Abstract: Techniques are described herein that are capable of performing quality-based action(s) regarding engineer-generated documentation associated with code and/or an API. Features are extracted from data associated with the engineer-generated documentation, which includes engineer-generated document(s). Weights are assigned to the features. The quality-based action(s) are performed. The quality-based action(s) include generating quality score(s) for the engineer-generated document(s) and/or providing a recommendation to revise a subset of the engineer-generated document(s). Each quality score is based at least in part on the weights assigned to the features that correspond to the respective engineer-generated document. The recommendation recommends performance of an operation to increase the quality of each engineer-generated document in the subset based at least in part on the weights assigned to the features that correspond to the subset.

Abstract: In some examples, a computer system may receive sensor data and failure data for equipment. The system may determine, for the equipment, a plurality of time between failure (TBF) durations that are longer than other TBF durations for the equipment. The system may determine, from the sensor data corresponding to operation of the equipment during the plurality of TBF durations, a plurality of measured sensor values for the equipment. Additionally, the system may determine a subset of the measured sensor values corresponding to a largest number of the TBF durations of the plurality of TBF durations. The system may further determine at least one operating parameter value for the equipment based on the subset of the measured sensor values. The system may send a control signal for operating the equipment based on the operating parameter value and/or a communication based on the operating parameter value.

Abstract: Techniques for determining range of electric vehicles are described. A sensor provides a signal indicative of the current being supplied by a battery of an electric vehicle to a motor of the electric vehicle. A controller receives the signal and determines the current supplied by the battery. The controller also receives a voltage supplied by the battery and determines a notional distance travelled by the electric vehicle. Based on the voltage, the current, and the notional distance, the controller determines the range of the electric vehicle.

Abstract: A method for reinforcement learning (RL) of continuous actions. The method may include receiving a state as input to at least one actor network to predict candidate actions based on the state, wherein the state is a current observation; outputting the candidate actions from the at least one actor network; receiving the state and the candidate actions as inputs to a plurality of distributional critic networks, wherein the plurality of distributional critic networks calculates quantiles of a return distribution associated with the candidate actions in relation to the state; outputting the quantiles from the plurality of distributional critic networks; and selecting an output action based on the candidate actions and the quantiles.

Abstract: A method for detecting an anomaly in time series sensor data. The method may include identifying a noisiest cycle from the time series sensor data; for an evaluation of the noisiest cycle indicative of the anomaly being detected at a confidence level above a threshold, providing an output associated with the noisiest cycle as being the anomaly; and for the evaluation of the noisiest cycle indicative of the anomaly being detected at the confidence level not above the threshold: identifying a cycle from the time series sensor data having a most differing shape; and providing the output associated with the cycle having the most differing shape as being the anomaly.

Abstract: K-nearest multi-agent reinforcement learning for collaborative tasks with variable numbers of agents. Centralized reinforcement learning is challenged by variable numbers of agents, whereas decentralized reinforcement learning is challenged by dependencies among agents' actions. An algorithm is disclosed that can address both of these challenges, among others, by grouping agents with their k-nearest agents during training and operation of a policy network. The observations of all k+1 agents in each group are used as the input to the policy network to determine the next action tor each of the k+1 agents in the group. When an agent belongs to more than one group, such that multiple actions are determined for the agent, an aggregation strategy can be used to determine the final action for that agent.

Abstract: An apparatus for predicting a characteristic of a system is provided. The apparatus may include a memory and at least one processor coupled to the memory. The at least one processor may be configured to perform a method including measuring, at a high sample rate, data relating to an operation of the system over a first time period. The method may further include producing a two-dimensional (2D) time-and-frequency input data set by applying a wavelet transform to the measured data. The method may additionally include generating a set of one or more values associated with one or more system characteristics by processing the 2D time-and-frequency input data set using a functional neural network (FNN).

Abstract: Example implementations involve fault detection and isolation in industrial networks through defining a component as a combination of measurements and parameters and define an industrial network as a set of components connected with different degrees of connections (weights). Faults in industrial network are defined as unpermitted changes in component parameters. Further, the fault detection and isolation in industrial networks are formulated as a node classification problem in graph theory. Example implementations detect and isolate faults in industrial networks through 1) uploading/learning network structure, 2) detecting component communities in the network, 3) extracting features for each community, 4) using the extracted features for each community to detect and isolate faults, 5) at each time step, based on the faulty components provide maintenance recommendation for the network.

Abstract: Example implementations described herein are directed to a system for manufacturing dispatching using reinforcement learning and transfer learning. The systems and methods described herein can be deployed in factories for manufacturing dispatching for reducing job-due related costs. In particular, example implementations described herein can be used to reduce massive data collection and reduce model training time, which can eventually improve dispatching efficiency and reduce factory cost.

Abstract: Example implementations described herein can involve systems and methods involving, for receipt of input data from one or more assets, identifying and separating different event contexts from the input data; training a plurality of machine learning models for each of the different event contexts; selecting a best performing model from the plurality of machine learning models to form a compound model; selecting a best performing subset of the input data for the compound model based on maximizing a metric; and deploying the compound model for the selected subset.

Abstract: Example implementations described herein are directed to systems and methods for predicting if a conjunction of multiple events will occur within a certain time. It relies on an approximate decomposition into subproblems and a search among the possible decompositions and hyperparameters for the best model. When the conjunction is rare, the method mitigates the problem of data imbalance by estimating events that are less rare.

Abstract: Example implementations involve systems and methods to create robust visual inspection datasets and models. The novel method learns and transfers damage representation from few samples to new images. The proposed method introduces a generative region-of-interest based adversarial network with the aim of learning a common damage representation and transferring it to an unseen image. The proposed approach shows the benefit of adding damage-region-based component, since existing methods fail to transfer the damages. The proposed method successfully generated images with variations in context and conditions to improve model generalization for small datasets.

Abstract: Systems and methods described herein involve facilitating a recommendation of materials to users, which can involve determining, from a job profile, a job experience level of a user for a job type and equipment type combination; determining, for each material in a database of materials, the job experience level associated with the each material based on an access log to the each material by one or more users and content of the each material to generate a material profile for each of the job experience level; and generating a recommendation of materials from the database for the user based on the determined job experience level of the user and the job experience level associated with the each material.

Abstract: Example implementations described herein involve an approach to address an imperfect simulator challenge using off-line data plus reward modification. The proposed solution is robust to simulator error, and therefore, it requires less maintenance in keeping the simulators updated. Even when the simulators are accurate, it is costly to keep them accurate over time. Moreover, compared to other robust reinforcement learning algorithms, the proposed approach does not assume the distribution of uncertainties in the simulator are known. Less complexity leads to fewer potential errors as well as lower computational cost during the training. Finally, the proposed approach has better performance compared to the state-of-the-art methods (higher overall cumulative rewards).

Abstract: Systems and methods described herein can involve executing a functional generator configured to generate multivariate continuous sensor curves from training with arbitrary multivariate sensor data with irregular timestamps received from one or more apparatuses; executing a functional discriminator to discriminate the generated multivariate continuous sensor curve from the arbitrary multivariate sensor data; and for the functional discriminator discriminating the generated multivariate continuous sensor curve from the arbitrary multivariate sensor data with irregular timestamps, providing feedback to the functional generator to retrain the functional generator.

Abstract: Example implementations described herein involve systems and methods for generating an ensemble of deep learning or neural network models, which can involve, for a training set of data, generating a plurality of model samples for the training set of data, the plurality of model samples generated from deep learning or neural network methods; and aggregating output of the model samples to generate an output of the ensemble models.

Abstract: In some examples, a computer system may receive historical repair data and may extract features from the historical repair data for use as training data. The computer system may determine, from the historical repair data, a repair hierarchy including a plurality of repair levels which includes repair actions as one of the repair levels. Furthermore, the computer system may train the machine learning model, which performs multiple tasks for predicting values of individual levels of the repair hierarchy, by tuning parameters of the machine learning model using the training data.

Abstract: Example implementations described herein involve a new data-driven analytical redundancy relationship (ARR) generation for fault detection and isolation. The proposed solution uses historical data during normal operation to extract the data-driven ARRs among sensor measurements, and then uses them for fault detection and isolation. The proposed solution thereby does not need to rely on the system model, can detect and isolate more faults than traditional data-driven methods, can work when the system is not fully observable, and does not rely on a vast amount of historical fault data, which can save on memory storage or database storage. The proposed solution can thereby be practical in many real cases where there are data limitations.

Abstract: In example implementations described herein, there are systems and methods for processing sensor data from an equipment over a period of time to generate sensor time series data; processing the sensor time series data in a kernel weight layer configured to generate weights to weigh the sensor time series data; providing the weighted sensor time series data to fully connected layers configured to conduct a correlation on the weighted sensor time series data with predictive maintenance labels to generate an intermediate predictive maintenance label; and providing the intermediate predictive maintenance label to an inversed kernel weight layer configured to inverse the weights generated by the kernel weight layer, to generate a predictive maintenance label for the equipment.

Abstract: Example implementations involve a system for Predictive Maintenance using Generative Adversarial Networks for Failure Prediction. Through utilizing three processes concurrently and training them iteratively with data-label pairs, example implementations described herein can thereby generate a more accurate predictive maintenance model than that of the related art. Example implementations further involve shared networks so that the three processes can be trained concurrently while sharing parameters with each other.