533 results about "Industrial setting" patented technology

The invention belongs to the technical field of inspection robot systems, and particularly relates to an inspection robot path planning method and system.The visual semantic perception module collects an industrial environment image through a top industrial camera, after graying and Gaussian filtering preprocessing, feature points are detected and matched through an ORB algorithm, and a path planning result is obtained; in combination with an illumination self-adaptive threshold screening mechanism, mismatching points are eliminated, semantics are marked, and a semantic feature map is constructed; the initial path planning module generates an initial path through a semantic cost-containing A * algorithm based on the map; the dynamic obstacle avoidance module captures a moving obstacle by using a visual sensor, and predicts a trajectory through Kalman filtering; the path optimization module combines an initial path and an obstacle track, optimizes the path by using quadratic programming of a fusion curvature constraint and an energy consumption model, and corrects positioning by fusing vision and IMU data through a dynamic weight fusion algorithm; and the execution feedback module generates an instruction according to the optimized path, re-triggers path optimization, forms a closed loop, and ensures the inspection stability.

The invention relates to a production workshop carbon flow twinborn mapping method, and belongs to the technical field of carbon emission optimization. The method comprises the steps of collecting production workshop data in real time to perform multi-modal data fusion; constructing a carbon flow dynamic accounting mechanism model, and calculating the real-time carbon emission intensity of the process; constructing a carbon flow intensity tensor model, extracting multi-granularity carbon flow features based on the carbon flow intensity tensor model, and realizing real-time digital twinborn deduction of carbon flow propagation by using an intelligent prediction algorithm; establishing a differential equation to describe double-flow real-time interaction of the carbon flow and the value flow, constructing a carbon value incidence matrix, and performing carbon flow value analysis; and on the basis of the carbon value incidence matrix, a space-time carbon chain-oriented cooperative adjustment strategy is dynamically generated through a multi-objective optimization algorithm, a double-layer topological optimization model is constructed, and a closed-loop feedback mechanism is introduced to drive the economic sustainability of the control strategy in an industrial environment. The workshop carbon footprint can be displayed in real time, the workshop carbon emission condition can be truly reflected, and the carbon emission data can be analyzed and optimized in time.

Methods and systems for a monitoring system for data collection in an industrial environment including a data collector communicatively coupled to a plurality of input channels connected to data collection points operationally coupled to at least one industrial component in at least one of an industrial boiler system or industrial pipeline system; a data storage structured to store a library of stored noise patterns associated with operation of the at least one industrial component; a data acquisition circuit structured to interpret a plurality of detection values from the collected data; and a data analysis circuit structured to: analyze the collected data, determine a measured noise pattern for the at least one industrial component, and compare the measured noise pattern to the library of stored noise patterns to identify a changed condition of the at least one industrial component.

The invention relates to the technical field of intelligent monitoring of petroleum equipment, and particularly provides an industrial equipment state diagnosis method based on multi-modal fusion deep learning. The method comprises the following steps: synchronously acquiring load, vibration and current data through an explosion-proof RTU (Remote Terminal Unit), and transmitting the data to an edge node through an industrial LoRaWAN (Load RaWide Area Network); aligning a multi-source signal time sequence by adopting Kalman filtering, and fusing to generate data streams with consistent time domains; features are extracted by using wavelet packet energy entropy, and a lightweight ResNet18 model is input to realize high-precision diagnosis; based on the diagnosis result, a dynamic optimization strategy is generated through an LSTM-Transform parallel model; and finally, issuing a control instruction to the equipment for execution, and collecting feedback data to update the cloud model. Through the multi-rate signal time sequence alignment and feature-decision two-stage fusion technology, the problem of diagnosis errors caused by data asynchronization in a traditional method is solved, the fault recognition precision and the equipment energy efficiency are remarkably improved, and meanwhile the requirements for explosion prevention and real-time performance of the industrial environment are met.

The invention discloses an explosion-proof and intrinsic safety type combined feeder switch state monitoring method based on big data, and relates to the technical field of industrial electrical equipment state monitoring and fault diagnosis, and the method is realized based on a three-level architecture constructed by an edge computing node, a region computing node and a cloud platform. Comprising the following steps: S1, collecting multi-source sensing data of a feeder switch in real time by an edge computing node, and performing feature extraction and fusion calculation on the multi-source sensing data; according to the method for monitoring the state of the explosion-proof and intrinsic safety type combined feeder switch based on the big data, the contradiction between the real-time performance and the accuracy in multi-source heterogeneous data fusion processing is effectively solved, abnormity can be found in the first time, early warning can be triggered, and the reliability of a diagnosis conclusion is improved; and the accuracy and foresight of fault diagnosis are ensured. According to the grading processing mechanism, computing resources are reasonably distributed, the network transmission load is greatly reduced, and the system can stably operate in a complex industrial environment.

The present invention relates to a collaborative robot system used in an industrial environment where workers collaborate. The collaborative robot system comprises: a collaborative robot body having a multi-joint structure; a control unit for controlling each joint or auxiliary shaft; one or more sensors for detecting the operational state of the robot in real time; and a status diagnosis and response module for diagnosing the state of the robot on the basis of detected data and controlling the operation of the robot accordingly. Specifically, the system is configured to enable the robot to autonomously perform actions such as deceleration, stopping, and recovery in response to various state changes occurring during work, and to perform self-learning and trajectory optimization on the basis of data accumulated through repetitive tasks. Furthermore, the system includes a graphical user interface (GUI) for intuitive user interaction, which is linked to a digital twin-based virtual simulation environment, enabling presetting and modification of work paths. When multiple collaborative robots are operated together, the system enables task synchronization, path collision avoidance, and sharing of status information among the robots, and may be connected to an external control server or a cloud-based control system to allow integrated management of the entire workflow.

The invention relates to the technical field of impurity gas detection control, and discloses an impurity detection control method and system for high-purity oxygen, and the method comprises the steps: arranging a plurality of groups of TDLAS detection probes and temperature vibration monitoring units, and obtaining a spectrum harmonic signal and temperature and vibration data; the concentration is inverted through wavelength modulation spectrum demodulation and temperature and pressure disturbance compensation; pCA fusion denoising processing is executed through the edge calculation unit, and correction concentration is output; and abnormity is judged through a multi-scale dynamic threshold mechanism and linkage control is carried out. Compared with a common single-point probe or traditional low-pass filtering in the prior art, the technical problem that interference between impurity concentration change and environmental disturbance cannot be effectively handled especially in a high-vibration and high-temperature-difference environment is solved. According to the invention, through multi-channel cooperative weighting, PCA fusion compensation and a dynamic threshold determination mechanism, accurate detection control of the high-purity oxygen conveying pipeline in an industrial environment is realized, and the automation level of pipeline impurity gas detection control is improved.

The invention relates to the technical field of internet big data and information security, and designs a gearbox fault diagnosis method based on multi-source agent federal field generalization by combining the interaction capability of wide-area data and a local diagnosis agent. According to the method, a dual regularization mechanism is introduced in the training process of each local diagnosis agent, and the problem of negative migration is solved by actively learning domain-invariant fault features, so that the cross-working-condition and cross-equipment generalization diagnosis performance of a final model is remarkably enhanced on the premise of protecting data privacy; meanwhile, a central server is replaced by a decentralized coordination network realized by a block chain technology, and a committee consensus protocol is executed to ensure that the generation process of the global model is open, transparent and non-tampering, so that the single-point fault risk is fundamentally eliminated, the security and robustness guarantee is provided for the whole coordination process, and the method has the advantages of being high in practicability and the like. And the long-term applicability and the fault diagnosis accuracy and reliability of the method in a dynamically changing industrial environment are ensured.

The invention discloses an industrial data risk assessment method and system based on big data analysis, and relates to the technical field of industrial data risk assessment, and the method comprises the steps: collecting industrial data, carrying out the preprocessing and fusion, and obtaining a fusion feature vector; randomly selecting feature dimensions as nodes in an isolated forest algorithm based on the fused feature vectors, obtaining a value domain to divide the fused feature vectors, obtaining left and right sub-trees, embedding a performance counter for initialization, and executing recursion operation based on the left and right sub-trees to obtain a division path length; calculating an average expected path length and an abnormal score to carry out abnormal point determination, calculating a prediction error to update a performance counter and execute a deletion operation of a tree, calculating a Shapley value and combining the Shapley value with the abnormal score to generate a fusion abnormal score; according to the method, the adaptability to industrial environment changes is improved, and the risk assessment process is more comprehensive and accurate.

The invention relates to the technical field of sensors, and provides a grating position sensor. A scanning assembly and a light source module are relatively fixed, and an incident diaphragm and an increment detector are arranged in the scanning assembly; the increment detector is spatially divided into at least two first detector regions for detecting a first phase increment signal component and at least two second detector regions for detecting a second phase increment signal component, and the at least two first detector regions are spatially separated from each other; performing redundant detection on the first phase increment signal component; the at least two second detector areas are separated from each other in space so as to perform redundancy detection on the second phase increment signal component; the position metering element is suitable for being fixed on a measured object or a measuring datum plane and can generate relative displacement with the scanning assembly. The invention provides a grating position sensor with strong anti-pollution capability. The grating position sensor can keep a high-reliability working state for a long time in a complex or severe industrial environment.

The invention discloses a console identity recognition method based on a block chain, relates to the technical field of computer security and human-computer interaction, and realizes non-sensibility and precision of console identity recognition through fusion of behavior feature modeling and a block chain technology. In a multi-person alternate scene, an operator does not need to actively execute a biological verification action, and the system converts behavior characteristics into encrypted operation fingerprints by continuously capturing physical operation actions and graphic interaction logic and carries out uplink storage on the encrypted operation fingerprints; the block chain smart contract compares the time sequence difference between the current operation and the historical fingerprint in real time, and only when the behavior is abnormal, the biological auxiliary verification is triggered, so that the operation interruption caused by the factors such as gloves and light in the industrial environment is remarkably reduced; a dynamic permission label generation mechanism breaks through static authorization limitation; by analyzing the semantic intention of the control instruction and combining a preset equipment permission topological graph, the minimum equipment operation range is automatically delimited, and the tag validity period is set according to the instruction risk level.

The invention provides a bus duct temperature field dynamic regulation and control system based on edge calculation, and relates to the technical field of bus ducts. The bus duct temperature field dynamic regulation and control system based on edge calculation comprises a shell, an edge calculation gateway, a protection plate and a connector. The temperature data is processed in real time through the edge computing gateway, the temperature control response time is shortened to 200 milliseconds from 5 seconds of a traditional single-chip microcomputer, the problem of local overheating caused by response lag in the prior art is effectively solved, meanwhile, the TEC module, the phase change material and the air cooling structure are adopted for cooperative heat dissipation, the temperature control precision of a hot spot area reaches + / -0.5 K, and the temperature control accuracy of the hot spot area reaches + / -0.5 K. The safety of a power supply system is remarkably improved, an IP68-level sealing structure is formed by combining resin packaging with a high-thermal-conductivity insulating layer, heat balance is achieved through active heat absorption of a phase change material and active refrigeration of TEC in a completely closed environment, the defect that in the prior art, the protection level is insufficient (below IP54) due to forced air cooling is overcome, and the power supply system adapts to severe industrial environments such as humid and dusty environments.

The invention discloses a multi-branch industrial ventilation intelligent regulation and control system and method based on a PLC. According to the system, a closed-loop control network is formed by an infrared sensor, a wind speed sensor, a PLC (Programmable Logic Controller), an air door control cabinet, an electric valve, a frequency converter, a frequency conversion fan and an upper computer. The infrared sensor is responsible for monitoring the running state of each production line in real time. The wind speed sensor is used for detecting the wind speed in the wind pipe and verifying wind quantity balance. The PLC processes all sensor data and outputs a control instruction. On one hand, the opening degree of the electric valve is adjusted through the air door control cabinet, and on the other hand, the rotating speed of the fan is adjusted in real time through the frequency converter. The upper computer is used for system parameter monitoring, threshold setting and data interaction with the manufacturing execution system. According to the system, on-demand adjustment of multi-branch ventilation is achieved through intelligent closed-loop control, the problem of response lag of a traditional control mode is effectively solved, the dust removal efficiency and the energy utilization rate are remarkably improved, and safe and efficient operation of the industrial environment is guaranteed.

The invention discloses a real-time adjustment camera focusing method and system, and aims to solve the problem of poor anti-interference capability of an existing focusing mode. The method comprises the following steps: off-line construction of an optimization lookup table and on-line real-time focusing: in an off-line stage, constructing a fixed-focus platform, generating an original lookup table through light spot anti-interference preprocessing and centroid calculation, and then constructing an efficient retrieval data structure to obtain the optimization lookup table; in the online stage, images are collected in real time, the center of mass is obtained through anti-interference processing, compensation is conducted through a preset prediction algorithm during shielding, target reference points are matched through an efficient retrieval data structure, and focusing is triggered according to deviation of the center of mass. The system comprises a hardware module and a software module which cooperatively realize the method. The method improves the anti-interference capability of light spot processing and the matching efficiency of the lookup table, adapts to the interference of illumination fluctuation, shielding and the like of an industrial environment, meets the real-time focusing requirements of high-speed production, is compatible with existing hardware, and is convenient to deploy.

The invention relates to the technical field of hybrid intelligence, in particular to a quadruped robot motion control and operation system for an industrial environment, which realizes full-link intelligent management from environment perception to motion control, and remarkably improves the operation precision of a robot and the system efficiency. A three-dimensional map is constructed through a multi-sensor fused environment sensing module, and precise positioning is realized by combining state estimation based on deep learning; a motion control module with a hierarchical control architecture is adopted, and stable motion under a complex terrain is ensured through model prediction and gait optimization; the digital twinning and cloud side end collaboratively constructs a virtual-real mapping system to realize predictive maintenance and remote monitoring; and the multi-agent coordination module realizes task coordination and resource optimization of the multi-robot system through a distributed scheduling algorithm.

The application discloses a short video code rate self-adaptive method based on meta learning, relates to the technical field of streaming media, and comprises the following steps: S1, offline training, a model is established to represent user characteristics and network prediction information; S2, online learning, according to the characteristics of the current user environment, the model parameters are adjusted and optimized. The short video code rate self-adaptive method based on meta learning is adopted, a new SABR framework based on meta learning is successfully realized, the framework can quickly adapt to different user demands, the practicability and the calculation speed of the system are improved, and the framework has industrial application; the offline training and the online learning technology are successfully combined, the generalization and the stability of the model are enhanced; the idea of action masking is introduced in pre-training, the rationality and the reliability of decision are enhanced, the data amount required by meta learning is effectively reduced, the learning efficiency and the accuracy are improved, and the data demand and the training time in the industrial environment are significantly reduced.

The invention specifically relates to a federated learning-based distributed dyeing machine anomaly detection method, and relates to the technical field of industrial equipment anomaly detection and federated learning, and the method comprises the steps: compressing an obtained weight difference value, encrypting the weight difference value, and transmitting the weight difference value to a federated server; according to the method, a CNN-LSTM mixed structure is adopted for model training, space and time sequence characteristics are considered, and dyeing machine multi-sensor data association and abnormal hysteresis characteristics are adapted; incremental training and small-batch training strategies are adopted to solve the problem of computing power memory limitation of edge equipment, so that the model can be locally and stably trained in the dyeing machine, and network dependence is avoided; a compression transmission link, a dynamic sparse adaptation process stage and hierarchical quantification distinguishing of information levels are performed, so that the data volume is compressed, the transmission efficiency is guaranteed, key information is reserved, the federal learning process is stably operated in an industrial environment, and a dyeing machine production scene is comprehensively adapted from data processing to model training deployment; and a solid support is provided for abnormal detection landing.

Active machine learning systems for anomalous event detection and classification. Initial samples from an industrial environment may be received and labeled. Initially, a training pool of audio samples may be labeled. These labeled samples may be used to train an audio event classifier to detect and categorize sounds. Environment states may be calculated using outputs from the classifier. A batch of audio samples may then selected from an unlabeled pool for annotation, guided by a reinforcement learning agent. These selected samples may be annotated and added to the labeled training pool. The classifier may be retrained with this updated pool. Rewards may be calculated for each of the annotated samples based on their annotations. The environment states may be updated using the retrained classifier, and the exploration-exploitation parameter of the reinforcement learning agent may be adjusted. The reinforcement learning agent may be retrained using the updated environment states and rewards.

The invention relates to a light hydraulic pump fault diagnosis method applicable to all working conditions, and belongs to the technical field of fault diagnosis. The method comprises the steps that a resampling preprocessing technology combining cubic spline interpolation and nearest neighbor interpolation is adopted, unified length transformation is conducted on signals of each circle of a hydraulic pump, and high-frequency and low-frequency feature information of the signals is reserved; designing an order calibrator with global perception capability, wherein the order calibrator is used for stabilizing feature expression after resampling; a multi-cycle component fault feature decoupling module embedded with a prior decomposition factor is constructed, and key component features are extracted; an intrinsic task guiding strategy is provided, and the recognition capability of the model on key fault features is enhanced; interference of working condition characteristics such as rotating speed and pressure is inhibited through a multivariable working condition distribution removal method. The method has the advantages of being small in model parameter, high in calculation speed and the like while achieving full-working-condition high-precision diagnosis, and is suitable for real-time intelligent monitoring of the hydraulic pump in the industrial environment.

A system and method for automatically generating immersive training scenarios for workers in an industrial environment for hazardous events in a computer simulated environment is provided. The method includes acquiring, by processing unit, information pertaining to operation of assets and related anomalies and hazards in industrial environment for which training scenarios are to be simulated, loading simulation sequence of industrial environment including assets operating at ideal behavior, wherein simulation sequence executes a first set of tasks on virtual assets within ideal behavior, defining one or morse sequence of events that lead to hazardous event in industrial environment based on acquired information, determining second set of tasks to be executed in loaded simulation sequence, simulating second set of tasks in loaded simulation sequence, and generating immersive training scenario in computer simulated environment based on execution of the first set of tasks and the second set of tasks in loaded simulation sequence.

A gas emission monitoring system is configured for versatile deployment across various sites, including gas extraction locations, industrial settings, and environmental monitoring areas. The system may include a support structure holding a plurality of tubings, each equipped with at least one intake port. The tubings may be interconnected through a connecting tubing that ultimately links to an analysis tubing feeding into a gas analyzer. The design ensures that the intake ports are strategically positioned at different vertical levels relative to the ground, for example, for optimized air sampling. The gas analyzer may be configured to identify multiple types of gas content in a received air mixture, which is collected from the various intake ports. Thus, the systems discussed herein may provide a comprehensive, adaptable solution for real-time gas monitoring, capable of handling a broad range of gases and environmental conditions.

A system and method are disclosed for advanced multimodal-sensor systems integrating various sensing characteristics for machine condition monitoring, including thermal imaging cameras, ultrasonic, vibration, temperature, magnetic sensors, high-band microphones, electro-magnetic emission detectors and others. The system's architecture comprises edge computing capabilities for real-time anomaly detection and operational feedback, utilizing edge machine learning (ML) models trained in the cloud. The system supports flexible configuration and calibration to optimize measurements based on machine requirements, while a cloud-based analysis framework enables robust data fusion, training and condition assessment. The method comprises performing automated diagnostic workflows enabled by models at the edge, reducing or eliminating human intervention, and significantly enhancing operational performance, maintenance and efficiency across multiple machines in an industrial setting.

The invention relates to the technical field of audio signal processing, and discloses an industrial noise identification method and system, and the method comprises the steps: obtaining an audio signal, and carrying out the time-frequency decomposition, and obtaining preliminary decomposition data; classifying the coupling features of the preliminary decomposition data to obtain a coupling region boundary value; if the boundary value of the coupling region exceeds a preset boundary threshold value, performing filtering processing to obtain separated noise spectrum data; calculating an overlapping proportion of the separated noise spectrum data and a preset target sound; if the overlapping proportion causes extraction deviation, extracting dynamic change characteristics of the separated noise spectrum data and fusing the dynamic change characteristics into a spectrum extraction process to obtain an accurate noise spectrum; calculating an intensity value according to the accurate noise spectrum, and determining an intensity evaluation result; and comparing the intensity evaluation result with a preset pollution threshold, calculating a noise pollution degree and outputting a noise identification result. The method is suitable for industrial environment noise monitoring, and can accurately extract the noise spectrum.

In modern industrial environments, there may be numerous independent applications deployed throughout a facility, all performing different tasks, gathering different data, and communicating data and control information among one another. For example, this may include industrial control, quality control, work instructions, training, oversight, and so forth. Against this backdrop, an AI system is trained with a large language model to assist in characterization of new applications, in order to support administration and management of the software infrastructure for a facility.

The invention discloses a humanoid robot decision interaction method, system and device and a medium. The method comprises the steps of obtaining industrial sensor data; inputting the industrial sensor data into a multi-modal large model for environment evaluation processing to obtain an industrial environment evaluation result; inputting the industrial sensor data into an anomaly recognition model according to the industrial environment evaluation result to obtain an anomaly recognition result; inputting the industrial sensor data and the anomaly recognition result into the multi-modal large model for strategy generation processing to obtain an interaction strategy; and performing interaction control on the humanoid robot according to the interaction strategy. The decision interaction efficiency of the humanoid robot can be improved, and the method can be widely applied to the technical field of intelligent robots.

The invention discloses a flat gate valve performance detection device, and belongs to the technical field of gate valve detection devices, the flat gate valve performance detection device comprises a detection table, the top of the detection table is provided with a caliber detection mechanism, and the bottom of the detection table is provided with an air tightness auxiliary detection mechanism; according to the invention, through the arranged aperture detection mechanism, the multi-station alternate conveying detection of the flat gate valve body is realized, the detection efficiency and the automation level are significantly improved, and through a mechanical feedback structure formed by the extrusion plate, the reset spring, the push type trigger switch and other components, the detection precision can be greatly improved on the premise of no complex sensor. Structural elasticity changes are matched with displacement triggering, structural abnormity of the gate valve to be detected is accurately judged, sound-light alarm is given out, dependence of a detection system on circuit stability is reduced, meanwhile, the anti-interference capacity and the capacity of adapting to severe industrial environments of the device are enhanced, alarm response is fast, structural configuration is stable, and batched flat valve body rotary detection is facilitated.

The invention relates to the technical field of man-machine interaction, and provides a man-machine interaction method based on multi-modal data, and the method comprises the steps: carrying out the timing detection of the transmission conditions of an industrial environment through the deployment of collection equipment for industrial operation and maintenance and inspection, and dividing corresponding levels for sampling processing; corresponding semantic tags and templates are established for the process of industrial operation and maintenance and inspection work, the semantic tags and templates are issued to equipment to be called, and meanwhile deviation terms are analyzed and optimized; collecting multi-modal data to perform aggregation and normalization processing, aligning vector lengths and projecting the vector lengths to a unified dimension, aligning formed fusion feature vectors with timestamps, and performing detection according to similarity, a standard semantic tag and a template library; and inputting the multi-modal feature vector into an instruction classifier, outputting an instruction according to a predefined instruction template, sending the instruction to corresponding equipment for execution, monitoring the execution condition in real time, and uploading a deviation log for iterative optimization.

The invention discloses a concurrent scene-oriented extensible block chain client optimization method, which comprises the following steps of: decoupling a client into an interface service layer, a message service layer and a data service layer based on an asynchronous message bus, and realizing node dynamic registration and routing table maintenance through a heartbeat protocol; the interface service layer calculates a dynamic weight according to the state information of the data service nodes to construct a dynamic weight table so as to distribute an external request to the surviving data service nodes; a distributed cache layer is introduced, a cache layer cluster is preferentially queried in a read operation path, chain code query is triggered when the cache layer is not hit, and a result is written into a cache; and a write operation path adopts two-stage cache failure guarantee to eliminate dirty reading. Industrial environment parameters of all the data service nodes are collected in real time and scored, and part or all of the flow is intelligently migrated according to the score. According to the method, the client throughput, the response efficiency and the industrial environment adaptability are remarkably improved, and large-scale deployment of intelligent manufacturing high-concurrency scenes is supported.

Methods and systems for a data marketplace in a fluid conveyance device includes a self-organizing data marketplace. The self-organizing data marketplace includes at least one data collector and at least one corresponding fluid conveyance device in an industrial environment, wherein the at least one data collector is structured to collect detection values from the fluid conveyance device; a data storage structured to store a data pool comprising at least a portion of the detection values; a data marketplace structured to self-organize the data pool; and a transaction system structured to interpret a user data request, and to selectively provide a portion of the self-organized data pool to a user in response to the user data request.

The invention discloses a real-time data acquisition and analysis method in industrial intelligent manufacturing, and relates to the technical field of industrial automation and intelligent manufacturing, and the method comprises the following steps: air quality monitoring equipment carries out conventional detection on the concentration of harmful gas in the environment according to a pre-configured time sequence resolution, and obtains air quality parameter information in real time; according to the invention, the response sensitivity and intelligent identification capability of the air quality monitoring equipment to instantaneous high-concentration harmful gas leakage are improved, and the monitoring limitation of traditional fixed time sequence resolution is broken through. And through fusion of feature engineering and a machine learning model, accurate judgment of dynamic change of gas is realized. After the severe fluctuation state is identified, the system dynamically adjusts the sampling frequency and starts the cache, the concentration peak value is effectively captured, meanwhile, the storage pressure is relieved, the stability and the real-time performance of the system are enhanced, and the safety protection capability of the industrial environment is improved.