6256 results about "Mechanical equipment" patented technology

The invention discloses an electromechanical equipment noise reduction method based on machine learning, and relates to the field of electromechanical equipment noise reduction, and the method comprises the steps: collecting sound pressure and vibration signals during the operation of electromechanical equipment, and collecting the operation state data of the electromechanical equipment; sparse reconstruction is carried out on the noise features; carrying out sound source localization on the reconstructed noise features by using a beam forming algorithm to obtain a noise distribution diagram; constructing a noise reduction model based on deep learning to obtain noise signals after noise reduction; extracting the frequency of the noise signal in a preset frequency range through a peak search algorithm; analyzing the acquired running state data by using a time-varying linear predictive coding algorithm TVLPC to obtain a noise frequency offset caused by the abnormal running state of the electromechanical equipment; generating an optimal solution by using a particle swarm algorithm; and according to the optimal solution of noise control, noise dominant frequency components are extracted for separation, and a plurality of phase-reversal noise reduction control signals are obtained. Aiming at low noise reduction precision of electromechanical equipment in the prior art, the noise reduction control precision is improved.

The invention relates to the technical field of project management, in particular to a BIM-based building project resource scheduling optimization method, which comprises the following steps: based on the current progress state of a construction task, collecting the consumption of constructors, mechanical equipment and materials, comparing the task plan progress with the real-time progress, screening out construction links with the backward task progress, and establishing a construction project resource scheduling optimization model; and judging a resource type, and establishing a task progress offset. According to the method, the construction progress is accurately monitored, real-time evaluation of resource consumption is achieved, waste and scheduling lag are avoided, the construction path is optimized by means of the BIM model, the key path monitoring precision is improved, progress management and control effectiveness is ensured, key path progress deviation is analyzed, the resource shortage risk is recognized, stable supply of construction resources is guaranteed, and on the basis of the influence of resource shortage, the construction efficiency is improved. The resource distribution sequence is optimized, the resource utilization efficiency is improved, the supply chain delivery cycle is matched, the resource scheduling is optimized, the influence of resource supply and demand imbalance on the construction progress is reduced, and the continuous and stable construction progress is ensured.

The invention provides an intelligent mechanical equipment fault diagnosis method fused with a machine learning algorithm, and the method comprises the steps: obtaining a multi-source signal, and generating a complete machine-level anomaly detection result through dynamic threshold comparison and machine learning anomaly detection model processing; the multi-source signal comprises a vibration signal, a temperature signal and a pressure signal; performing signal decomposition and multi-source parameter fusion analysis processing based on a complete machine level anomaly detection result, and determining a physical subsystem of an anomaly source; time-frequency features are extracted from the operation data of the physical subsystem, and a part-level anomaly positioning result and a microdefect classification result are generated through hierarchical machine learning model processing; and performing multi-granularity data fusion processing based on a complete machine level anomaly detection result, a physical subsystem and a microdefect classification result, and generating a hierarchical diagnosis report. By adopting the method, progressive diagnosis can be carried out on the mechanical equipment hierarchically, and the accuracy of fault diagnosis is improved.

The invention relates to the technical field of construction management, in particular to a BIM-based building construction management system, which comprises a path compression module, a priority scheduling module, an equipment allocation module, a material arrangement module and a progress coordination module. According to the method, the BIM model construction path node set is obtained, the node compression condition is judged based on the labor resource availability index of the construction scheduling schedule, high coordination of the construction path and resource configuration is achieved, the problems of resource mismatching and construction efficiency reduction are avoided, and the construction efficiency is improved based on the density comparison between the space area to which the component belongs and the construction equipment in the area. Reasonable allocation of construction equipment is achieved, full utilization of mechanical equipment is guaranteed, structural hierarchical indexes, space coordinates and construction logic dependency relationships are associated through component identification numbers, a construction feasible dependency graph and material entering batch sorting are formed, and a material entering time window is accurately determined; coordination conflicts between material approach and storage area arrangement are mitigated.

The invention relates to a mechanical equipment fault data identification method based on artificial intelligence, and belongs to the technical field of data processing and artificial intelligence. The problems of insensitive signal processing, insufficient feature extraction, significant noise interference, low model training efficiency and the like in fault diagnosis in the prior art are solved. According to the method, a self-adaptive normalization method based on energy density is provided, the influence of non-stationary signals is effectively inhibited, and key features are reserved; through mixed energy entropy feature extraction and inter-band energy jump penalty terms, the sensitivity to a complex fault mode is significantly enhanced; constructing a fault feature enhancement strategy based on a Gaussian potential well, and reinforcing the response of a fault feature accumulation area; a weighted loss function and a gradient directional correction mechanism are adopted, so that the robustness and accuracy of the model are improved; and in combination with an entropy weighted learning rate and a covariance scaling strategy, adaptive training is realized, and the convergence speed and adaptability are improved. According to the method, the precision and efficiency of mechanical fault diagnosis are improved, and support is provided for industrial intelligent development.

The invention relates to the technical field of mining mechanical equipment, and particularly discloses a mining mechanical equipment anomaly detection system and method. Current signals, voltage signals and vibration signals in the operation process of mining mechanical equipment are obtained; the method comprises the following steps: extracting an equipment operation current-voltage correlation feature vector and a mining mechanical equipment time frequency correlation feature vector, fusing to obtain a mining mechanical equipment anomaly classification feature vector, and obtaining a classification result through a classifier to indicate whether the mining mechanical equipment is abnormal or not, thereby realizing anomaly detection of the mining mechanical equipment.

The invention discloses a mechanical equipment multi-state selective maintenance method based on deep learning, and relates to the technical field of mechanical equipment intelligent prediction maintenance, and the method comprises the following steps: deploying a sensor at mechanical equipment to collect operation state data in real time, collecting maintenance operation logs and historical fault diagnosis record text data, and storing the collected maintenance operation logs and historical fault diagnosis record text data; generating a multi-source data stream through timestamp alignment, and preprocessing the multi-source data stream to obtain a preprocessed multi-modal data set; according to the method, the multi-modal data collected for the mechanical equipment has comprehensiveness and availability of data sources, the utilization rate of heterogeneous data is improved, the multi-modal feature data is fused by using the cross-modal association mapping model, hidden information can be mined, the invisible state can be recognized, the equipment operation condition is clearly mastered, and the method is suitable for popularization and application. And through combination of the STCN and the Weibull-deep learning hybrid model, the residual life of the mechanical equipment can be dynamically and accurately predicted.

The present invention relates to the field of real-time monitoring, and discloses a remote real-time monitoring system for on-site construction scenes, including a video monitoring module, a sensor and environment monitoring module, an intelligent safety early warning module, an equipment monitoring module and a personnel positioning module; the video monitoring module collects image data of the construction site in real time through a high-definition camera and intelligent monitoring equipment; the sensor and environment monitoring module is used to deploy temperature and humidity, wind speed, air pressure, noise, and vibration environment monitoring sensors to collect environmental data of the construction site in real time; the intelligent safety early warning module combines artificial intelligence and machine learning technology to analyze the video and sensor data of the construction site in real time and automatically identify potential safety hazards; the equipment monitoring module monitors the operating status of construction machinery and equipment through the Internet of Things technology; the personnel positioning module tracks the location and behavior of construction personnel in real time through wearable devices, positioning sensors or RFID tags. The present invention has the advantage of improving construction management efficiency.

The invention provides a rotary mechanical equipment fault identification method and device based on vibration data, and belongs to the field of vibration monitoring. The method comprises the following steps: acquiring a component information library of to-be-monitored rotary mechanical equipment; fault information corresponding to the component information base is determined, the fault characteristic frequency of each fault is calculated, and a fault characteristic frequency model corresponding to the component information base is established; collecting a vibration signal characteristic value of each component in the component information base in real time; extracting a vibration signal characteristic value, and matching the frequency domain characteristic value with the fault characteristic frequency based on a component information base and a fault characteristic frequency model to obtain a matching result; positioning an abnormal feature in the signal based on the time domain feature value and the geometric feature value; and identifying the fault type and degree of the mechanical equipment according to the matching result and the abnormal features. According to the mechanical equipment vibration monitoring data processing method and device, potential faults of the equipment can be found as soon as possible, and the equipment can be maintained in time.

The present invention relates to the technical field of electrical connectors, and in particular to an anti-loosening electrical connector for electromechanical equipment, comprising a coaxially plugged core barrel and a piercing barrel, wherein a plurality of cables are clamped on the core barrel, and the ends of the plurality of cables extend along the radial direction of the core barrel and are evenly distributed around the circumference of the core barrel, and the piercing barrel is provided with a plurality of piercing pieces, one end of the piercing piece is provided with a clamping groove, and the interior of the clamping groove is provided with a cutting section, a pressing section and a conductive section in sequence from bottom to top, the cutting section is used for cutting the insulating sheath of the cable, the pressing section is used for clamping the insulating sheath of the cable, and the conductive section is used for conductive connection with the wire core of the cable, and a clamping ring is rotatably provided on the piercing piece, and the clamping ring is U-shaped; in the initial state, the center line of the clamping ring coincides with the center line of the clamping groove, and the clamping ring can be clamped with the insulating sheath of the cable; the clamping ring can be rotated 90°, so that the insulating sheath is in closer contact with the wire core.

The invention relates to the technical field of agricultural mechanical equipment, and provides a laser weeding method of a weeding robot and the laser weeding robot, the weeding method comprises the following steps: obtaining weed information, and selecting a weeding mode based on the weed information; laser parameters are adjusted based on the selected weeding mode, and path planning is carried out; controlling the weeding robot to advance according to the planned path, controlling the laser beam to align with weeds to perform weeding operation, and continuously feeding back the real-time position of the laser beam; and comparing the real-time position with a predetermined target position, and maintaining the current position or adjusting the current position based on a comparison result. According to the method, the laser parameters can be adjusted based on the weeding mode, the path can be planned, and the mode can be suitable for various complex weeding environments and can adapt to the weeding environments better, so that weeds are accurately and rapidly removed.

The invention discloses a fault prediction and health management system for a belt conveyor, relates to the technical field of intelligent monitoring and management of mechanical equipment, and aims to solve the problems of fault recognition lagging and high misjudgment rate caused by insufficient consideration of real-time performance and high reliability required by industrial equipment. Motor current fluctuation, roller temperature change rate, belt tension distribution and vibration spectrum data are acquired in real time through a data acquisition unit; the fault feature extraction unit extracts abnormal features based on wavelet transform, and calculates an operation stability index through a principal component analysis method; the risk assessment unit combines the abnormal features, the abrasion loss and the stability index, and adopts fuzzy logic reasoning to judge the fault risk level; and the intelligent regulation and control unit dynamically regulates and controls the operation state or gives an alarm according to grading processing, so that accurate early warning and intelligent response of early faults of the equipment are realized.

The invention discloses a railway engineering mechanical equipment energy consumption digital monitoring method and system, and relates to the field of railway construction equipment energy consumption management, and the method comprises the steps: obtaining the energy consumption data of each piece of to-be-selected railway engineering mechanical equipment in the operation process; preprocessing the energy consumption data in an edge processing unit to obtain a standardized feature vector; on the basis of the feature vectors, through a working condition recognition model, recognizing the current working condition of each piece of to-be-selected railway engineering mechanical equipment, and generating a working state labeling sequence; before operation task scheduling, unit energy consumption of each piece of to-be-selected railway engineering mechanical equipment is predicted based on the three-dimensional coupling atlas and the target task type, and task allocation optimization suggestions are output; and determining target railway engineering mechanical equipment based on the task allocation optimization suggestion, and outputting control parameters of the target railway engineering mechanical equipment. The key problems of energy consumption monitoring lag, working condition identification difficulty, unreasonable multi-equipment task allocation and the like in the prior art are effectively solved.

The invention discloses a mining mechanical equipment type selection management control platform based on a network, and relates to the technical field of mining mechanical equipment, and the control platform comprises a data collection module, a data processing and analysis module, and a type selection recommendation module. Multi-source heterogeneous data from a mining area geological exploration department, an equipment sensor, a satellite remote sensing image and a meteorological station are ingeniously fused, and the data are effectively integrated together through normalization processing and weight distribution, so that a comprehensive and accurate information basis is provided for subsequent model selection recommendation; the data processing and analysis module further performs cleaning, classification, coding and feature extraction on the data, a quantitative relation model between working condition factors and equipment performance is established, and the intelligent data analysis and processing capability enables the platform to perform quantitative analysis according to actual working condition requirements of a mining area. And equipment models and parameters with high adaptability and lowest full life cycle cost are accurately recommended.

The invention provides a digital mechanical equipment data management system based on cloud computing. The digital mechanical equipment data management system comprises a data acquisition module for acquiring equipment state and environment information; the feature coding module is composed of a gating circulation unit and a multi-layer perceptron and is used for extracting high-dimensional features; the feature fusion module fuses the high-dimensional features and outputs sparse joint codes; the cloud computing model construction module constructs a model and introduces a trainable enhancement layer; the state interaction module enables the code to obtain an advanced interaction state based on a model; the state synchronization module synchronizes a device state and environment information through MechLayer; the implicit state generation module obtains an implicit state by combining normalization and enhanced connection; operating an environment perception modeling module to improve perception estimation modeling; the perception learning vector generation module obtains a learning vector; the state prediction module predicts an operation state; and the track decoding module processes the input to obtain an equipment running track. The equipment management efficiency and the operation reliability can be improved.

The invention belongs to the technical field of mechanical equipment wear state monitoring. The method comprises the following steps of: extracting wear rate characteristics, wear degree characteristics, cutting index characteristics, fatigue index characteristics and oxidation index characteristics in an abrasive particle sample image, and respectively clustering to obtain five groups of discrete stage labels; carrying out normalization processing on the five groups of discrete stage labels to obtain a normalized data matrix; according to the data matrix, weights corresponding to all the features are calculated in multiple modes, and the average value of the weights calculated in the multiple modes serves as the final weight of all the features; according to the final weight of each feature and the normalized data matrix, calculating a comprehensive score sequence of all the abrasive particle sample images; performing clustering according to the comprehensive score sequence to obtain a plurality of optimal clustering centers, and determining a current wear stage according to the optimal clustering centers; and more comprehensive and more accurate division of the wear stages is realized.

The invention discloses an electrostatic induction and optical imaging principle-fused online monitoring device and method for wear particles of a water-lubricated bearing, and belongs to the field of state monitoring of mechanical equipment. The device comprises a square insulation detection cavity, a detection electrode array, an electromagnetic shielding shell, a high-speed optical imaging module and a signal processing unit, the square insulation detection cavity is installed in a bearing lubrication water loop. The detection electrode array is fixed to the outer wall of the cavity and used for capturing electrostatic signals generated when the abrasion particles pass through. The electromagnetic shielding shell wraps the detection cavity and is grounded through a wire to eliminate environmental electromagnetic interference. The high-speed optical imaging module integrates a high-magnification microscope lens and a CMOS sensor, is coaxially mounted with the detection cavity, and obtains the morphology characteristics of the wear particles in real time; and the signal processing unit performs multi-modal data fusion analysis on the electrostatic signal and the optical image. Through cooperative detection of electrostatic induction and optical imaging, the monitoring precision and reliability of the wear particles of the water-lubricated bearing are remarkably improved.

The invention discloses a double-row steel sheet pile cofferdam construction method, which comprises the following steps of: before construction, measuring the original riverbed elevation of a cofferdam piling area, organizing steel pipes to enter a site according to a cross-section diagram and a construction sequence of a cofferdam, timely removing and recording if stone blocks and the like at the river bottom are measured in the measurement process, and before construction, checking and maintaining all mechanical equipment, so that the construction efficiency is improved. After entering the field, the steel pipes are stacked according to specifications, varieties and classifications, before pile conveying, the models and the number of the steel pipes used during construction are determined, and the steel pipes are arranged strictly according to the designed section. Compared with a construction scheme of adopting a Larsen steel sheet pile cofferdam and a temporary construction platform, the construction cost, the rental cost, the earthwork transportation cost, the earthwork compaction cost, the earthwork filling excavation filling cost and the like of temporary facilities can be saved, building construction is carried out in a water area needing a large area, the construction period is long, and the construction cost is low. The method is more economical and reasonable when being used for constructing structures in water under the conditions of high water level and the like.

The invention is suitable for the technical field of mechanical equipment monitoring and control, and provides a mechanical state real-time monitoring system based on the Internet of Things, and the system comprises a data obtaining module which is used for obtaining a real-time monitoring result when a target feller performs felling operation on a target tree according to a preset cutting pressure parameter; real-time vibration data, real-time pressure feedback data and real-time temperature change data of the target feller saw blade within a preset time range are collected; according to the invention, multi-dimensional real-time monitoring of the state of the feller saw blade and dynamic adjustment of the cutting parameters are realized through the Internet of Things technology, and the stability and the intelligent level of equipment operation are effectively improved. By integrating three key parameters of vibration, pressure and temperature, the system provides more accurate saw blade aging evaluation, and solves the problem that a traditional single-parameter monitoring method is easily influenced by the environment and is not comprehensive enough.

The invention discloses a chemical process fault diagnosis and detection method and system. Belongs to the field of mechanical equipment fault diagnosis, and comprises the following detection steps: de-noising collected data by using a de-noising diffusion probability model (DDPM), and reducing noise interference in signals, thereby providing a clearer data basis for subsequent fault diagnosis; then, a fault diagnosis model (AResNet-Linformer) is built, the AResNet model is used for carrying out feature extraction on the denoised signals, and then feature information is sent to a Linformer neural network model for fault diagnosis; in order to improve the accuracy of the model, an improved star-sparrow optimization algorithm is used to carry out parameter optimization on the established fault diagnosis model. According to the invention, faults in the chemical process can be effectively identified, fault types can be rapidly determined, and a powerful data basis is provided for prevention and maintenance work.

The utility model discloses an auxiliary tension bracket for slitting and cutting a silicon steel coiled material, which belongs to the technical field of slitting machine tension brackets, and comprises a slitting machine, a cutter arranged on the slitting machine, support frames arranged at one end of the slitting machine and oppositely distributed, and a support seat arranged between the two support frames, limiting rollers and positioning blocks used for supporting are distributed at the upper end of the supporting base at equal intervals, supporting plates are fixedly installed at the upper ends of the positioning blocks, and an adjusting mechanism is arranged between the two supporting frames. A metal plate is conveyed to the supporting plate through the slitting machine, the servo motor is started to drive the two-way lead screw to rotate, the oppositely-distributed movable plates are made to be close to each other till the limiting rollers are close to the side edge of the metal plate, and at the moment, the slitting machine continues to convey the metal plate. And the tension bracket is fast to adjust, manual approaching is not needed, and potential safety hazards caused by approaching of workers to mechanical equipment are avoided.

The utility model relates to the technical field of agricultural mechanical equipment, in particular to a small Chinese cabbage harvester which is internally provided with a cutting component, a conveying component, a storage assembly and a traveling assembly, the two ends of the conveying component are connected with the cutting component and the storage assembly respectively, and the traveling assembly is installed below the storage assembly; the cutting component comprises a cutting assembly and a stirring assembly, the cutting assembly comprises a first fixing frame, two pulling shovels of the same structure and two cutting pieces of the same structure, one end of the first fixing frame is connected with the conveying component, and each cutting piece is connected with the other end of the first fixing frame; the middle part of each pulling shovel is fixedly mounted at the top end of one cutting piece; thus, when Chinese cabbages are harvested, the Chinese cabbages are pulled up through the pulling shovel, the roots of the Chinese cabbages are cut off through the cutting piece located below the pulling shovel, in the process, due to the fact that the cutting piece is located below the pulling shovel, the cutting piece does not make direct contact with the Chinese cabbages, the Chinese cabbages cannot be damaged, and the quality of the Chinese cabbages is improved.

The invention discloses a double-roller cooperative equal-seeding-depth rotary tillage, seeding and ditching all-in-one machine which comprises a double-shaft rotary cultivator, a traction hanging frame, a double-roller cooperative device, a 7-shaped knife roller and a transmission mechanism, the traction hanging frame is connected with the upper end of the double-shaft rotary cultivator, and the double-roller cooperative device is connected with the rear end of the traction hanging frame through a connecting rod and a hydraulic rod; the 7-shaped knife roller is connected with the rear end of the double-roller cooperation device, the transmission mechanism transmits power of a tractor to the double-shaft rotary cultivator, the double-roller cooperation device and the 7-shaped knife roller, the wrapping performance of soil on seeds is guaranteed, roots of the seeds can be attached to the soil in the germination period, in addition, the seeds are sown on the concave face, the sowing cavitation performance is good, and the sowing efficiency is high. The sowing depth is consistent, and automatic operation of agricultural automatic mechanical equipment in ridges is facilitated.

The invention relates to a small sample fault diagnosis method based on multi-scale feature learning and domain adaptive optimization, and the method comprises the steps: obtaining historical heterogeneous fault data of a plurality of mechanical devices as a source domain data set, and obtaining historical heterogeneous fault data of a target mechanical device as a target domain data set, label spaces are set for the source domain data set and the target domain data set respectively; random sampling combination is carried out based on a source domain data set and a target domain data set, a triple data set and a domain adaptive data set are constructed and input into a dual-branch feature extraction sub-network, a triple feature embedding distance is measured, iterative training is carried out in combination with a joint loss function formed by triple loss and domain adaptive loss, and a dual-branch feature extraction sub-network is obtained; obtaining a double-branch fault diagnosis model; and collecting current heterogeneous fault data of the target mechanical equipment, inputting the current heterogeneous fault data into the double-branch fault diagnosis model, and outputting fault classification of vibration signals of the target mechanical equipment. According to the method, the problem of model performance reduction caused by small sample data conditions and data distribution differences can be solved.

The invention belongs to the technical field of attack and defense of adversarial samples, and provides an attack and defense method of a mechanical equipment fault diagnosis model based on a conditional generative adversarial network, which adopts the conditional generative adversarial network to train a substitution model, simulates the input and output characteristics of a target model, and utilizes the migration characteristics of the adversarial samples to realize the attack and defense of the mechanical equipment fault diagnosis model. And while a better attack effect is achieved, the robustness of the target model is improved through further adversarial training by using the adversarial sample, and the defense capability of the target model to malicious attacks is enhanced. According to the method, the substitution model can be trained under the condition that internal information and original data of the target model are not used, the method is more suitable for scenes which widely exist in mechanical equipment fault diagnosis and are insufficient in original data, and the attack and defense effects are remarkably improved compared with a traditional substitution model pre-training method. According to the method, the safety of the mechanical equipment fault diagnosis model can be protected under the background of big data and cloud computing.

The invention relates to the technical field of coal mine mechanical equipment, and discloses a frequency converter control method based on state detection and load adaptive adjustment, which comprises the following steps: when a starting command is waited after a frequency converter is shut down, calling an event at the last moment and shutdown data to judge whether a control strategy is adjusted in next starting; after the frequency converter receives the starting command, the output rotating speed, the torque and the current value are monitored in real time to trigger abnormal starting identification; if the stator resistance changes, the identification parameters are stored, and then the normal starting mode is executed; if the stator resistance is abnormal, a frequency converter fault is output; if the stator resistance does not change, self-adaptive chain clamping identification is carried out according to the output rotating speed, the torque and the current value, self-adaptive adjustment is carried out on the frequency converter in the chain clamping state, and a normal starting mode is executed after chain clamping is removed. According to the invention, dynamic adjustment can be carried out according to load changes and specific abnormal conditions, so that the stability and reliability of equipment are improved.

The invention relates to the technical field of signal processing and state monitoring, in particular to an intelligent lubricating state monitoring method based on oil-impact pulse, which comprises the following steps of: constructing a'fluid-solid-heat-electricity 'multi-field coupled particle double-electric-layer electrostatic model, and forming a particle electrostatic characteristic analysis and monitoring method; oil physical and chemical property parameters and mechanical equipment transmission system gear impact pulse characteristics in different lubrication states are collected in real time, an oil-impact pulse-lubrication state correlation model is constructed, and a gear transmission system lubrication state monitoring method is formed in combination with a signal processing method and a deep learning algorithm. According to the invention, the real-time performance and comprehensiveness of lubrication state evaluation are enhanced, and the work and maintenance efficiency of equipment is also improved.

The invention discloses a mechanical equipment residual service life prediction and uncertainty quantitative analysis method and device. The method comprises the following steps: acquiring multi-dimensional time sequence sensor data generated by mechanical equipment to be predicted in an operation process; inputting the multi-dimensional time sequence sensor data into a pre-trained physical constraint Bayesian neural network model; wherein the physical constraint Bayesian neural network model comprises a segmented bidirectional long short-term memory network feature extraction module, a hierarchical gating recursive regression network degradation dynamic modeling module and a Bayesian reasoning and physical constraint fusion regression module which are connected in sequence; the segmented bidirectional long-short-term memory network feature extraction module is used for processing input multi-dimensional time sequence sensor data and outputting hidden feature vectors representing local degradation dynamics of equipment; the hierarchical gating recursive regression network degradation dynamic modeling module is used for processing hidden feature vectors and capturing global degradation dynamic features through a complex numerical value hidden state updating mechanism; the Bayesian reasoning and physical constraint fusion regression module is used for carrying out Weibull distribution parameter regression based on the global degradation dynamic characteristics, introducing a deep implicit physical residual constraint and outputting a probability distribution parameter of the residual service life; and based on the probability distribution parameters, generating a residual service life prediction result and uncertainty quantitative information of the mechanical equipment.

An AI-driven wireless lubricator remote control system includes multiple grease injection lubrication devices, a cloud server host and an artificial intelligence (AI) system. Each grease injection lubrication device includes a central control processing unit, a grease injection lubrication unit, a parameter setting unit, an operating status information unit, a detection unit, a warning unit, a wireless communication unit and a remaining oil volume information unit. The grease injection lubrication device can independently monitor the oil supply status and abnormal operating status information of individual lubrication points, and through wireless remote transmission (network or satellite network), the grease injection lubrication device information distributed on the mechanical equipment scattered around the factory is sent to the cloud server host. Furthermore, the mobile device can view the information of each grease injection lubrication device and issue commands directly through APP and the Internet (connected to the cloud server host).

The invention discloses a weak supervision soft contrast distillation fault diagnosis method and system based on micro automatic enhancement, equipment and a storage medium, and the method comprises the steps: obtaining a vibration signal of mechanical equipment operation, and dividing a sample set; the sample set is enhanced, and two different enhanced views are generated from each sample; performing feature extraction on the enhanced view to obtain deep feature coding representation; summing the comparison loss of the deep feature codes of each batch, and obtaining a comparison pre-training feature extractor after joint optimization; performing knowledge migration on the comparison pre-training feature extractor to a lightweight feature extractor by adopting a knowledge distillation strategy; using a lightweight feature extractor to obtain distinguishable feature representation, and training the distinguishable feature representation and the samples with the labels to obtain a fault state classification model; and the vibration signal passes through the lightweight feature extractor and then is input into the fault state classification model to obtain a fault diagnosis result.