116 results about "Three axis accelerometer" patented technology

The invention relates to an AI server cooling water pump vibration quantity self-adaptive calibration test method and system, an intelligent test platform integrates a six-dimensional force sensor and a temperature compensation vibration exciter, the platform rigidity is automatically calibrated, a water pump-pipeline system transfer function is obtained, and a rotating speed-lift-modal frequency three-dimensional mathematical model is established; a three-axis MEMS accelerometer array is arranged at sensitive parts such as a water pump bearing seat and a motor shell, and vibration, current and pressure signals are synchronously collected; carrying out time-frequency domain signal processing by adopting variational mode decomposition in combination with self-adaptive S transformation, and extracting a 128-dimensional full-frequency domain feature vector containing a modulation side frequency band; effective values of vibration acceleration, speed and displacement are calculated through a frequency domain integration algorithm, and current harmonic interference is corrected through an electromagnetic vibration compensation model; and finally, a vibration health degree evaluation model containing 18 characteristic parameters is established based on a support vector machine, the test system comprises an intelligent test platform unit, a multi-source sensing unit, an edge calculation unit and a data management unit, and microsecond-level synchronous acquisition and GB-level data throughput are realized through a time sensitive network. And online incremental learning and automatic generation of a test report are supported. The method has the effect of improving the water pump vibration quantity test precision.

The present application relates to a sensor-weight system for an exercise machine. The system comprises a load cell, a three-axis accelerometer, a battery, a housing, a communication unit, a data processing unit, and a weight stack with multiple weights. The load cell interconnects a cable with the weight sword of the weight stack, allowing precise measurement of the user's exerted force during exercise.

The invention is a system for continuous monitoring of respiratory and gastric functions using wearable devices. Each device includes a three-axis accelerometer and optionally a gyroscopic sensor. They feature wireless communication for data transmission and means for attachment to the skin. A computation device analyzes the data, using a machine learning model to detect coughing, swallowing and respiration. The method involves placing sensors on the skin of the cricoid region and epigastric region, filtering and transmitting data, training the model, and plotting coughing frequency. This system enhances detection accuracy and facilitates early medical interventions, benefiting chronic condition management and postoperative care.

The invention provides a triaxial accelerometer based on a four-degree-of-freedom weak coupling resonator, the triaxial accelerometer comprises an upper-layer structure and a lower-layer structure, the upper layer is a micromechanical sensitive element constructed by taking silicon as a material, the lower layer is a glass base processed by a silicon dioxide material, and the glass base is used for providing mechanical support and electrical isolation functions. Wherein the micromechanical sensitive element has a signal conversion function; and the lower-layer glass base is formed by wet etching and metal sputtering processes and is used for signal output. On the basis of collaborative design of the orthogonally distributed resonance unit array and the mechanical amplification mechanism, electrostatic driving and amplitude ratio detection are combined, synchronous and accurate sensing of acceleration of the Y axis, the X axis and the Z axis is achieved through a single sensitive element, the technical limitation of a traditional single-axis detection mode is broken through, the complexity of a rear-end signal processing circuit is reduced, and the detection precision is improved. The device space utilization rate is improved.

The invention discloses a gastrointestinal decompression nursing device and a gastrointestinal tract pressure supervision system, and belongs to the technical field of medical nursing. A gastrointestinal decompression nursing device comprises a suction tank, a regulation and control box, a stomach tube and a flexible arm band, and the regulation and control box comprises a data preprocessing module and a control module; a plurality of flexible resistance type sensors are distributed in the flexible arm band at equal intervals, an in-vivo capsule is arranged at the front end of the stomach tube, and a pressure sensor and a three-axis accelerometer are arranged in the in-vivo capsule. According to the gastrointestinal nursing pressure reducer, the problem that an existing gastrointestinal nursing pressure reducer cannot achieve pressure nursing and supervision work according to different patients is solved, the in-vivo capsule is integrated with the pressure sensor, the triaxial accelerometer and the impedance sensor, and the pressure in an intestinal tract cavity, the peristalsis frequency and the content impedance can be synchronously collected; in combination with body surface pressure gradient data of the flexible arm band, improper treatment caused by misjudgment is avoided, and serious complications such as intestinal perforation and bleeding caused by delayed treatment are avoided.

The invention discloses an inclinometer magnetic interference error compensation method, system and device and a medium, and relates to the technical field of measurement while drilling, the method comprises the following steps: obtaining triaxial accelerometer data and triaxial magnetometer data collected by a plurality of preset azimuth angles of an inclinometer; performing magnetic interference preliminary correction on the data of the three-axis magnetometer by using a multi-measuring-point analysis method to obtain a preliminary correction azimuth angle; inputting the triaxial accelerometer data and the triaxial magnetometer data into a pre-trained error compensation model ICGO-RELM, and outputting a magnetic interference error compensation value; and compensating the initial correction azimuth angle based on the error compensation value to obtain final azimuth angle data. And the solving precision of the underground azimuth angle is improved.

The present disclosure provides a kind of inertial motion measurement double-axis rotation excitation enhancement method and system based on observability analysis.First, the system state space model of introducing double-axis rotation mechanism is constructed, the normalized observability analytical expression of sensor error under zero speed condition is derived based on Gramian matrix eigenvalue decomposition;Accordingly, the attitude condition of error observability maximization is determined, and the optimal rotation excitation strategy including a series of optimal observation positions is set;In the process of inertial navigation positioning assisted by zero speed update ZUPT, in non-zero speed interval, based on the optimal rotation excitation strategy, the IMU is sequentially guided to each optimal observation position by controlling double-axis rotation mechanism, to solve the problem of low error state observability caused by single carrier attitude in zero speed correction.The present application can realize full state high-precision estimation of three-axis accelerometer bias and gyroscope zero bias, effectively improve the precision and robustness of autonomous motion measurement in complex environment.

The invention relates to the technical field of hoisting machinery safety monitoring and control, and particularly discloses a portal crane moment limit protection method and system based on current verification. Real-time detection signals of a hoisting mechanism are obtained through a moment sensor, and a three-axis accelerometer is arranged at the connecting position of a steel wire rope to obtain swing signals; analyzing a jitter interference factor based on the steel wire rope jitter displacement, and judging the accuracy of a detection signal; on the premise that the signal is accurate, operation state detection of primary mechanical power calculation is carried out, then secondary operation state detection is carried out by combining the rated working current of the lifting frequency converter calculated by the detection signal and the real-time working current collected by the PLC, and the lifting mechanism is controlled to operate according to the detection result. Through multi-dimensional signal fusion and secondary verification, the detection precision and the overload judgment reliability are improved, the overload operation of equipment can be effectively prevented, and the operation safety of the crane and the service life of the equipment are guaranteed.

The invention provides a vehicle state identification method and device based on a triaxial accelerometer, equipment and a medium, and relates to the technical field of automotive electronics. The method comprises the following steps: a calibration stage: calculating and storing an initial attitude angle theta1 representing a horizontal static state of a vehicle; a data acquisition stage: calculating a real-time attitude angle theta2 representing the real-time state of the vehicle; a deviation value calculation stage: calculating an attitude deviation value delta theta based on the initial attitude angle theta 1 and the real-time attitude angle theta 2; in the vehicle state recognition and decision-making stage, at least one set of posture deviation threshold values are preset, the posture deviation value delta theta is compared with the posture deviation threshold values, meanwhile, at least two whole vehicle state signals are obtained through a vehicle communication interface, and the vehicle state recognition and decision-making stage is carried out on the basis of the comparison result of the posture deviation value delta theta and the posture deviation threshold values and the whole vehicle state signals. And comprehensively judging the current state of the vehicle. According to the invention, reliable and accurate identification of the vehicle state can be realized with extremely low cost through the triaxial accelerometer, and the false triggering rate is significantly reduced.

The application belongs to the technical field of music frequency point adjustment, and discloses an EQ frequency point self-adaptive adjustment method, device, equipment and storage medium, the method comprises the following steps: constructing a music database; detecting the music sound wave of the current music emitted by the audio generator by using a three-axis accelerometer, and obtaining a third three-axis change value of the music sound wave; comparing the third three-axis change value of the music sound wave with the range of the first three-axis change value in the music database, and determining the music type of the current music; detecting the music sound wave in real time by using the three-axis accelerometer, obtaining a fourth three-axis change value, and determining the real-time frequency EQ gain of the music sound wave according to the fourth three-axis change value; adaptively adjusting the EQ frequency point according to the music type, and adjusting the EQ playing gain according to the real-time frequency EQ gain; the music effect of sound playing is greatly improved, and the problem that the EQ frequency point value cannot be adaptively adjusted in real time according to the sound effect category of the current song is solved.

A system and method for avoiding unintended acceleration is provided and includes a first integrated circuit-based electronic controller configured to receive acceleration and brake requests and provide a control output via a datalink dedicated to controlling a prime mover system of the vehicle, a three-axis accelerometer configured to provide acceleration outputs indicative of acceleration of the accelerometer relative to three dimensions, and a second integrated circuit-based electronic controller operative independently of the first integrated circuit-based controller configured to receive the acceleration and braking requests, receive the acceleration outputs of the three-axis accelerometer, and operatively coupled with the datalink. The second integrated circuit-based electronic controller is configured to determine an unintended acceleration event in response to the acceleration and braking requests, and the acceleration outputs of the three-axis accelerometer.

The intelligent positioning and tracking device comprises a cap body, a three-axis magnetometer is fixedly connected to the front end of the left side of the cap body, a positioner is fixedly connected to the rear end of the left side of the cap body, and a three-axis accelerometer is fixedly connected to the front end of the right side of the cap body. And the rear end of the right side of the cap body is fixedly connected with a three-axis gyroscope. A worker wears the helmet body on the head, the first binding belt and the second binding belt can be firmly connected under the cooperation of the nylon velvet belt and the nylon hook belt, the three-axis accelerometer, the three-axis magnetometer, the three-axis gyroscope and the positioner are arranged, the position information of the worker can be positioned in real time, and the working efficiency is improved. A methane sensor, a carbon monoxide sensor, an oxygen concentration sensor, a temperature and humidity sensor, a dust concentration sensor and a microseismic monitoring sensor are arranged, and the methane concentration, the carbon monoxide concentration, the oxygen concentration, the temperature and humidity information, the dust concentration and the vibration condition in the environment can be detected respectively.

The invention belongs to the technical field of sleep detection, and particularly discloses a sleep detection method and system based on time sequence continuity optimization, and the method comprises the following steps: collecting original wrist strap accelerometer data through a triaxial accelerometer, and carrying out the preprocessing, thereby obtaining an input tensor; inputting the input tensor into a feature extraction module, and extracting local features and global features of the input tensor to obtain an advanced feature tensor; inputting the high-level feature tensor into a feature reconstruction module, and performing up-sampling and feature jump connection on the high-level feature tensor by adopting a linear interpolation reconstruction strategy to obtain a final data tensor; and carrying out secondary fine adjustment and time sequence smooth correction on the data tensor output by the feature reconstruction module to form complete sleep state prediction of one day per minute and corresponding confidence score output. By adopting the technical scheme, the residual unit is improved by utilizing the multi-scale cavity convolution, and the prediction result of the sleep event is more accurate through a bidirectional time sequence information processing mechanism.

The utility model discloses a three-axis acceleration sensor circuit and a three-axis accelerometer. The three-axis acceleration sensor circuit comprises an MCU module, an acceleration sensor module and a linear voltage stabilization module. The MCU module is provided with a first power supply end, a first input end and a first output end, the acceleration sensor module is provided with a second power supply end and a second output end, the second output end of the acceleration sensor module is connected with the first input end of the MCU module, and the linear voltage stabilization module is provided with a third output end. The third output end of the linear voltage stabilization module is connected with the first power end of the MCU module and the second power end of the acceleration sensor module. By integrating the acceleration sensor module, the MCU module and the linear voltage stabilization module, the acceleration of an object in the three-axis direction can be detected in real time, the influence of power supply noise is reduced, the accuracy of signal acquisition is improved, the integration level is improved, the power consumption is reduced, the size is reduced, and stable operation in a complex environment can be ensured.

The present application relates to a kind of pedestrian collaborative navigation method based on distance and angle, the collaborative navigation method includes: S1, by MIMU output each pedestrian respective three-axis accelerometer and three-axis gyroscope data, and carry out strapdown inertial navigation solution, again by the state of zero speed detection to the data of inertial navigation solution is carried out zero speed correction by extended Kalman filtering;S2, by UWB ranging angle measurement obtains the relative distance and angle between pedestrians as observation, then with the position information and heading angle information of N pedestrians as state quantity, carries out Kalman filtering, obtains the correction data of the position information and heading angle information of each pedestrian;S3, according to the position information and heading angle information of each pedestrian after correction collaborative navigation is carried out.The present application uses distance and angle as observation to correct pedestrian navigation after ZUPT auxiliary, solves the current pedestrian navigation heading angle drift and the problem of large amount of calculation of centralized filtering.

The application relates to an angle calibration solution method and system of a tilt sensor. Compared with the prior art, the method comprises the following steps: 1) collecting three-axis original acceleration data output by a three-axis accelerometer and performing filtering processing; 2) adopting a six-position calibration method to perform calibration; and 3) adopting a segmented combination angle solution method to calculate the included angle between the X axis and the Y axis of the tilt sensor relative to a horizontal plane. The application has the advantages of high accuracy and high precision in full-range measurement, smooth angle output, high calibration efficiency and the like.

The application discloses a building construction site data acquisition system based on Internet of Things and relates to the technical field of building engineering. The system is provided with a sound wave acquisition module, three-dimensional space is laid out with acquisition points in underground pouring structures, and an excitation source position is set in combination with the position of a pre-buried anchoring support, so that sound wave reverberation signals generated by wideband vibration signals are used to realize high-density and high-time-efficiency data acquisition. The MEMS three-axis accelerometer arranged in the acquisition point can collect the sound wave decay time Tdec and the reverberation residual energy peak value Ares of each acquisition point in real time, form a standard vibration sound wave energy data set, and provide a data basis for subsequent structure integrity judgment. Compared with traditional manual detection, image recognition and external detection methods, the system has the advantages of not needing to be damaged and not needing to additionally lay out ultrasonic equipment, and can realize early warning of internal interlayers, cavities and cold joints and real-time visualization of structure states in the construction process.

The invention provides a fall judgment method and a wearable device thereof. The method comprises the following steps: acquiring acceleration data based on a three-axis accelerometer, and acquiring inclination angle data based on an inclination angle sensor; determining a speed variation and a displacement variation of the wearable device in unit time based on the acceleration data, and determining final attitude information of the wearable device in space in combination with the inclination angle data; if it is determined that the posture of the wearable device is an abnormal movement posture based on the final posture information, starting a camera device to collect a front image of the wearable device, and determining the current orientation of the camera device; performing image analysis based on the front image to obtain human body features, and determining a relative position relationship between the human body and the ground based on the current orientation and the position of the human body features in the front image; and performing fall judgment based on the relative position relationship. According to the invention, the accuracy and reliability of fall judgment are improved.

This invention belongs to the field of inertial measurement technology, specifically an inertial measurement unit and its linear-angular coupling motion calibration method. It includes constructing a non-contact inertial measurement unit linear-angular motion synchronous measurement system. Through a reference cubic prism, a three-dimensional laser vibrometer, a first dual-axis autocollimator, a second dual-axis autocollimator, and a data acquisition module, an attitude transformation matrix is ​​established from the cubic mirror coordinate system to the inertial measurement unit coordinate system. By synchronously triggering the inertial measurement unit, based on the outputs of a three-axis gyroscope and a three-axis accelerometer, the three-axis acceleration measured by the three-dimensional laser vibrometer in the inertial measurement unit coordinate system, and the three-axis angular velocity of the inertial measurement unit measured by the dual-axis autocollimator, the linear-angular coupling motion of the inertial measurement unit is calibrated. This invention avoids the influence of vibration on the accuracy of the measurement system and solves the problem of difficulty in dynamically tracking and monitoring the actual motion of the inertial measurement unit during vibration.

The application discloses a MEMS three-axis accelerometer calibration method based on a simulated annealing particle swarm optimization algorithm, adopts a centrifuge to calibrate a MEMS three-axis accelerometer, uses angular velocity generated by the centrifuge as specific force input of the MEMS three-axis accelerometer, applies the simulated annealing particle swarm optimization algorithm to a nonlinear model for solving to-be-calibrated parameters of the MEMS three-axis accelerometer, and identifies corresponding parameters; in the calibration process, firstly, six-position tumbling method is used to determine scale factors and zero offset values of the three-axis accelerometer, and initial values of particle swarm iteration are determined, so that the convergence speed and stability of the algorithm are improved. By rotating a slave shaft on which the accelerometer is installed by 180 degrees, the influence of centrifuge system error on parameter identification is reduced. The method effectively excites high-order coefficients of the MEMS three-axis accelerometer, significantly reduces the uncertainty of unknown parameters of the MEMS three-axis accelerometer, and greatly improves the calibration precision.

The application relates to the field of power-assisted carrying technology, and particularly relates to an intelligent trolley, which comprises a trolley frame, a push rod, a handle arranged on the push rod, an electric control box fixed on a rear frame of the trolley frame, a central control circuit board integrated in the electric control box, a sensing module electrically connected with the central control circuit board through a line buried in the push rod and a bottom frame of the trolley frame, a three-axis accelerometer arranged on the bottom frame of the trolley frame, and an intelligent control system connected with the central control circuit board, wherein the intelligent control system comprises a function conversion module configured to acquire user input information or an actual running state of the trolley and correspondingly make the trolley be in or be converted to a corresponding function state, and a state control module configured to collect corresponding control condition information according to a current function state to control a running state of the trolley. The trolley can provide multiple function states to cope with different scenes and user demands.

The present application relates to the field of measurement while drilling technology, and more particularly to a method, system and electronic device for improving the measurement accuracy of data while drilling, the method comprising: obtaining the attitude angle of the drill string at the current time by using a MEMS three-axis accelerometer and a MEMS three-axis gyroscope, wherein the MEMS three-axis accelerometer and the MEMS three-axis gyroscope are both installed on the drill string; calculating the error compensation value corresponding to the attitude angle of the drill string at the current time; and compensating the attitude angle of the drill string at the current time by using the error compensation value corresponding to the attitude angle of the drill string at the current time, to obtain the final attitude angle of the drill string at the current time. The installation error of the MEMS three-axis accelerometer and the MEMS three-axis gyroscope installed on the drill string, the angle random walk error and the zero drift error can be reduced, and the measurement accuracy of the data while drilling, i.e. the attitude angle of the drill string, can be improved.

The invention discloses an electronic equipment falling protection system based on multi-dimensional sensing. The system comprises a multi-dimensional sensing array, an edge calculation unit, a self-adaptive magnetic field control system and a continuous learning unit, the multi-dimensional sensor array is integrated with a triaxial accelerometer, a gyroscope, a barometer and a magnetometer, and the edge calculation unit adopts a low-power-consumption FPGA and a customized neural network processor to execute a time sequence feature extraction and trajectory prediction algorithm. According to the invention, the problem of insufficient identification precision of a traditional single sensor method under insufficient illumination or complex scenes is overcome; a 5kHz high-frequency sampling rate is adopted, and a multi-stage assembly line parallel processing architecture is combined, so that efficient extraction and trajectory prediction of time sequence characteristics are realized, and the response speed of the system is greatly improved; according to the method, the system power consumption is effectively reduced, and meanwhile, the real-time performance and accuracy of the model are ensured; the multiple electronic devices are controlled to cooperatively generate the dynamic magnetic field network, accurate magnetic suspension track control is provided for the falling device, and the device damage risk is effectively reduced.

The invention relates to the technical field of intelligent gyroscopes, in particular to an intelligent gyroscope system and method.The intelligent gyroscope system comprises a gyroscope body, a motion detection module, a data processing module, a wireless communication module, a power module and a mobile terminal application, a sealed containing cavity is formed in the gyroscope body, and the gyroscope body is of a low-gravity-center structure; the motion detection module is arranged in the accommodating cavity, and the motion detection module comprises a six-axis inertial measurement unit, an integrated three-axis gyroscope and a three-axis accelerometer and is used for collecting rotation motion data of the gyroscope in real time; the data processing module is connected with the motion detection module and is used for filtering the collected original motion data and calculating the real-time rotation speed and rotation duration of the gyroscope; according to the invention, accurate quantification and objective recording of motion parameters are realized, and the competitive property and interestingness of the toy are improved.

The invention relates to the technical field of welding gun clamping, and discloses a welding gun clamping device which comprises a robot and a rotating arm, a miniature photoelectric encoder is arranged in an upper joint hemisphere, and a lower joint hemisphere is arranged at one end of the upper joint hemisphere. The upper joint hemisphere and the lower joint hemisphere are elastically connected through a plurality of belleville spring sets, a copper ring is embedded in a groove formed in the lower joint hemisphere, an integrated circuit board is arranged in the lower joint hemisphere, and a three-axis MEMS accelerometer is arranged at one end of the integrated circuit board. Passive compliance is achieved through the belleville spring set, active stabilization is achieved through the enameled wire coil-copper circular ring eddy current damper based on ACRI intelligent decision, the belleville spring set and the copper circular ring eddy current damper are connected in parallel and cooperate, and the contradiction that in a traditional scheme, the response speed and stability cannot be achieved at the same time is solved. And the efficiency and the reliability of automatic production can be greatly improved while complete functions are ensured.

The invention discloses a six-axis inertial sensor wearable device for cow behavior recognition and an edge processing system, and aims to solve the problems that an existing behavior monitoring system is high in power consumption, large in recognition delay, heavy in communication burden and the like. The device integrates a three-axis accelerometer and a three-axis gyroscope, adopts a low-frequency triggering and high-frequency sampling mechanism, and collects dairy cow attitude and motion data in an intermittent high-resolution sampling mode; an edge recognition algorithm is deployed locally, and behavior feature extraction and initial judgment of key behaviors such as oestrus are achieved; and communication uploading is triggered only when the identification event occurs, so that the energy consumption is obviously reduced and the identification real-time performance is improved. The system supports various wireless communication protocols and remote model updating, adapts to different cow varieties and breeding scenes, and is widely applied to oestrus monitoring and behavior management tasks in smart pastures. The method has the technical advantages of high energy efficiency, strong adaptability and intelligent cooperation, and is suitable for large-scale dairy cow behavior monitoring scenes.

The application relates to a MEMS accelerometer-based rocker arm inclination angle detection method, three three-axis MEMS accelerometers a, b and c are respectively installed in an electric control box and left and right rocker arms of a coal mining machine, the y detection axes of the accelerometers b and c are respectively parallel to swing axes of the left and right rocker arms, the z detection axes of the accelerometers b and c are vertically upward, the x detection axes of the accelerometers b and c are horizontally extended and far away from the swing axes of the respective rocker arms when the electric control box and the left and right rocker arms are in a horizontal state, the corresponding detection axes of the accelerometers a and c are parallel, then original acceleration vectors output by the MEMS accelerometers a, b and c are respectively acquired, the original acceleration vectors are subjected to filtering processing to obtain filtered acceleration vectors, inclination angle values of the filtered acceleration vectors relative to a horizontal plane are respectively calculated, and the included angles of the left and right rocker arms relative to the electric control box are respectively calculated. Compared with a traditional method, the application has the advantages of small sensor volume, simple installation and low cost.

An implantable medical device that includes an inflatable member, a fluid reservoir, a first pressure sensor connected to the fluid reservoir, a second pressure sensor connected to the inflatable member, an accelerometer configured to detect an acceleration of the implantable medical device along three orthogonal directions, and an electronic pump device. The electronic pump device includes a controller that is configured to execute operations that include receiving a first signal with pressure readings from the first pressure sensor and computing an ambient pressure value based on the pressure readings. The operations further include detecting an inflation pressure of the inflatable member using the second pressure sensor, receiving a second signal with acceleration data from the accelerometer, computing a gauge pressure based on the ambient pressure, the acceleration data, and the inflation pressure, and controlling inflation or deflation of the inflatable member based on the gauge pressure.

A system for acquiring ultrasound images of internal organs of a human body, includes a scanner and at least a minimum number of components in, or associated therewith including: i) an ultrasound probe head; ii) the at least one IMU, which comprises a three-axis accelerometer and a three-axis gyroscope; iii) electronic components for wired or wireless communication with remote terminals, and iv) a power source, wherein the 3-axis gyroscopes and 3-axis accelerometers of the IMU are calibrated by the manufacturer for offset, scale-factor, cross-axis sensitivity and initial orientation; and MEMS IMUs are calibrated by the user.

The application belongs to the field of sign language recognition, and provides a sign language recognition method based on wearable computing, and a sign language recognition system based on wearable computing, which comprises a pair of inertial data gloves, a routing device and a human-computer interaction platform. Each inertial data glove comprises sixteen inertial sensors and a wireless transmission module, wherein the inertial sensors comprise a three-axis accelerometer, a three-axis gyroscope and a three-axis magnetometer, and the wireless transmission module completes interaction with the human-computer interaction platform through the transmission control protocol with the routing device as the hub. The human-computer interaction module can operate the sign language recognition system, and is integrated with a trained Bi-LSTM model, hand data uploaded by the inertial data gloves is input into the Bi-LSTM model for sign language recognition, and the recognized sign language information is displayed. The system can recognize 20 kinds of Chinese dynamic sign languages, and has the characteristics of high precision, low power consumption, small device size and easy deployment and recognition.