility network, to a different format, e.g., relational database format. A process generates a digital twin of the utility network utilizing the data in the different format. A data quality service (DQS) performs evaluations and/or analyses of the digital twin to generate a baseline score and an updated score representing a state of the digital twin if corrections are applied. If the updated score meets or is above a threshold value, the DQS automatically applies and save the corrections to the digital twin. If the updated score does not meet the threshold value, the DQS presents a failure notification and one or more graphical representations of the utility network such that incremental corrections can be made.

Abstract: In example embodiments, techniques are provided for calculating camera rotation using translations between sensor-derived camera positions (e.g., from GPS) and pairwise information, producing a sensor-derived camera pose that may be integrated in an early stage of SfM reconstruction. A software process of a photogrammetry application may obtain metadata including sensor-derived camera positions for a plurality of cameras for a set of images and determine optical centers based thereupon. The software process may estimate unit vectors along epipoles from a given camera of the plurality of cameras to two or more other cameras. The software process then may determine a camera rotation that best maps unit vectors defined based on differences in the optical centers to the unit vectors along the epipoles. The determined camera rotation and the sensor-derived camera position form a sensor-derived camera pose that may be returned and used.

Abstract: In various embodiments, techniques are provided for determining a connection between a rail turnout and another rail turnout or other rail element by a geometry connection process of rail network design software, by reducing the actual complex geometry of the rail turnout to a simplified arc, which at one end is tangent to the geometry of a connecting element at end of the rail turnout and at the other end is tangent to the geometry of a parent base element of the rail turnout. The simplified arc is utilized instead of the actual complex geometry of the rail turnout by a connection computation engine to determine the connection in the model (e.g., by fitting a connection solution using least squares).

Abstract: In example embodiments, an enhanced deep belief learning model with an extended Kalman filter (EKF) is used for training and updating a deep belief network (DBN) with new data to produce a DBN model useful in making predictions on a variety of types of datasets, including data captured from infrastructure-attached sensors describing the condition of the infrastructure. The EKF is employed to estimate operation parameters of the DBN and generate the model's output covariance. Further, in example embodiments, the configuration of the DBN model may be optimized by a competent genetic algorithm.

Abstract: In an illustrative embodiment, the present disclosure relates to systems, methods, and an industrial internet of things (IIOT) platform and environment for generating a device integration definition to be used for configuring a new device type for interoperability with the IIOT platform and environment, where the device integration definition includes a standardized format in a programming language syntax, the device integration definition is customizable using code hook templates for issuing commands to the device type, and the device integration definition is customizable using control templates for applying the device integration definition as a foundation for preparing a graphical user interface for configuring devices of the device type with the IIOT platform and environment.

Abstract: In an example embodiment, a process may create a disk for each point of the point cloud, where a size of the disk and the orientation of the disk are respectively based on a computed scale and a non-oriented normal. The process may insert each disk into a search structure that is queried to determine if one or more disks intersect the paths from a given point to each scanner in the point cloud. The process may create an output corresponding to each scanner in the point cloud, where each output includes the number of intersecting disks and the distance from the given point to the scanner. The process may implement a sorting algorithm to assign the given point to a scanner position. An application may utilize the assignment of each point in the point cloud to a scanner position to generate a high-resolution 3D mesh of a scene.

Abstract: In various example embodiments, relevant changes between 3D models of a scene are detected and classified by transforming the 3D models into point clouds and applying a deep learning model to the point clouds. The model may employ a Siamese arrangement of sparse lattice networks each including a number of modified BCLs. The sparse lattice networks may each take a point cloud as input and extract features in 3D space to provide a primary output with features in 3D space and an intermediate output with features in lattice space. The intermediate output from both sparse lattice networks may be compared using a lattice convolution layer. The results may be projected into the 3D space of the point clouds using a slice process and concatenated to the primary io outputs of the sparse lattice networks. Each concatenated output may be subject to a convolutional network to detect and classify relevant changes.

Abstract: In example embodiments, techniques are provided to automatically identify misclassified elements of an infrastructure model using machine learning. In a first set of embodiments, supervised machine learning is used to train one or more classification models that use different types of data describing elements (e.g., a geometric classification model that uses geometry data, a natural language processing (NLP) classification model that uses textual data, and an omniscient (Omni) classification model that uses a combination of geometry and textual data; or a single classification model that uses geometry data, textual data, and a combination of geometry and textual data). Predictions from classification models (e.g., predictions from the geometric classification model, NLP classification model and the Omni classification model) are compared to identify misclassified elements, or a prediction of misclassified elements directly produced (e.g., from the single classification model).

Abstract: In example embodiments, techniques are provided for decoupling user access to infrastructure models from proprietary software that maintains and updates the infrastructure models. A backend application may include an infrastructure modeling backend module that, among other functions, handles communication with an infrastructure modeling frontend module of a frontend application that provides user access to the infrastructure model, infrastructure modeling hub services that maintain repositories for the infrastructure model, and an infrastructure modeling native module that creates, performs operations upon, and updates local instances of a database that stores the infrastructure model.

Abstract: In one embodiment, a design application is provided that utilizes layered analytical modeling in a design and analysis workflow. An analytical model may be described in a model file by a base geometry and a plurality of analysis parameters, including modification geometries that define changes that can be made to the base geometry, loading definitions that define how loads are evaluated, and appurtenances groups and configurations that define the nature and arrangement of appurtenances. A user may select analysis parameters which together with the base geometry define a scenario. A plurality of scenarios may be maintained within the same model file. When a particular scenario is to be visualized and analyzed, the analysis parameters of a scenario are layered on to (i.e. merged with) the base geometry.

Abstract: In example embodiments, techniques are provided for visualizing a 3D model in an interactive editing workflow. A user modifies one or more elements of a model of the 3D model, by inserting one or more new elements having geometry, changing the geometry of one or more existing elements and/or deleting one or more existing elements having geometry. An updated view of the 3D model is then rendered to reflect the modification to the one or more elements in part by obtaining, for each new element or changed existing element of the model visible in the view, a polygon mesh that represents geometry of the individual element, obtaining a set of tiles that each include a polygon mesh that represent collective geometry of a set of elements intersecting the tile's volume, displaying the polygon mesh for each new element or changed existing element, and displaying the set of tiles while hiding any deleted or changed existing elements therein.

Abstract: In example embodiments, techniques are provided for refining tiles of an HLOD tree representing a model in order to display a view. A frontend module selects a tile represented by a node of the HLOD sub-tree and obtains information describing geometry of the selected tile. It determines that the selected tile requires refinement to support the view of the model based on the information describing geometry of the selected tile. A tile refinement strategy is determined from a plurality of tile refinement strategies. The frontend module applies the determined tile refinement strategy to the selected tile to generate one or more child tiles that have a higher resolution than the selected tile, the one or more child tiles represented by child nodes added to the HLOD sub-tree. The frontend module displays the view of the model at least in part by showing tiles represented by nodes of the HLOD sub-tree.