24 results about "Production risk" patented technology

The invention relates to the technical field of predictive maintenance and health management of industrial equipment, in particular to an intelligent electromechanical integrated monitoring system based on the industrial internet, which comprises a data acquisition module, a data processing module, a data processing module and a data processing module, and is characterized in that the data acquisition module acquires an equipment dynamic operation parameter set, inherent physical attribute parameters and historical maintenance data of target electromechanical equipment; calling preset process topology data, economic loss data and maintenance cost data; the state evaluation module iteratively calculates an accumulated degradation index representing the health condition of the equipment; the importance quantification module calculates a process importance coefficient representing the criticality of the equipment in the production line based on the process topology data; the risk calculation module generates a production risk degree which quantifies the shutdown influence; the decision generation module generates a dynamic maintenance decision instruction; according to the invention, systematic risk cognition from the individual equipment to the overall production line is realized, extensive management of all equipment is avoided, and allocation of maintenance resources is more strategic and targeted.

An adjustable mounting groove structure relates to the technical field of die mounting and comprises a die holder, a plurality of mounting groove groups are arranged at the edge of the die holder, and each mounting groove group comprises at least two mounting grooves; the adjustable mounting module is mounted at the position of the mounting groove group when the die holder and the sliding table are fixed; an adjustable mounting groove is formed in the first end of the adjustable mounting module, and the adjustable mounting groove is aligned with any mounting groove by adjusting the mounting position of the adjustable mounting module and the mounting groove set. According to the mounting conditions of two or more production lines, a plurality of mounting grooves are formed in the positions of the original mounting grooves in the die holder base body, so that quick-clamping chucks on different production lines are provided with the mounting grooves corresponding to the quick-clamping chucks in position, the die can be mounted corresponding to different production lines, and the requirement that when a main production line breaks down suddenly, the die holder base body cannot be damaged due to the fact that the main production line breaks down suddenly is met. The temporary-to-standby production line production demand guarantees production, after the state of the main production line is recovered, the main production line can be rapidly recovered to the main production line installation condition, and the production halt risk and economic loss caused by production line faults are reduced.

The invention relates to the technical field of centrifugal pumps, in particular to an ultra-low specific speed unit transient pressure fluctuation suppression system and method.The method comprises the steps that a segmented broken line type guide vane closing rule is optimized, and decision variables are determined; determining a unit rotating speed water head ratio item in the target function of the multi-target optimization of the guide vane closing rule; according to the method, the'segmented broken line law 'of closing of guide vanes is optimized through a multi-target genetic algorithm, the'rotating speed water head ratio' is taken as a key regulation and control index, transient pressure fluctuation and runner hydraulic thrust are balanced, and the transient pressure fluctuation and the runner hydraulic thrust are controlled. The method is suitable for controlling transition processes such as starting, stopping or sudden load change of an ultralow-specific-speed unit, vibration and noise in the operation process of equipment can be reduced, the service life of the equipment is prolonged, the production efficiency is improved, equipment failures and safety accidents caused by pressure fluctuation are avoided, the production risk is reduced, meanwhile, energy waste is reduced, and the production cost is reduced.

The invention discloses a product evaluation method, device and equipment and a medium, and the method comprises the steps: obtaining a product statistical parameter, a parameter limit value, and a measurement statistical parameter of a measurement system, and the measurement system is used for carrying out the product qualification measurement; determining the production risk probability of the product and the measurement risk probability of the product measured by the measurement system based on the product statistical parameter, the parameter limit value and the measurement statistical parameter of the measurement system; and obtaining an index value corresponding to the product evaluation index based on the production risk probability and the measurement risk probability.

A production risk analysis device (100) comprises: a risk scenario pattern acquisition unit (112) that, on the basis of product-related information (121) including at least one of product specifications and production process information, uses a language model (see a language model server (200)) to acquire a risk scenario pattern pertaining to the production of the product; a causal model generation unit (113) that extracts causal relationships between factors and results included in the risk scenario pattern and generates a causal model (130); and a detailed risk scenario acquisition unit (114) that, on the basis of the product-related information (121) and the causal model (130), uses the language model to acquire a detailed risk scenario pertaining to the production of the product.

The invention relates to an intelligent production scheduling system architecture integrated with deep reinforcement learning and time sequence prediction, which realizes production scheduling strategy autonomous learning, production risk pre-judgment and man-machine collaborative optimization through collaborative linkage of six layers of architectures. The architecture is composed of a data acquisition and fusion layer, a micro-service business core layer, a deep learning engine layer, a production scheduling execution layer, a visual decision-making layer and a system guarantee layer, and multi-source production data is gathered on the basis of the data acquisition and fusion layer; a deep learning engine layer is taken as a core, and production scheduling decision and risk prediction are carried out; the production scheduling execution layer is used as a bridge, and the AI decision is converted into a production instruction; man-machine cooperation is realized through a visual decision-making layer; and finally, a feedback data driving model in the deep learning engine layer is continuously optimized to form a self-evolved intelligent closed loop, the micro-service business core layer provides a necessary business data standardization function, and the system guarantee layer ensures stable operation of the AI service. The method is suitable for the technical field of manufacturing industry production scheduling.

The invention relates to application of a digital twinning technology in the aspect of risk monitoring of chemical production equipment, and discloses a real-time risk monitoring and early warning system for isocyanate production equipment, the classification number is G06Q or G06F, and the keyword is digital twinning. The system comprises a sensor data acquisition module, a data preprocessing module, a digital twinborn simulation module, a risk assessment module, an early warning decision module and an intervention control module. According to the method, the equipment state is predicted through the digital twinborn model, the risk index is calculated, the early warning is generated, and pre-intervention is realized; the method is characterized in that the digital twinning technology is integrated, excessive dependence on sensor precision is reduced, the problems of uncertainty and hysteresis of early warning of an existing system are solved, the technical effect of improving early warning accuracy, timeliness and safety is achieved, and the method is suitable for chemical production risk monitoring.

The invention relates to the technical field of production monitoring, in particular to an industrial safety production monitoring method and system based on AI, and the method comprises the following steps: collecting an omnibearing monitoring video stream of a production environment, carrying out the synchronous calibration, and constructing a synchronous monitoring video stream; performing risk labeling on the synchronous monitoring video stream, and constructing a production environment topology risk field; personnel area matching detection is carried out based on the production environment topology risk field, and a position safety early warning signal is generated; performing action safety logic verification based on the synchronous monitoring video stream, and marking an abnormal operation behavior event; and performing intelligent production monitoring decision based on the position safety early warning signal and the abnormal operation behavior event. According to the invention, the safety early warning efficiency and accuracy of precision industrial production are improved, the production safety is improved, and the generation risk is effectively reduced.

The invention discloses an efficient vertical machining center BOM building method, and belongs to the technical field of machine manufacturing. The method comprises the following steps that S1, a BOM frame is built based on the modular design concept; s2, carrying out association design by utilizing three-dimensional design software; s3, establishing a BOM change management mechanism; and S4, introducing a related research and development product management informatization system. According to the method, the building efficiency is improved, a large amount of manual input work is avoided, and the BOM building time is greatly shortened; the accuracy is improved, human errors are reduced, and the accuracy and integrity of BOM information are ensured; the method adapts to design changes, can quickly respond to the design changes, timely updates BOM information, and effectively reduces production risks and cost increase caused by the design changes. Data management is facilitated, efficient management and utilization of BOM information are achieved, and data query and analysis of links such as production plan making, purchase management and cost control are facilitated.

This invention relates to the field of database construction technology, specifically disclosing a database construction and management method for multi-source data. The method includes the following steps: S1: acquiring and preprocessing multi-source data; S2: establishing an agricultural and rural spatiotemporal database; S3: establishing a first construction management analysis model; S4: establishing a second construction management analysis model; S5: evaluating the construction management quality; and S6: establishing a construction management in-depth analysis model. This invention acquires and preprocesses multi-source data to construct a spatiotemporal database, and evaluates the construction management quality by establishing a first and a second construction management analysis model. This invention achieves the integration and unified management of multi-source agricultural and rural data, significantly improving data quality and application value, providing comprehensive and accurate data support for agricultural analysis, and helping to improve agricultural production efficiency, reduce production risks, and promote sustainable agricultural development.

The application provides an electronic product production risk assessment method and system based on artificial intelligence, relates to the field of risk assessment, and solves the technical problems of fuzzy cause-effect relationship and insufficient response to distribution deviation during electronic product production risk assessment. The method first extracts material, process, equipment and environment heterogeneous elements of the production process, constructs an MPEE standard data set and a heterogeneous cause-effect diagram; collects real-time MPEE data through a fixed time sliding window to construct a sliding window data set, detects the distribution deviation degree of the data set from the standard data set by using a kernel function, sets a threshold value in combination with process stability and locates the deviation nodes, realizes dynamic updating of the heterogeneous cause-effect diagram, inputs the real-time data into a risk assessment model trained by a deep neural network to obtain a risk result, reversely traverses a cause-effect path based on the risk level and the heterogeneous cause-effect diagram, completes root cause positioning and impact degree quantification, and finally matches a process knowledge base strategy and selects an optimal execution strategy.

The invention discloses an intelligent operation management method and platform for the whole process of industrial production, and relates to the technical field of operation management, and the method comprises the steps: obtaining corresponding equipment state data flow, production state data flow and material state data flow, performing coupling hidden danger prediction under multi-node fault tracing on the current production scheme to establish an equipment associated production hidden danger space; introducing a production risk identification network to carry out risk-driven process environment coupling hidden danger prediction on the current production scheme, and establishing a process environment coupling hidden danger space; carrying out material support adaptation associated hidden danger prediction on the current production scheme, and building a material support associated hidden danger space; and according to the plurality of hidden danger spaces, collaboratively optimizing the current production scheme, obtaining a production optimization strategy, encrypting and sending to a management cockpit of the thermal power plant. The technical problem of inaccurate production scheme optimization in the prior art is solved, and the technical effects of realizing accurate prediction of production hidden dangers and improving the overall optimization effect of the production scheme are achieved.

A computer-implemented method for testing a risk model trained to output a risk determination for open banking transactions that includes: unit testing the risk model implemented in an application programming interface (API) platform; performing manual and automated feature validation of the risk model by comparing feature outputs from the risk model to expected feature output values; performing functional validation of the risk model according to an accuracy metric; benchmark testing the risk model, implemented in the API platform, using simulated scenario test data sets; load testing the risk model; after performing the foregoing, deploying the risk model as a production risk model with a web portal in a production environment; and dog-food testing the production risk model using a plurality of simulated scenario test data sets configured to simulate real production usage.

This invention discloses an industrial safety production risk perception method and system based on an LLM (Limited Least Mechanism) agent, relating to the field of industrial data processing technology. The method includes: during tank leak repair, predicting the set of hazardous gas concentrations in area A within a repair time window based on historical hazardous gas concentration monitoring records; acquiring images of protective equipment worn by personnel going to area A for repair within the preset repair time window, performing wear feature recognition to obtain the fit, and obtaining the filter canister model and effective pressure difference accumulation duration; using an abnormal risk perception engine trained on an LLM agent, deriving the predicted probability of abnormal protection risk based on the predicted hazardous gas concentration set, fit, filter canister model, and effective pressure difference accumulation duration; and issuing a protective risk warning to personnel if the risk exceeds a preset threshold. This invention effectively improves the accuracy and reliability of industrial safety production risk perception.

The invention discloses a packaging production risk early warning system fused with time sequence modeling, and the system comprises the following modules: a data collection and preprocessing module which is used for collecting multi-modal perception data and carrying out the preprocessing of the multi-modal perception data; the time alignment module is used for performing time alignment by using an improved Soft-DTW algorithm; the technological process mapping module is used for generating a risk causal map according to the standard production process of the packaged product and the multi-modal unified data sample set; the anomaly judgment module is used for carrying out anomaly identification on the collected real-time multi-modal sensing data based on an index rule base; the risk scoring module is used for calculating an accumulated abnormal score of each batch of products based on the abnormal judgment result set; and the risk diffusion and response module is used for calling the risk causal atlas to track the risk path of the downstream process and generating a risk diffusion response list. According to the invention, multi-modal sensing and time sequence modeling are fused, and the intelligent risk early warning system for the packaging production line is constructed.

A computer-implemented method for testing a risk model trained to output a risk determination for open banking transactions that includes: unit testing the risk model implemented in an application programming interface (API) platform; performing manual and automated feature validation of the risk model by comparing feature outputs from the risk model to expected feature output values; performing functional validation of the risk model according to an accuracy metric; benchmark testing the risk model, implemented in the API platform, using simulated scenario test data sets; load testing the risk model; after performing the foregoing, deploying the risk model as a production risk model with a web portal in a production environment; and dog-food testing the production risk model using a plurality of simulated scenario test data sets configured to simulate real production usage.

This invention discloses a method and system for early warning of safety production risks, relating to the field of safety production management technology. The method includes collecting multimodal data from the production site, preprocessing and fusing the multimodal data to form a fused feature dataset; analyzing the fused feature dataset to determine risk characteristics, and calibrating these risk characteristics, including parametric and descriptive calibration, and analyzing the calibrated content to determine risk hazard values; determining the preset risk hazard value range to which the risk hazard value belongs, and further determining the early warning level. This invention achieves deep fusion of multimodal data and intelligent risk identification, significantly improving the accuracy, timeliness, and interpretability of safety production risk early warning.

The invention provides a production risk prediction method, relates to the field of artificial intelligence, and can be applied to the field of financial science and technology. The production risk prediction method comprises the steps of obtaining a demand item data set and a production keyword; calculating the importance score of each demand item in the demand item data set; taking the demand item of which the importance score meets a first preset condition as a key demand item, and obtaining text information of the key demand item from the demand item data set; inputting the text information into a pre-trained deep learning model to obtain risk keywords and risk category identification results corresponding to the key demand items; performing matching based on a pre-constructed historical problem database to obtain historical risk data corresponding to the key demand items and the risk keywords; and performing matching according to the historical risk data and the risk category identification result to obtain a risk prediction result of the key demand item. The invention further provides a production risk prediction device and equipment, a storage medium and a program product.

This invention relates to the field of product quality monitoring, and in particular to a method, equipment, and medium for monitoring the status of a thin film production line. The method acquires time-series data of operating status parameters of automated coating equipment, such as die pressure, feed flow rate, and feed temperature, within a specific time period. This data is then input into a pre-trained quality prediction model to obtain the predicted anomaly probability. Based on this, the judgment threshold of the visual defect detection algorithm is dynamically adjusted, achieving a precise match between detection sensitivity and production risk, thus solving the imbalance between missed and false detections caused by fixed thresholds. The model training employs a spatiotemporal window-aligned sample construction method, considering the material transport delay in the coating process. Continuous products are discretized into the smallest detection unit, and the anomaly percentage is used as a label, effectively solving the problem of the correlation between equipment parameters and product quality, and improving prediction accuracy.

The application relates to the technical field of predictive maintenance and health management of industrial equipment, in particular to an intelligent electromechanical comprehensive monitoring system based on an industrial internet, which comprises the following steps: a data acquisition module acquires equipment dynamic operation parameter sets, inherent physical attribute parameters and historical maintenance data of target electromechanical equipment, and calls preset process topology data, economic loss data and maintenance cost data; a state evaluation module iteratively calculates a cumulative degradation index representing the health condition of the equipment; an importance quantification module calculates a process importance coefficient representing the key degree of the equipment in a production line based on the process topology data; a risk calculation module generates a production risk degree quantifying the influence of shutdown; and a decision generation module generates a dynamic maintenance decision instruction; the application realizes systematic risk cognition from equipment individuals to the whole production line, breaks away from the extensive management of treating all the equipment equally, and makes the allocation of maintenance resources more strategic and targeted.

The invention discloses a safety production risk dynamic assessment and hierarchical management and control method based on a mobile management and control system, and relates to the technical field of mobile management and control systems, and the method comprises the steps: building an assessment model, and constructing a risk assessment model through a big data analysis and machine learning algorithm; real-time evaluation calculation: the mobile management and control system substitutes the data collected in real time into a risk evaluation model for dynamic calculation; according to low risk level definition, medium risk level definition and high risk level definition, a hierarchical management and control strategy is established, technologies such as big data analysis and machine learning algorithms can be utilized to realize real-time monitoring and dynamic evaluation of various risks in the production process, and accurate hierarchical management and control are implemented according to evaluation results. And the scientificity and effectiveness of safety production management are improved.

The invention relates to the technical field of agricultural informatization, in particular to an intelligent data management system for agricultural data, which comprises an agricultural data structuring module, a flowering phase characteristic clustering module, a risk linkage judgment module and a risk aggregation early warning module. According to the method, key agricultural condition information such as the initial time of the flowering phase and the number of continuous days is constructed into time sequence parameters, growth mode generality under different space identifiers is automatically mined and classified, linkage judgment is carried out by associating the yield value with the preset risk threshold value, and dynamic evaluation of the potential production risk of a specific growth feature unit is achieved. Accumulative statistics is carried out according to the occurrence frequency of the risk unit in the continuous time node, a grading risk early warning instruction is generated after comparison with an aggregation frequency standard, post statistics is effectively converted into beforehand prediction and process intervention, and the initiative and accuracy of agricultural production risk management and control are remarkably enhanced.

The invention relates to the technical field of safety production, in particular to a safety production risk management method and system based on an AI model. Comprising the steps of setting a plurality of risk sensing points according to production business parameters, and generating a time sequence monitoring strategy according to all the risk sensing points; generating a risk thermodynamic diagram according to the monitoring data of each risk sensing point, and setting an inspection strategy according to the risk thermodynamic diagram; and obtaining a feedback data packet according to the preset feedback time node, and judging whether a correction instruction of the inspection strategy is generated or not according to the feedback data packet. A plurality of risk sensing points are set for a production business process in combination with historical production risks, a time sequence monitoring strategy is set according to historical risk characteristics of each risk sensing point in combination with a risk diffusion trend, and a corresponding data acquisition strategy is dynamically adjusted, so that the overall monitoring cost is reduced; and meanwhile, by dynamically adjusting the fusion weight of each risk sensing point on the risk thermodynamic diagram, the overall risk analysis precision and inspection efficiency are improved, and safe operation of enterprises is ensured.

The application relates to a production risk event detection method, system, electronic device and storage medium, wherein the production risk event detection method comprises the following steps: collecting production parameter samples and risk event samples of multiple monitoring points on a production line; adopting a correlation analysis algorithm to calculate a time lag correlation relationship between the production parameters and the risk events, and obtaining a correlation matrix representing the correlation relationship between the production parameters and the risk events; adopting a clustering analysis algorithm to classify the risk events, and obtaining the types of the risk events; according to the types of the risk events and the correlation matrix, a corresponding multi-model fusion prediction model is constructed; and according to the prediction model, the real-time collected production parameters are subjected to risk prediction, and a corresponding risk prediction result is obtained. The production parameter and the risk event can be subjected to time lag correlation analysis, the correlation matrix is obtained, and according to the correlation matrix, a corresponding multi-model fusion prediction model is constructed, so that the accuracy of production risk event detection is improved.