10results about How to "Increase risk resistance" patented technology

The invention discloses a two-stage space-time diagram network and multi-source information fusion time sequence probability prediction method and device, and relates to the technical field of artificial intelligence and big data analysis. The method comprises the following steps: acquiring historical wind speed sequence data and corresponding target variable sequence data; preprocessing the data, and constructing a training sample according to a preset time sliding window; constructing a time sequence probability prediction framework of the two-stage space-time diagram network and multi-source information fusion; based on the fluctuation correlation of the historical sequence data, constructing an adjacent matrix between nodes; inputting the training sample and the adjacent matrix between the nodes into a wind speed prediction model, training the model through a designed threshold perception loss function of a wind speed-power nonlinear relationship, and outputting a multi-node wind speed prediction probability of a first stage; and inputting the multi-node wind speed prediction probability and the multi-source environmental factor data into the gradient boosting tree model for second-stage prediction, and outputting a multi-node wind power prediction result. According to the invention, prediction errors can be reduced.

The invention belongs to the technical field of electrical monitoring, and particularly relates to a railway traction substation three-dimensional visual monitoring system, which comprises a data acquisition unit, a data processing unit and a data feedback interaction unit, and is characterized in that the data acquisition unit is used for acquiring working condition data of electrical equipment in a railway traction substation; comprising a fixed acquisition module and a mobile acquisition module; according to the invention, image information acquisition is carried out on dead corners which are difficult to cover by the fixed acquisition module through the mobile trolley, comprehensive coverage and full monitoring of the railway traction substation are realized under dynamic and static cooperation mutual verification, and the safety and reliability degree of information acquisition is improved; moreover, when the information acquisition devices corresponding to the fixed acquisition modules in part of the areas break down, the mobile trolley can be controlled to go to the fault area as a supplement, so that the blank of a monitoring network is filled, and the anti-risk capability of the whole railway traction substation monitoring system is improved.

The invention discloses a supply chain node toughness dynamic evaluation method based on information entropy, and belongs to the field of supply chain network toughness research. The method comprises the steps of calculating efficiency and redundancy of enterprise nodes in supply and demand directions based on an information entropy theory; according to the roles of the enterprise nodes in the supply chain network, performing weighted fusion to obtain the total efficiency and the total redundancy of the enterprise nodes; by comprehensively considering efficiency and redundancy, dynamic quantification of enterprise node toughness is realized. In addition, node toughness driving mechanism diagnosis based on an internal structure is further introduced, and internal structure factors for driving node toughness fluctuation are accurately recognized through exponential decomposition and sensitivity analysis. According to the method disclosed by the invention, dynamic quantification and attribution analysis of the fine-grained toughness of the enterprise node level based on the supply and demand bidirectional dependency relationship are realized, and powerful decision support is provided for accurately positioning the fragile link of the supply chain, optimizing the structure of the supply chain and improving the overall anti-risk capability of the supply chain.

This application discloses a method and system for stable hydrogen supply planning in a hydrogen production system considering electrolyzer failures, relating to the field of new energy hydrogen production. The method includes acquiring parameter data, historical new energy output data, and historical hydrogen load data of a new energy hydrogen production system containing multiple electrolyzers; constructing multi-state switching models for the electrolyzers, an electrolyzer operation model, an energy storage battery operation model, and a hydrogen storage tank operation model; then constructing a mathematical model for planning the new energy hydrogen production system; and finally, using clustering algorithms and a two-layer iterative solution algorithm to solve the mathematical model for planning the new energy hydrogen production system, determining the optimal capacity planning scheme for each electrolyzer, energy storage battery, and hydrogen storage tank in the new energy hydrogen production system. This application can incorporate the uncertainty of electrolyzer failures into the hydrogen production system planning model, improve the multi-state characterization of the electrolyzers, achieve optimal capacity planning for each device in the new energy hydrogen production system, and ensure a stable and reliable supply of green hydrogen.

The invention provides a multi-source data fused power equipment fault root cause analysis method and system. The method comprises the steps of performing credibility evaluation on multi-source power equipment data; the power equipment comprises sensing monitoring data, operation and maintenance record data and power grid topology data; calculating a fusion weight according to a credibility evaluation result; fusing the power equipment data by using the fusion weight to obtain an equipment fault feature vector; performing correlation calculation on the fault root causes and the key features to obtain a correlation matrix; performing root cause matching degree calculation and screening according to the incidence matrix and the equipment fault feature vector to obtain candidate root causes; constructing a Bayesian network according to the candidate root causes and the corresponding key features, dynamically initializing the conditional probability of the Bayesian network by using real-time data update factors according to an incidence matrix, and adjusting the Bayesian network by using fault reasoning knowledge of a fault knowledge graph; and performing root cause screening on the equipment fault feature vector by adopting a Bayesian network to obtain a power equipment matching fault root cause and a corresponding confidence coefficient. Through the scheme, the accuracy and the disposal efficiency of fault root cause analysis in a complex scene can be improved, and the operation and maintenance cost is reduced.

The application discloses an AI digital customer service device based on an offline large model and an intelligent interaction method. The device is deployed on a user terminal device. The device can complete intelligent interaction without cloud and network, ensuring the continuity and stability of customer service. A lightweight offline large model is used for running, without occupying high server computing power and storage space. It can be directly adapted to various ordinary user terminal devices, and is convenient to deploy and has strong hardware adaptability. Through a knowledge base management module, standardized and structured enterprise customer service knowledge can be stored and managed, and business-related enterprise customer service knowledge can be called as needed, which is beneficial to realize the standardized output of user instruction data and response speech, get rid of the dependence on personal experience of customer service personnel, accurately locate the core problem of customers and formulate a scientific solution method. With the help of the thinking chain technology, the related enterprise customer service knowledge is integrated, combed and logically deduced, and the standardized answer with clear logic and unified format is output.

The utility model relates to the technical field of pipeline beveling machine locking, and provides a pipeline beveling machine locking device which comprises a limiting table, and a fixing shaft is fixedly connected to the side wall of the limiting table. The side wall of the fixing shaft is slidably connected with a sliding cylinder. The side wall of the sliding cylinder is rotationally connected with rotating blocks, and the side walls of the multiple rotating blocks are rotationally connected with limiting blocks. The end part of the limiting block is fixedly connected with a clamping block; a push block is fixedly connected to the side wall of the sliding cylinder. A hydraulic cylinder is arranged on the side wall of the push block; the bottoms of the two hydraulic cylinders are fixedly connected with hydraulic tables correspondingly. The hydraulic cylinder is arranged to drive the sliding barrel, so that the multiple clamping blocks are clamped on the side wall of the pipeline, automatic rapid locking of the pipeline is facilitated, convenience is provided for pipeline locking actions of workers, physical exhaustion of the workers is reduced, and working efficiency is improved.

The application relates to an adaptive direct-current input interface circuit and a driving method thereof. The circuit comprises a voltage comparison module, an adaptive protection module and a voltage reference module. The voltage reference module performs voltage stabilization processing on a target direct-current power supply to obtain a reference direct-current power supply and transmits the reference direct-current power supply to the voltage comparison module. The voltage comparison module divides the voltage of two types of power supplies to obtain a to-be-detected voltage and a reference voltage and obtains a voltage comparison result according to the difference between the to-be-detected voltage and the reference voltage. The adaptive protection module performs polarity detection on the target direct-current power supply to obtain a power supply polarity detection result. According to the two types of results, if the target direct-current power supply is of a positive polarity and is within a voltage control range, the adaptive protection module turns on the connection between the target direct-current power supply and a subsequent circuit; if the target direct-current power supply is of the positive polarity and is not within the voltage control range, the adaptive protection module blocks the corresponding connection; and if the target direct-current power supply is of a reverse polarity, the adaptive protection module blocks the corresponding connection. The method can realize adaptive identification and protection control of a direct-current input interface under an abnormal power supply scene.

The invention discloses an advertisement type photovoltaic energy-saving outdoor garbage can. The advertisement box comprises a base, a shell is arranged at the top of the base, advertisement frames and sliding grooves are arranged on the two sides of the two ends of the shell, push-pull plates are arranged on the two sides of the shell in a sliding mode, and inner barrels are arranged at the top ends of the push-pull plates. According to the outdoor garbage can advertising machine, the outdoor garbage can advertising machine is divided into the shell and the lifting shell, in the carrying and assembling process of installation personnel, due to the fact that the shell is sleeved with the lifting shell, the size of the outdoor garbage can advertising machine is reduced, the installation personnel can carry and assemble the outdoor garbage can advertising machine conveniently, and in case of severe weather, the installation personnel can unlock the clamping pieces; when the outdoor garbage can advertising machine is used, the bolts at the round holes are removed, an installer can contract the shell and the lifting shell, the disaster area of the outdoor garbage can advertising machine in severe weather is reduced, the anti-risk effect of the outdoor garbage can advertising machine in severe weather is improved, and therefore the outdoor garbage can advertising machine is prevented from being damaged in severe weather.

The invention provides a hydropower station project group dynamic investment decision-making method considering uncertainty, and relates to the technical field of hydropower project investment decision-making, and the method comprises the steps: S1, constructing a dynamic element perception and iteration engine, and obtaining a basic decision-making data source of a hydropower project group according to the dynamic element perception and iteration engine; extracting a plurality of decision-making elements from the basic decision-making data source, and dividing the plurality of decision-making elements into static basic elements and dynamic sensitive elements; according to the dynamic sensitive elements, through a real-time data and high-frequency feature analysis technology, an evaluation threshold interval is dynamically calculated and corrected, and a real-time iterative dynamic element library is formed. A multi-dimensional static evaluation system fused with expert experience can be upgraded into a decision support system capable of embedding a key uncertainty dynamic evolution model and performing adaptive simulation and optimization according to time sequence information input, so that a dynamic portfolio strategy with higher anti-risk capability is output.