157 results about "Predictive systems" patented technology

The invention discloses an operation collaborative optimization method for an optical storage direct current flexible interaction system. Comprising the steps of collecting operation data such as photovoltaic output, an energy storage state, household load power and direct current bus transmission power, fusing power market price information, and constructing a multi-dimensional time series data set; then, predicting an adjustable load capacity interval of the system based on a coupled physical constraint neural network model embedded with DC bus power balance, voltage constraint and equipment operation limitation; further constructing a state-action space, solving a Pareto frontier by adopting a multi-objective optimization algorithm, and generating a light storage and home load collaborative scheduling strategy set; then combining the real-time operation state and the prediction deviation information, applying a voltage-power droop control mechanism to carry out strategy decoupling, and generating an energy storage power correction amount and a flexible load priority control instruction; and finally, a control instruction is issued to the optical storage direct flexible system, so that collaborative optimization operation with consideration of economical efficiency, safety and comfort of the system is realized.

The invention provides a virtual power plant energy storage system co-scheduling and control method and system, and relates to the technical field of power management, and the method comprises the steps: obtaining power grid scheduling data, calculating the charge and discharge income, collecting the real-time parameters of a battery, analyzing the performance attenuation law through deep reinforcement learning, determining the initial working parameters, predicting the system state based on a rolling time domain, and obtaining the real-time parameters of the battery. An optimal scheduling scheme is calculated through mixed integer linear programming and model prediction control in combination with a power distribution strategy and is corrected in real time, operation is executed according to a time-phased scheduling instruction and is monitored in real time, and an emergency strategy is started when necessary, so that the economic benefit and the safety of an energy storage system are improved, and the service life of a battery is prolonged.

Methods and systems for managing data processing systems are disclosed. A data processing system may include and depend on the operation of hardware and / or software components. Inference models may be implemented to predict future system infrastructure outcomes (e.g., component failures) using information recorded in logs that reflect the operation of the components. However, the models may be complex “black boxes” and may generate critical outcome predictions for downstream consumers without explanations of how the predictions are determined, resulting in downstream consumers having low confidence in the predictions. Therefore, hidden knowledge (e.g., structured knowledge attributes) of the models may be extracted and / or used to understand the underlying processes that the models use to predict the system infrastructure outcomes. The hidden knowledge may be provided for interactively managing data processing system(s) failures in order to increase the likelihood of preventing and / or mitigating future data processing system failures.

Methods and systems for managing data processing systems are disclosed. A data processing system may include and depend on the operation of hardware and / or software components. Inference models may be implemented to predict future system infrastructure outcomes (e.g., component failures) using information recorded in logs that reflect the operation of the components. However, the models may be complex “black boxes” and may generate critical outcome predictions for downstream consumers without explanations of how the predictions are determined, resulting in downstream consumers having low confidence in the predictions. Therefore, hidden knowledge (e.g., structured knowledge attributes) of the models may be extracted and / or used to understand the underlying processes that the models use to predict the system infrastructure outcomes. The hidden knowledge may be provided for interactively managing data processing system(s) failures in order to increase the likelihood of preventing and / or mitigating future data processing system failures.

Methods and systems for managing data processing systems are disclosed. A data processing system may include and depend on the operation of hardware and / or software components. Inference models may be implemented to predict future system infrastructure outcomes (e.g., component failures) using information recorded in logs that reflect the operation of the components. However, the models may be complex “black boxes” and may generate critical outcome predictions for downstream consumers without explanations of how the predictions are determined, resulting in downstream consumers having low confidence in the predictions. Therefore, hidden knowledge (e.g., structured knowledge attributes) of the models may be extracted and / or used to understand the underlying processes that the models use to predict the system infrastructure outcomes. The hidden knowledge may be stored in a repository and may be provided for downstream use in order to increase the likelihood of preventing and / or mitigating future data processing system failures.

The invention discloses a modularized intelligent tubular column conveying system based on digital twinning and self-adaptive control, and belongs to the technical field of digital twinning. The modularized intelligent tubular column conveying system is characterized in that a digital twinning model integrating a mechanical structure, electrical control and hydraulic power attributes is constructed; acquiring multi-source sensing data including an image sequence, a three-dimensional point cloud and vibration acceleration in real time, driving the digital twin model to perform synchronous simulation, and calculating a deviation value between the digital twin model and internal simulation data; on the basis of the deviation value, a control logic parameter adjusting instruction is generated through a predefined mapping rule, then updated control logic parameters are executed, and a complete pipe column conveying process is simulated to generate a predictive system state sequence; and finally, the safety-related state subsets are issued to a field controller to guide and execute preventive actions. According to the invention, deep fusion and closed-loop control of digital twinning and physical entities are realized, and the debugging efficiency, the environmental adaptability and the operation safety of a tubular column conveying system are effectively improved.

The invention discloses an artificial intelligence-driven industrial Internet of Things equipment fault prediction system, and relates to the technical field of industrial Internet of Things and predictive maintenance, an edge-cloud collaborative architecture is adopted, real-time acquisition, preprocessing and online fault prediction of industrial equipment sensing data are realized, the system uses a Transform neural network to construct a hierarchical spatio-temporal model, and the fault prediction of the industrial equipment sensing data is realized. Time sequence data are processed in a segmented mode through a sliding window method, a causal reasoning enhancement mechanism is integrated, an industrial equipment causal atlas is constructed, attention masks are generated, a model is focused on key features, and therefore prediction accuracy and interpretability are improved, meanwhile, a closed-loop continuous optimization mechanism is established by the system, and prediction efficiency is improved. And an edge fault prediction result and actual operation feedback are uploaded to a cloud, a causal atlas and model parameters are updated, adaptive optimization of the model is realized, and the system provides efficient, accurate and explainable decision support for preventive maintenance of industrial equipment.

The invention relates to the technical field of inventory optimization, in particular to an intelligent supply chain demand prediction and inventory optimization system, which comprises a supply chain dynamic demand prediction module for intelligently predicting the demand quantity of a supply chain, and an inventory intelligent optimization module for intelligently optimizing the inventory according to the demand prediction result of the supply chain. The prediction correction and optimization adjustment module is used for dynamically correcting demand prediction and intelligently optimizing and adjusting inventory; according to the invention, through establishment of a three-channel cross validation prediction and anomaly elimination mechanism, single-channel prediction anomaly can be resisted, the stability and accuracy of supply chain demand prediction are improved, and inventory risks caused by prediction errors are reduced; the safe inventory level is dynamically set according to different stages, so that the inventory strategy better conforms to the commodity market change, and the shortage rate and the unsalable inventory are reduced; the correction amplitude is dynamically adjusted through error fluctuation, excessive correction is avoided, and the self-learning and self-evolution ability of a long-term supply chain prediction system is improved.

The present disclosure relates to the field of Controlled Environment Agriculture (CEA). It details a predictive method and system for optimizing the use of resources and crop productivity in indoor farming across an entire crop cycle. The present disclosure provides for a predictive method and system for optimizing resource use and crop productivity in indoor farming. According to one aspect of the present disclosure, a predictor for optimizing resource use and crop productivity in indoor farming. According to a second aspect of the present disclosure, a predictive system for optimizing resource use and crop productivity in indoor farming. According to a third aspect of the present disclosure, a method of using a predictive system for optimizing resource use and crop productivity in indoor farming.

Methods and systems for managing data processing systems are disclosed. A data processing system may include and depend on the operation of hardware and / or software components. Inference models may be implemented to predict future system infrastructure outcomes (e.g., component failures) using information recorded in logs that reflect the operation of the components. However, the models may be complex “black boxes” and may generate critical outcome predictions for downstream consumers without explanations of how the predictions are determined, resulting in downstream consumers having low confidence in the predictions. Therefore, hidden knowledge (e.g., structured knowledge attributes) of the models may be extracted and / or used to understand the underlying processes that the models use to predict the system infrastructure outcomes. The hidden knowledge may be used to generate citations for the outcome predictions to provide references to previous cases (e.g., historic data) from which the outcome predictions are based.

The invention relates to the technical field of intelligent retail and big data analysis, and discloses a multi-retail store sales volume prediction method and system based on an improved Transform architecture, and the method comprises the steps: collecting historical retail store sales data, historical weather characteristics and holiday and festival data, carrying out the correlation, and carrying out the preprocessing of the collected data; dynamically constructing and training a store sales volume prediction model based on a deep learning neural network, and obtaining gated store-level features and product cluster features which have important influence on sales volume prediction through a multi-level attention mechanism; and fusing external covariables with the gated store-level features and the product cluster features to enhance the prediction capability of the model, and predicting the sales volume of the multiple retail stores based on the trained store sales volume prediction model. According to the multi-retail store sales volume prediction system realized through the method, more comprehensive and more accurate sales volume prediction is realized through interactive analysis of stores and products and comprehensive modeling of external environment variables.

The invention discloses an efficient circulating water heating system based on a heat pump and a control method thereof.The system comprises a multi-stage heat pump system, a circulating water heating loop and an intelligent control unit, and the multi-stage heat pump system is used for increasing heat energy of a low-temperature heat source stage by stage to heat circulating water; the intelligent control unit is integrated with a data acquisition module, a load prediction module, a system modeling module, a parameter optimization module, an instruction issuing module and a performance evaluation module, and can realize thermal load dynamic prediction and thermal performance modeling and optimization control of the heat pump system. The control method is based on deep learning and model prediction control, combines real-time data and an external scheduling instruction, calculates an optimal operation parameter to improve the system energy efficiency ratio or reduce the operation cost, and continuously optimizes prediction and modeling precision through an adaptive learning mechanism. The system has the capacity of intelligent prediction, accurate control, efficient heat transfer and self-optimization, is suitable for occasions such as industries and buildings with high requirements for hot water supply energy efficiency, and remarkably improves the operation efficiency and stability of the system.

The invention relates to the technical field of geothermal energy utilization and underground heat exchange, in particular to a medium-deep layer buried pipe heat exchanger seepage thermal response rapid prediction method based on artificial intelligence, and the method comprises the steps: obtaining temperature field snapshot data of a medium-deep layer buried pipe heat exchanger system under different operation conditions; performing orthogonal decomposition on the temperature field snapshot data to obtain main modal characteristics and corresponding amplitudes; the parameters of all the operation conditions serve as input variables, all the main modal features and the corresponding amplitudes serve as output variables, a BP neural network is trained, and an artificial intelligence agent model is constructed; and obtaining parameters of a target operation condition, inputting the parameters into the artificial intelligence agent model, outputting the amplitude of each main mode under the target operation condition, reconstructing a temperature field, and completing rapid prediction of the seepage thermal response of the medium-deep layer buried pipe heat exchanger under the target operation condition. According to the method, the temperature field distribution of the DBHE system under the action of underground water seepage can be quickly predicted.

Methods and systems for managing data processing systems are disclosed. A data processing system may include and depend on the operation of hardware and / or software components. Inference models may be implemented to predict future system infrastructure outcomes (e.g., component failures) using information recorded in logs that reflect the operation of the components. However, the models may be complex “black boxes” and may generate critical outcome predictions for downstream consumers without explanations of how the predictions are determined, resulting in downstream consumers having low confidence in the predictions. Therefore, hidden knowledge (e.g., structured knowledge attributes) of the models may be extracted and / or used to understand the underlying processes that the models use to predict the system infrastructure outcomes. The hidden knowledge may be utilized interactively (e.g., using AI chatbots) to provide users with failure prediction responses that allow users to better remediate failures of the data processing systems.

The present invention embodiments provide a forecasting system that derives carbon intensity, emissions, and environmental impact forecasts from a life cycle assessment (LCA). The forecasting system offers an intuitive, user-friendly interface that simplifies the complexity of forecasting methodologies, making generating forecasts of carbon intensity, emissions, and environmental impacts accessible to a broader audience. It incorporates advanced algorithms and real-time data integration, ensuring accurate and up-to-date forecasts. Additionally, the forecasting system is designed with a modular architecture and is highly configurable, allowing seamless integration with various industries and accommodating diverse products and processes.

The invention relates to a data-driven criminal period prediction system, belongs to the technical field of artificial intelligence, solves the problems of insufficient accuracy, poor regional adaptability and the like of prisoner classification and criminal period prediction in the prior art, and provides a multi-model fusion provincial prisoner classification and criminal period prediction system based on real judicial sentencing logic. The system comprises an input display module, a legal judgment element extraction module, a sentency and insignment prediction module, a sentency judgment prediction module and a judgment output display module, and can effectively improve the prediction precision and optimize judicial decision support by fusing multiple advanced algorithms and combining judicial practices of different provinces. The method has a wide application prospect and a strong regional adaptation capability.

Methods and systems for managing data processing systems are disclosed. A data processing system may include and depend on the operation of hardware and / or software components. Inference models may be implemented to predict future system infrastructure outcomes (e.g., component failures) using information recorded in logs that reflect the operation of the components. However, the models may be complex “black boxes” and may generate critical outcome predictions for downstream consumers without explanations of how the predictions are determined, resulting in downstream consumers having low confidence in the predictions. Therefore, hidden knowledge (e.g., structured knowledge attributes) of the models may be extracted and / or used to understand the underlying processes that the models use to predict the system infrastructure outcomes. The hidden knowledge may be stored in a repository and may be provided for downstream use in order to increase the likelihood of preventing and / or mitigating future data processing system failures.

Methods and systems for managing data processing systems are disclosed. A data processing system may include and depend on the operation of hardware and / or software components. Inference models may be implemented to predict future system infrastructure outcomes (e.g., component failures) using information recorded in logs that reflect the operation of the components. However, the models may be complex “black boxes” and may generate critical outcome predictions for downstream consumers without explanations of how the predictions are determined, resulting in downstream consumers having low confidence in the predictions. Therefore, hidden knowledge (e.g., structured knowledge attributes) of the models may be extracted and / or used to understand the underlying processes that the models use to predict the system infrastructure outcomes. The hidden knowledge may be provided for interactively managing data processing system(s) failures in order to increase the likelihood of preventing and / or mitigating future data processing system failures.

Systems, methods, and computer-readable storage media for aggregating media (and commentary on that media) into a topology. To do so, the system receives first content (and associated metadata) as well as second content (and associated metadata). The system then generates a topology based on a relationship between the first content and the second content, where the topology has a number of dimensions based on the metadata of the different pieces of content. The system then compares the topology and the metadata to previously stored topologies and / or metadata and, based on that comparison, executes a machine learning algorithm. The output of that machine learning algorithm includes predicted future changes to the topology, which the system uses to reduce the number of dimensions within the topology.

A computer-implemented system for short-term stock price prediction, consisting of: • a data acquisition module (101) configured to retrieve historical intraday stock data including closing prices, trading volumes and technical indicators; • a data preprocessing module (102) configured to normalize the data and generate temporally consecutive samples using a sliding window approach; • a neural network module (103) comprising a Gated Recurrent Unit (GRU) architecture configured to receive the temporally consecutive samples and output intermediate stock price predictions; • a gradient boosting module (104) comprising an Extreme Gradient Boosting (XGBoost) regressor configured to receive the output of the GRU module along with associated residual features and to refine the predictions by modeling nonlinear patterns and residual errors; • and an output module (105) configured to present the final refined stock price prediction, where the GRU module is trained to minimize a loss function for the mean squared error, and the XGBoost module is trained to minimize an objective function for the squared error, thereby providing improved predictive accuracy for financial time series forecasts.

The invention relates to the technical field of electric power management, and particularly discloses a multi-element load short-term prediction system for an electric power system, and the system obtains an actual operation data source and a meteorological data source of a power grid through a multi-source data collection platform, and carries out the preprocessing of the data sources. The method comprises the steps of extracting local fluctuation characteristics according to an actual operation data source and a meteorological data source of a power grid, fusing to generate a composite data sequence, designing a load trend sensing model based on the operation data sequence and the composite data sequence to analyze a power load recovery trend, responding to power grid dispatching according to a prediction result, and forming a feedback closed loop. The prediction and scheduling strategy is continuously corrected and optimized, internal and external multi-dimensional information is fused, and the system structure of short-term fluctuation and long-term trend is considered, so that the prediction precision is improved, and the robustness and the adaptive capacity of the system are remarkably enhanced.

The disclosed system provides advanced mission control predictive systems for low earth orbit semi-autonomous satellites. In operation, the system may include a satellite transit behavior prediction module configured to train a neural network based on current and past satellite orbital transit paths so as to predict future transit paths. Knowing precise future satellite transit paths enables a ground-based satellite control system to more efficiently (and with greater accuracy) control certain operations of the satellites. For example, a ground-based satellite control system can prepare for communications to commence at a particular time. Legacy systems can only predict one or two days in advance However, using a neural network that not only takes into consideration historical transit data, but also learned details such as solar wind, cloud patterns, etc., the neural network predicts future satellite transit paths with statistically-certain accuracy leading to a much narrower cone of uncertainty.

A Thermal Performance Forecast approach is described that can be used to forecast heating and cooling fuel consumption based on changes to user preferences and building-specific parameters that include indoor temperature, building insulation, HVAC system efficiency, and internal gains. A simplified version of the Thermal Performance Forecast approach, called the Approximated Thermal Performance Forecast, provides a single equation that accepts two fundamental input parameters and four ratios that express the relationship between the existing and post-change variables for the building properties to estimate future fuel consumption. The Approximated Thermal Performance Forecast approach marginally sacrifices accuracy for a simplified forecast. In addition, the thermal conductivity, effective window area, and thermal mass of a building can be determined using different combinations of utility consumption, outdoor temperature data, indoor temperature data, internal heating gains data, and HVAC system efficiency as inputs.

The present application relates to the field of safety science and technology, and provides a dissipative analysis method of system failure process, the system failure evolution process is a changing process influenced by the outside world, and the method is provided for determining the dissipative property thereof; the characteristics of the system failure evolution process are discussed, the dissipative property of the evolution is studied, and a calculation method of key parameters in the dissipative structure is proposed; the evolution process satisfies four conditions of the dissipative structure; the calculation method of the key parameters can be constructed with the aid of the physical meaning of the evolution process and the mathematical method of the spatial failure network, so as to quantitatively calculate and judge the dissipative property of the evolution process; and the method can be used to judge and predict the influence of the final result of the system failure evolution process on subsequent events. The present application can quantitatively calculate and judge the dissipative property of the system failure evolution process, and according to the result of the dissipative property, whether the system failure evolution process is stable and whether there is a failure overflow risk can be judged.

The application relates to a message middleware domestic substitution adaptation method for power dispatching, which comprises the following steps: step 1: the system is split into independent services, and each service is responsible for a specific function; a lightweight communication protocol is used for communication between the services; step 2: each service instance is independently expanded according to the load condition; step 3: a Docker image is created for each microservice, local development and testing are carried out by using Docker Compose, and automatic deployment, expansion and management are carried out by using Kubernetes; step 4: a local scheduler is deployed on each node, communication of local tasks is realized based on a message middleware, AI technology is used to predict system load and performance bottlenecks, and a message middleware domestic substitution adaptation scheme is optimized; and step 5: according to evaluation indexes, compatibility and stability tests are carried out on the message middleware domestic substitution adaptation scheme. The application can effectively ensure the compatibility and stability of the power dispatching system when the message middleware is domestically substituted.

A factory carbon emission monitoring and prediction system based on artificial intelligence relates to the technical field of carbon emission monitoring. The system divides the factory's overall production process into different production sub-processes, obtains basic information and equipment data of industrial equipment corresponding to each production sub-process, constructs a digital twin model of each production sub-process, obtains the difference set of operation data and emission data of adjacent production sub-processes, constructs a first evaluation model for each production sub-process and a second evaluation model for adjacent production sub-processes, obtains real-time equipment data of each production sub-process, and judges whether the corresponding production sub-process is in an abnormal state by combining the first evaluation model and the second evaluation model. The system can analyze the carbon emission impact relationship between adjacent production sub-processes, effectively judge whether each current production sub-process is in an abnormal state and what kind of abnormal state exists, and provide timely feedback.

The invention relates to the technical field of social network information spreading prediction, and discloses an information spreading prediction method fusing public opinion field effect and a heterogeneous hypergraph. In order to solve the problems that in the prior art, only pairwise user relations are relied on, multi-user group influences cannot be described, different information is subjected to cascade independent processing, and multi-topic competition is not considered, the invention provides a prediction scheme fusing public opinion field effects and heterogeneous hypergraph learning. A heterogeneous hypergraph is constructed to obtain user multivariate relation representation, then a public opinion field effect is utilized to quantify attraction energy of different information topics to a user, attention competition among multiple topics is modeled, and a more real user propagation tendency is obtained; and finally, realizing joint prediction of user interest features and social influence features through an interactive fusion mechanism. The method can be used for scenes of information propagation trend analysis, public opinion monitoring, marketing recommendation, false information early warning and the like.

A machine learning based (ML-based) method and system for forecasting cash flow, is disclosed. Initially, the data associated with business units are obtained from data sources. The data are pre-processed to generate pre-processed data. Features associated with financial information are determined for horizons based on the pre-processed data using a plurality of input AI models. Feature combinations are generated by integrating the features associated with the financial information, for each horizon of the horizons. Forecasts are generated for each horizon for a pre-determined time interval, using a stacked AI model including forecasting models. The generated forecasts for the cash flow of the business units, are provided as an output, to the users on user interfaces associated with electronic devices associated with the users.

The invention relates to the field of manufacturing execution systems and intelligent manufacturing, in particular to a manufacturing execution system management method oriented to production data, which comprises the following steps: a multi-source data acquisition step: acquiring physical sensing state data, manual interaction time data and system scheduling data of a manufacturing execution system, and integrating to generate multi-source heterogeneous production data; a trust quantitative evaluation step of quantifying the distortion degree of the execution state based on the multi-source heterogeneous production data to obtain an execution trust entropy; a cross validation prediction step: comparing the physical sensing state data with the man-machine interaction time data to calculate execution trust entropy, and predicting system failure risk; a dynamic scheduling decision step: setting a scheduling degradation adjustment mechanism based on execution trust entropy, and outputting a target scheduling instruction to adjust the running state of the system; according to the method, the dynamic balance between pursuit of efficiency and maintenance of authenticity of underlying data is realized, and the vulnerability resistance of the complex manufacturing network is effectively improved.

A system for providing security analytics from surveillance systems using artificial intelligence is provided. In particular, the system monitors an environment of interest utilizing surveillance systems that include sensors for detecting and analyzing events, anomalies, actions, activities, objects, and / or anything of interest. As the system monitors the environment, first content including sensor data from the sensors is loaded into an artificial intelligence model for analysis. The artificial intelligence model compares the first content to second content that is utilized to train or is otherwise associated with the model. If the first content matches and / or correlates with the second content, the system generates a prediction relating to the detection of an object, activity, motion, action, occurrence, and / or anomaly. The system generates a confidence score for the prediction and if the confidence score is at a threshold value, the system may facilitate output of a response in response to the detection.