Intelligent electrical variable measurement and calibration device for orthopedic surgical instrument

Abstract

The invention relates to the technical field of data processing, in particular to an intelligent electrical variable measurement and calibration device for an orthopedic surgical instrument, which comprises a display screen, a shell, an intelligent processing module, a power supply, a humidity sensor, a temperature sensor, a voltage sensor, a current sensor and a vibration sensor, the intelligent processing module comprises a data acquisition unit, a data processing unit, an instrument monitoring unit, a dynamic calibration unit and a power distribution unit, the electrical variable data is processed, and the working state of the instrument is monitored according to the processed electrical variable data, so that instrument faults can be found in time, and the working efficiency of the instrument is improved. The intelligent electrical variable measurement and calibration system can monitor the operating state of the orthopedic surgical instrument, automatically calibrate the monitoring process, improve the monitoring precision of the operating state of the instrument, flexibly adjust the power distribution of each unit, and improve the adaptability of the surgical instrument in different operation stages, thereby improving the data processing efficiency of intelligent electrical variable measurement and calibration of the orthopedic surgical instrument in the surgical process.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, and in particular to an intelligent electric variable measurement and calibration device for orthopedic surgical instruments. BACKGROUND

[0002] The existing measurement and calibration device has limitations in the accuracy of electric variable measurement. Orthopedic surgery has very high requirements for the accuracy of instruments. Small deviations in electric variables can cause deviations in the operation of surgical instruments, affecting the effectiveness of surgery. However, traditional devices are limited by low efficiency of electric digital data processing, making it difficult to meet the requirements of high-precision data processing. The existing device is severely lacking in the degree of intelligence in electric digital data processing. Traditional devices lack intelligent automatic calibration and adjustment functions and require manual operation by doctors, which not only increases the workload of doctors but also may affect the progress of surgery due to untimely or inaccurate operation. Moreover, traditional data processing and calibration devices mostly use a single and fixed power supply mode, which cannot dynamically adjust the power according to the actual needs of surgical instruments in different operation stages.

[0003] Chinese Patent Publication No. CN113855269A discloses an orthopedic surgical instrument calibration device, which includes a cabinet. The upper side of the cabinet is provided with a calibration table. However, this scheme still has the problem that the instrument cannot automatically calibrate the instrument working state, and the single power supply mode leads to poor adaptability of the surgical instrument in different operation stages, resulting in low data processing efficiency of intelligent electric variable measurement and calibration of orthopedic surgical instruments during surgery. SUMMARY

[0004] To overcome the problem that the instrument cannot automatically calibrate the instrument working state and the single power supply mode leads to poor adaptability of the surgical instrument in different operation stages, resulting in low data processing efficiency of intelligent electric variable measurement and calibration of orthopedic surgical instruments during surgery, the present application provides an intelligent electric variable measurement and calibration device for orthopedic surgical instruments.

[0005] To achieve the above-mentioned purpose, the present application provides an intelligent electric variable measurement and calibration device for orthopedic surgical instruments, which comprises: a display screen connected with the shell, used for displaying the instrument working state, electric variable data in the target surgical data, and environmental data in the target surgical data; a shell connected with the display screen, intelligent processing module, power supply, and sensor set, used for providing mechanical support and protection for the display screen, intelligent processing module, power supply, and sensor set; An intelligent processing module connected with the shell, used for intelligent processing of target surgical data, the intelligent processing including acquisition of target surgical data, surgical data processing of target surgical data, judgment of instrument working state and pushing of the instrument working state to a display screen, calibration of the instrument working state and power distribution of the instrument; A power supply connected with the shell, used for providing power for running of the device; A sensor set used for collecting target surgical data, the sensor set including a humidity sensor, a temperature sensor, a voltage sensor, a current sensor and a vibration sensor.

[0006] Further, the intelligent processing module includes: A data acquisition unit used for acquisition of target surgical data, the target surgical data including electrical variable data, environmental data and instrument vibration frequency, the electrical variable data including instrument voltage and instrument current, the environmental data including environmental humidity and environmental temperature, the data acquisition unit acquiring the instrument voltage through the voltage sensor, the data acquisition unit acquiring the instrument current through the current sensor, the data acquisition unit acquiring the environmental humidity through the humidity sensor, the data acquisition unit acquiring the environmental temperature through the temperature sensor, and the data acquisition unit acquiring the instrument vibration frequency through the vibration sensor; A data processing unit used for surgical data processing of target surgical data according to a surgical data processing method, to obtain target processing data; An instrument monitoring unit used for construction of an electrical variable prediction model according to an electrical variable prediction model construction method based on electrical variable data, construction of an environmental prediction model according to an environmental prediction model construction method based on environmental data, judgment of an instrument working state according to the electrical variable prediction model and the environmental prediction model, pushing of the instrument working state to a display screen, state adjustment of the judgment process of the instrument working state according to the instrument vibration frequency, state update of the process of state adjustment according to a surgical complexity index; A dynamic calibration unit used for algorithm calibration of the electrical variable prediction model and the environmental prediction model according to an algorithm calibration method, to obtain a calibrated electrical variable prediction model and a calibrated environmental prediction model, calibration adjustment of the process of algorithm calibration according to a current algorithmic power matching calibration frequency, and calibration update of the process of calibration adjustment according to a current surgical instrument precision index; The power distribution unit is configured to obtain a target distribution weight set by a target distribution weight set obtaining method, and correct the target distribution weight set according to a working state of the instrument by a target distribution weight set correction method, wherein the target distribution weight set comprises a power weight coefficient of the data acquisition unit, a power weight coefficient of the data processing unit, a power weight coefficient of the instrument monitoring unit, and a power weight coefficient of the dynamic calibration unit.

[0007] Further, the data processing unit is configured to perform surgical data processing on the target surgical data according to a surgical data processing method, wherein the surgical data processing method comprises a wavelet decomposition method, a filtering processing method, and an energy enhancement method. The data processing unit is configured to perform wavelet decomposition on the target surgical data according to a wavelet decomposition method, wherein the wavelet decomposition comprises: Step Q01, setting a target decomposition layer number as m; Step Q02, a first layer decomposition process comprises inputting the electrical variable data and the environmental data into a low-pass filter, outputting a first approximation component by the low-pass filter, inputting the electrical variable data and the environmental data into a high-pass filter, and outputting a first detail component by the high-pass filter; A second layer decomposition process comprises inputting the first approximation component into a low-pass filter, outputting a second approximation component by the low-pass filter, inputting the first approximation component into a high-pass filter, and outputting a second detail component by the high-pass filter; … An mth layer decomposition process comprises inputting an (m-1)th approximation component into a low-pass filter, outputting an mth approximation component by the low-pass filter, inputting an (m-1)th detail component into a high-pass filter, and outputting an mth detail component by the high-pass filter; The data processing unit is configured to perform filtering processing on the mth approximation component and the mth detail component by a filtering processing method, wherein the filtering processing method comprises: Step Q11, segmenting the mth approximation component and the mth detail component according to a preset number and a preset length L to obtain each small window xi, i=1, 2, 3, …, i-1, i, wherein i is a total number of the small windows; Step Q12, calculating a mean value μ of each small window xi according to each small window xi and the preset length L, and setting calculating a local variance X` of each small window according to each small window xi, the preset length L, and the mean value μ of each small window xi, and setting ; Step Q13, comparing each small window xi with the local variance X` of each small window, judging the validity of each small window xi according to a comparison result, and processing each small window xi according to a judgment result, wherein: When xi≤X`, the data processing unit determines that the validity of the small window xi is invalid, and sets the small window xi to zero; When xi>X`, the data processing unit determines that the validity of the small window xi is valid, and retains the small window xi; In step Q14, the mth approximation component and the mth detail component after the filtering process are taken as target processing components, the target processing components are reconstructed by inverse operations of the low-pass filter and the high-pass filter starting from the mth layer, and the reconstructed target processing components are taken as target reconstruction data; The data processing unit performs energy enhancement on the target reconstruction data according to an energy enhancement method, and the energy enhancement method comprises: In step Q21, each descendant coefficient is obtained by wavelet decomposition of the target reconstruction data, the energy Ej of each descendant coefficient is calculated according to the second target decomposition layer j, the descendant coefficient k, the number Nj,k of the sub-band coefficient k, and the wavelet coefficient Cj,k(n) of the jth layer and the kth sub-band, n=1,2,3……n-1,n, and n is the number of descendants, and E0 is set as ; In step Q22, the energy Ej of each descendant coefficient is compared with the preset energy E0, the importance of the energy Ej of each descendant coefficient is judged according to the comparison result, and the energy Ej of each descendant coefficient is enhanced according to the judgment result, wherein: When Ej≥E0, the data processing unit determines that the importance of the energy Ej of each descendant coefficient is important, and the energy Ej of each descendant coefficient is enhanced, the enhancement factor is set as α, and the energy of each descendant coefficient after enhancement is Ej`, Ej`=α×Ej; When Ej<E0, the data processing unit determines that the importance of the energy Ej of each descendant coefficient is not important, and the energy Ej of each descendant coefficient is not enhanced.

[0008] Further, the instrument monitoring unit constructs an electrical variable prediction model according to an electrical variable prediction model construction method, and the electrical variable prediction model construction method comprises: In step U01, 70% of the electrical variable historical data is divided into an electrical variable training set, and 30% of the electrical variable historical data is divided into an electrical variable verification set; In step U02, a recurrent neural network model is selected as an electrical variable prediction model, weights and biases of the electrical variable prediction model are initialized, the electrical variable training set is input into the electrical variable prediction model, and the output of the electrical variable prediction model is calculated; Step U03, calculate the loss function value according to the output of the electrical variable prediction model and the label, calculate the gradient by the back propagation algorithm, and update the weight and bias of the electrical variable prediction model, repeat the process of forward propagation, loss function calculation and back propagation, get the trained electrical variable prediction model; Step U04, input the electrical variable verification set into the trained electrical variable prediction model for testing, output the trained electrical variable prediction model with a correct rate of 90%, and take it as the electrical variable prediction model; The instrument monitoring unit constructs the environment prediction model according to the environment prediction model construction method, and the environment prediction model construction method comprises: Step Z01, 70% of the environment historical data is divided into an environment training set, and 30% of the environment historical data is divided into an environment verification set; Step Z02, select a recurrent neural network model as the environment prediction model, initialize the weight and bias of the environment prediction model, and input the environment training set into the environment prediction model to calculate the output of the environment prediction model; Step Z03, calculate the loss function value according to the output of the environment prediction model and the label, calculate the gradient by the back propagation algorithm, and update the weight and bias of the environment prediction model, repeat the process of forward propagation, loss function calculation and back propagation, get the trained environment prediction model; Step Z04, input the environment verification set into the trained environment prediction model for testing, output the trained environment prediction model with a correct rate of 90%, and take it as the environment prediction model.

[0009] Further, the instrument monitoring unit judges the instrument working state according to the instrument working state judgment method, and the instrument working state judgment method comprises: Step U01, input the electrical variable data into the electrical variable prediction model, and output the first instrument normal working state probability mk1(θ1), the first instrument slight fault state probability mk1(θ2) and the first instrument serious fault state probability mk1(θ3) according to the electrical variable prediction model; Step U02, input the environment data into the environment prediction model, and output the second instrument normal working state probability mk2(θ1), the second instrument slight fault state probability mk2(θ2) and the second instrument serious fault state probability mk2(θ3) according to the environment prediction model; Step U03, calculate the instrument normal working state probability m(θ1) according to the first instrument slight fault state probability mk1(θ2) and the second instrument serious fault state probability mk2(θ3), set , wherein θ1 represents the instrument normal working state, θ2 represents the instrument slight fault state, θ3 represents the instrument serious fault state, and ∅ represents an empty set. Step U04, according to the first instrument serious fault state probability mk1(θ3) and the second instrument normal working state probability mk2(θ1), the instrument slight fault synthesis probability m(θ2) is calculated, set ; Step U05, according to the first instrument slight fault state probability mk1(θ2) and the second instrument normal working state probability mk2(θ1), the instrument serious fault synthesis probability m(θ3) is calculated, set ; Step U06, according to the first preset weight w1, the second preset weight w2 and the third preset weight w3, w1+w2+w3=1, the instrument working state value Ep is calculated, set Ep=w1×m(θ1)+w2×m(θ2)+w3×m(θ3); Step U07, the instrument working state value Ep is compared with each preset working state value, the preset working state value includes the first preset working state value Ep1 and the second preset working state value Ep2, the state of the instrument working state value Ep is judged according to the comparison result, and the instrument working state is output according to the judgment result, wherein: When Ep≥Ep2, the instrument monitoring unit determines that the state of the instrument working state value Ep is normal, and the instrument normal working state is output as the instrument working state; When Ep1≤Ep<Ep2, the instrument monitoring unit determines that the state of the instrument working state value Ep is slightly abnormal, and the instrument slight fault state is output as the instrument working state; When Ep<Ep1, the instrument monitoring unit determines that the state of the instrument working state value Ep is abnormal, and the instrument serious fault state is output as the instrument working state.

[0010] Further, when the instrument monitoring unit adjusts the state of the instrument working state according to the instrument vibration frequency, the instrument vibration frequency F is compared with the preset vibration frequency F0, the condition of the instrument vibration frequency is judged according to the comparison result, and the state of the instrument working state value Ep is adjusted according to the judgment result, wherein: When F≤F0, the instrument monitoring unit determines that the condition of the instrument vibration frequency is low frequency, and does not adjust the state of the instrument working state value Ep; When F>F0, the instrument monitoring unit determines that the condition of the instrument vibration frequency is high frequency, and adjusts the state of the instrument working state value Ep, sets the vibration adjustment coefficient as α1, , the adjusted instrument working state value is Ep`, Ep`=α1×Ep; The instrument monitoring unit updates the state of the process of state adjustment according to the surgical complexity index. The surgical complexity index Fs is calculated according to the surgical time aa, the number of surgical steps ab, the technical difficulty value ac, the risk degree value ad, the preset surgical time aa0, the preset number of surgical steps ab0, the preset technical difficulty value ac0, and the preset risk degree value ad0. Fs=0.2×aa / aa0+0.2×ab / ab0+0.3×ac / ac0+0.2×ad / ad0 is set. The preset surgical time aa0 is a preset value reflecting the complexity of the surgical time, and 2 hours≤aa0≤5 hours is set. The preset number of surgical steps ab0 is a preset value reflecting the complexity of the surgical steps, and 95≤ab0≤110 is set. The preset technical difficulty value ac0 is a preset value reflecting the complexity of the technical difficulty value, and 60≤ac0≤90 is set. The preset risk degree value ad0 is a preset value reflecting the complexity of the risk degree value, and 20≤ad0≤60 is set. The surgical complexity index Fs is compared with the preset complexity index Fs0. The degree of the surgical complexity index Fs is judged according to the comparison result, and the instrument vibration frequency F is updated according to the judgment result, wherein: When Fs≤Fs0, the instrument monitoring unit determines that the degree of the surgical complexity index Fs is low, and does not update the instrument vibration frequency F; When Fs>Fs0, the instrument monitoring unit determines that the degree of the surgical complexity index Fs is high, and updates the instrument vibration frequency F. The complexity update coefficient is set as β, The updated instrument vibration frequency is F`, and F`=β×F.

[0011] Further, the dynamic calibration unit calibrates the electrical variable prediction model and the environment prediction model by an algorithm calibration method. The algorithm calibration method comprises: Step S01, self-calibration of the instrument is performed to generate a standard electrical signal value Db; Step S02, a calibration deviation value Dp is calculated according to the target processing data Ds and the standard electrical signal value Dbb. Dp=Ds-D is set. Step S03, the calibration deviation value Dp is compared with the preset deviation value Dp0. The deviation degree of the calibration deviation value Dp is judged according to the comparison result, and the electrical variable prediction model and the environment prediction model are calibrated by the algorithm according to the judgment result, wherein: When Dp≤Dp0, the dynamic calibration unit determines that the deviation degree of the calibration deviation value Dp is low, and does not calibrate the electrical variable prediction model and the environment prediction model by the algorithm; When Dp>Dp0, the dynamic calibration unit determines that the deviation degree of the calibration deviation value Dp is high, and algorithmically calibrates the electric variable prediction model and the environment prediction model; Step S04, self-calibration is performed on the instrument to generate a standard electric signal value sequence d(n`); Step S05, a measurement value sequence of target processing data is set as x(n`) and a gain parameter is set as w(n`), where n`=1, 2, 3……n`-1, n` and n` is the number of time points; Step S06, gain initialization is performed on the gain parameter w(n`); Step S07, an error signal g(n`) is calculated according to the standard electric signal value sequence d(n`), the gain parameter w(n`) and the measurement value sequence x(n`) of the target processing data, and g(n`) is set as d(n`)-w(n`)×x(n`); Step S08, an adjusted gain parameter w(n1) is calculated according to the gain parameter w(n`+1) of the next time, a step parameter v, the error signal g(n`) and the measurement value sequence x(n`) of the target processing data, and w(n`) is set as w(n+1)×v×g(n`)×x(n`); Step S09, a mean square error gh of the error signal is calculated according to the total number np of samples and the error signal g(n`), and gh is set as ; Step S10, the mean square error gh of the error signal is compared with a preset convergence preset value gh0, the compliance of the mean square error gh of the error signal is judged according to the comparison result, and the optimal gain parameter w(n`)` is output according to the judgment result, where: When gh≤gh0, the dynamic calibration unit determines that the compliance of the mean square error gh of the error signal is up to standard, and the adjusted gain parameter w(n1) is output as the optimal gain parameter w(n`)`; When gh>gh0, the dynamic calibration unit determines that the compliance of the mean square error gh of the error signal is not up to standard, and steps S04 to S07 are repeated until gh≤gh0; Step S11, a calibration signal x(t`) is calculated according to the measurement value sequence x(t) of the target processing data at the current time and the optimal gain parameter w(n`)`, and x(t`) is set as x(t)×w(n`)`; Step S12, the calibration signal x(t`) is input into the electric variable prediction model and the environment prediction model to obtain a calibrated electric variable prediction model and a calibrated environment prediction model.

[0012] Further, when the dynamic calibration unit adjusts the calibration process according to the current algorithm matching calibration frequency, the current algorithm matching calibration frequency Fj is compared with the preset calibration frequency Fj0, the frequency state of the current algorithm matching calibration frequency Fj is judged according to the comparison result, and the optimal gain parameter w(n`)` is adjusted according to the judgment result, wherein: When Fj≤Fj0, the dynamic calibration unit determines that the frequency state of the current algorithm matching calibration frequency Fj is low frequency, and does not adjust the optimal gain parameter w(n`)`; When Fj>Fj0, the dynamic calibration unit determines that the frequency state of the current algorithm matching calibration frequency Fj is high frequency, and adjusts the optimal gain parameter w(n`)`, sets the momentum adjustment coefficient as β1, The adjusted optimal gain parameter is w(n`)1`, and w(n`)1`=w(n`)`×β1; When the dynamic calibration unit updates the calibration process according to the current surgical instrument precision index, the current surgical instrument precision index Jc is obtained according to the national standard, the current surgical instrument precision index Jc is compared with the previous surgical precision index Jc0, the precision attribute of the current surgical instrument precision index Jc is judged according to the comparison result, and the current algorithm matching calibration frequency Fj is updated according to the judgment result, wherein: When Jc>Jc0, the dynamic calibration unit determines that the precision attribute of the current surgical instrument precision index Jc is low precision, and updates the current algorithm matching calibration frequency Fj, sets the frequency update coefficient as β2, The updated current algorithm matching calibration frequency is Fj`, and Fj`=Fj×β2; When Jc≤Jc0, the dynamic calibration unit determines that the precision attribute of the current surgical instrument precision index Jc is high precision, and does not update the current algorithm matching calibration frequency Fj.

[0013] Further, the power distribution unit obtains the target allocation weight set by a target allocation weight set obtaining method, and the target allocation weight set obtaining method comprises: Step B01, the instrument voltage Vp1 of the data acquisition unit, the instrument voltage Vp2 of the data processing unit, the instrument voltage Vp3 of the instrument monitoring unit and the instrument voltage Vp4 of the dynamic calibration unit are obtained by the voltage sensor, and the instrument current Ip1 of the data acquisition unit, the instrument current Ip2 of the data processing unit, the instrument current Ip3 of the instrument monitoring unit and the instrument current Ip4 of the dynamic calibration unit are obtained by the current sensor; Step B02, calculate the power P1 of the data acquisition unit according to the instrument voltage Vp1 of the data acquisition unit and the instrument current Ip1 of the data acquisition unit, set P1=Vp1×Ip1, calculate the power P2 of the data processing unit according to the instrument voltage Vp2 of the data processing unit and the instrument current Ip2 of the data processing unit, set P2=Vp2×Ip2, calculate the power P3 of the instrument monitoring unit according to the instrument voltage Vp3 of the instrument monitoring unit and the instrument current Ip3 of the instrument monitoring unit, set P3=Vp3×Ip3, calculate the power P4 of the dynamic calibration unit according to the instrument voltage Vp4 of the dynamic calibration unit and the instrument current Ip4 of the dynamic calibration unit, set P4=Vp4×Ip4; Step B03, calculate the total demand power Pt according to the power weight coefficient k1 of the data acquisition unit, the power P1 of the data acquisition unit, the power weight coefficient k2 of the data processing unit, the power P2 of the data processing unit, the power weight coefficient k3 of the instrument monitoring unit, the power P3 of the instrument monitoring unit, the power weight coefficient k4 of the dynamic calibration unit and the power P4 of the dynamic calibration unit, set Pt=k1×P1+k2×P2+k3×P3+k4×P4; Step B04, take the power weight coefficient k1 of the data acquisition unit, the power weight coefficient k2 of the data processing unit, the power weight coefficient of the instrument monitoring unit and the power weight coefficient k4 of the dynamic calibration unit as the target allocation weight set.

[0014] Further, the power distribution unit corrects the target allocation weight set according to the instrument working state through a target allocation weight set correction method, and the target allocation weight set correction method comprises: Step C01, power weight initialization is performed on the target allocation weight set; Step C02, when the instrument working state is the normal instrument working state, the target allocation weight set is not corrected; When the instrument working state is the instrument slight fault state, the total demand power Pt is compared with the preset total demand power Pt0, the demand degree of the total demand power Pt is judged according to the comparison result, and the target allocation weight set is corrected according to the judgment result, wherein: When Pt When Pt≥Pt0, the power distribution unit determines that the demand degree of the total demand power Pt is high demand, and corrects the target allocation weight set, and sets the power weight coefficient of the dynamic calibration unit to 0; When the instrument working state is the instrument serious fault state, the current computing power matching calibration frequency Fj and the surgical complexity index Fs are corrected, the current computing power matching calibration frequency after correction is set as Fj1`, Fj1` is set as (1+(Pt-P4) / Pt)xFj, the surgical complexity index after correction is set as Fs1`, Fs1` is set as (P4-Pt) / Pt)xFs.

[0015] Compared with the prior art, the beneficial effects of the present application are that the intelligent processing module acquires target surgical data through the data acquisition unit, thereby providing comprehensive data support for subsequent analysis, improving the accuracy of calibration, the intelligent processing module processes surgical data through the data processing unit, so as to facilitate subsequent accurate identification of the instrument state, thereby improving the effectiveness of device calibration, the intelligent processing module constructs an electrical variable prediction model and an environmental prediction model through the instrument monitoring unit, so as to accurately judge the instrument working state, thereby improving the calibration accuracy, the intelligent processing module automatically calibrates the instrument working state through the dynamic calibration unit, thereby improving the accuracy of data calibration, the intelligent processing module adjusts the power distribution and related parameters of each module according to the instrument working state through the power distribution unit, dynamically adjusts the power supply mode, improves the adaptability of surgical instruments in different operation stages, and thereby improves the data processing efficiency of intelligent electrical variable measurement and calibration of orthopedic surgical instruments in the surgical process. BRIEF DESCRIPTION OF DRAWINGS

[0016] Figure 1 The figure is a structural schematic diagram of the intelligent electrical variable measurement and calibration device for orthopedic surgical instruments in the embodiment. Figure 2 The figure is a structural schematic diagram of the intelligent processing module in the embodiment. DETAILED DESCRIPTION

[0017] In order to make the purpose and advantages of the present application more clear and explicit, the present application is further described below in combination with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present application, and do not limit the present application.

[0018] The preferred embodiments of the present application are described below with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are only used to explain the technical principles of the present application, and are not intended to limit the protection scope of the present application.

[0019] It should be noted that in the description of the present application, the terms "upper", "lower", "left", "right", "inner", "outer" and the like indicate the direction or positional relationship of the terms based on the direction or positional relationship shown in the drawings, which is only for the convenience of description, and does not indicate or imply that the device or element must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation on the present application.

[0020] In addition, it should be noted that in the description of the present application, unless otherwise explicitly specified and limited, the terms "mounting", "connection", "connection" should be understood broadly, for example, it can be fixedly connected, or it can be detachably connected, or integrally connected; it can be mechanically connected, or it can be electrically connected; it can be directly connected, or it can be indirectly connected through an intermediate medium; it can be the communication inside two elements. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0021] Please refer to Figure 1 As shown in the structure schematic diagram of the intelligent electric variable measurement and calibration device for orthopedic surgical instruments in the present embodiment, the device comprises: The display screen 1 is connected with the shell 2, and is used to display the instrument working state, the electric variable data in the target surgery data and the environmental data in the target surgery data; The shell 2 is connected with the display screen 1, the intelligent processing module 3, the power supply 4 and the sensor set, and is used to provide mechanical support and protection for the display screen, the intelligent processing module, the power supply and the sensor set; The intelligent processing module 3 is connected with the shell 2, and is used to intelligently process the target surgery data, the intelligent processing including acquiring the target surgery data, processing the target surgery data, judging the instrument working state and pushing the instrument working state to the display screen, calibrating the instrument working state and distributing power to the instrument; The power supply 4 is connected with the shell 2, and is used to provide power for the device to run; The sensor set is used to collect the target surgery data, and the sensor set includes a humidity sensor 5, a temperature sensor 6, a voltage sensor 7, a current sensor 8 and a vibration sensor 9.

[0022] Specifically, the device is applied in orthopedic surgery, the display screen displays parameters in real time to facilitate monitoring by medical staff, the shell protects the internal components to ensure hardware stability, the sensor set collects multi-dimensional data, the intelligent processing module intelligently processes the device, and the power supply provides the necessary power for the device to run, so as to improve monitoring accuracy, system reliability and surgical safety.

[0023] Specifically, the display screen 1 is used to display the instrument working state, the electrical variable data and the environmental data, the instrument working state includes the normal working state of the instrument, the slight fault state of the instrument and the serious fault state of the instrument, the electrical variable data includes the instrument voltage and the instrument current, and the environmental data includes the environmental humidity and the environmental temperature.

[0024] Specifically, the instrument working state refers to the comprehensive performance representation of the orthopedic surgical instrument during operation, the normal working state of the instrument refers to the state that the electrical variable data and the environmental data are within the preset functional values and can be continuously and stably operated without intervention, the slight fault state of the instrument refers to the state that the electrical variable data and the environmental data deviate from the preset functional values but do not exceed the allowable fluctuation range, the allowable fluctuation range refers to the normal variation interval of the electrical variable data and the environmental data which is set in advance, and the allowable fluctuation range is not limited in the embodiment, and the related technicians in the field can freely select according to the actual needs, as long as the fluctuation of the limited electrical variable data and the environmental data is met, for example, the allowable fluctuation range of the instrument voltage in the electrical variable data is ±10% of the rated voltage, the allowable fluctuation range of the instrument current in the electrical variable data is ±15% of the rated current, the allowable fluctuation range of the environmental temperature in the environmental data is 22±2℃, and the allowable fluctuation range of the environmental humidity in the environmental data is 40% RH, and the serious fault state of the instrument refers to the state that the electrical variable data and the environmental data exceed the allowable fluctuation range, the electrical variable data refers to the real-time measurement parameters reflecting the electrical characteristics of the orthopedic surgical instrument, including the instrument voltage and the instrument current, the environmental data refers to the environmental physical parameters affecting the performance of the instrument in the operating room, including the environmental humidity and the environmental temperature, the instrument voltage refers to the power supply voltage value of the instrument during operation, the instrument current refers to the real-time current value of the instrument during operation, the environmental humidity refers to the humidity of the air in the operating room, the environmental temperature refers to the air temperature in the operating room, and the instrument vibration frequency refers to the vibration frequency generated by the instrument during operation.

[0025] Specifically, the device monitors, evaluates and intelligently calibrates the electrical variable and environmental data of the orthopedic surgical instrument in real time through multi-dimensional sensor integration and intelligent processing module, thereby improving the safety, reliability and operation efficiency of the surgical instrument, the display screen 1 directly presents the instrument working state, the electrical variable data and the environmental parameters, so as to quickly master the equipment running condition, the shell 2 uniformly carries each functional module, improves the compactness of the structure, the intelligent processing module 3 intelligently processes the instrument in real time through the built-in algorithm, thereby improving the calibration efficiency of the device, and the power supply 4 provides continuous and reliable power output for the device, and ensures the normal operation of the device.

[0026] Please refer to Figure 2As shown, it is a structural schematic diagram of the intelligent processing module of the embodiment, which includes A data acquisition unit is configured to acquire target surgical data, which includes electrical variable data, environmental data, and instrument vibration frequency, the electrical variable data includes instrument voltage and instrument current, the environmental data includes environmental humidity and environmental temperature, the data acquisition unit acquires the instrument voltage through a voltage sensor, acquires the instrument current through a current sensor, acquires the environmental humidity through a humidity sensor, acquires the environmental temperature through a temperature sensor, and acquires the instrument vibration frequency through a vibration sensor; A data processing unit is configured to perform surgical data processing on the target surgical data according to a surgical data processing method, to obtain target processing data; An instrument monitoring unit is configured to construct an electrical variable prediction model according to electrical variable data through an electrical variable prediction model construction method, to construct an environmental prediction model according to environmental data through an environmental prediction model construction method, to judge the instrument working state according to the electrical variable prediction model and the environmental prediction model, and to push the instrument working state to a display screen, to adjust the process of judging the instrument working state according to the instrument vibration frequency, to update the process of state adjustment according to the surgical complexity index, and to update the process of state adjustment according to the current surgical instrument precision index; A dynamic calibration unit is configured to perform algorithm calibration on the electrical variable prediction model and the environmental prediction model through an algorithm calibration method, to obtain a calibrated electrical variable prediction model and a calibrated environmental prediction model, to adjust the process of algorithm calibration according to the current algorithm power matching calibration frequency, and to update the process of calibration adjustment according to the current surgical instrument precision index; A power distribution unit is configured to acquire a target distribution weight set through a target distribution weight set acquisition method, and to correct the target distribution weight set according to the instrument working state through a target distribution weight set correction method, the target distribution weight set includes power weight coefficients of the data acquisition unit, the data processing unit, the instrument monitoring unit, and the dynamic calibration unit.

[0027] Specifically, the intelligent processing module is applied to the intelligent electric variable measurement and calibration device for orthopedic surgical instruments. The intelligent processing module collects target surgical data through multi-dimensional sensors, so as to intelligently calibrate the instrument according to the target surgical data, flexibly allocate the device power, and thereby improve the safety, reliability and operation efficiency of the instrument. The intelligent processing module acquires target surgical data through a data acquisition unit, thereby providing comprehensive data support for subsequent analysis, improving the accuracy of calibration. The intelligent processing module processes surgical data through a data processing unit, so as to accurately identify the instrument state, thereby improving the effectiveness of device calibration. The intelligent processing module constructs an electric variable prediction model and an environment prediction model through an instrument monitoring unit, so as to accurately judge the instrument working state, thereby improving the calibration accuracy. The intelligent processing module calibrates the electric variable prediction model and the environment prediction model through a dynamic calibration unit, thereby improving the accuracy of data calibration. The intelligent processing module adjusts the power distribution and related parameters of each module according to the instrument working state through a power distribution unit, thereby improving the efficiency and stability of the device.

[0028] Specifically, the data acquisition unit acquires target surgical data, which includes electric variable data, environmental data and instrument vibration frequency. The data acquisition unit acquires target surgical data through a sensor collection.

[0029] Specifically, the data processing unit processes target surgical data according to a surgical data processing method, which includes a wavelet decomposition method, a filtering processing method and an energy enhancement method.

[0030] Specifically, the data processing unit decomposes target surgical data according to a wavelet decomposition method, which includes: Step Q01, set the target decomposition level as m; Step Q02, the first layer decomposition process is to input the electric variable data and the environmental data into a low-pass filter, output the first approximate component through the low-pass filter, input the electric variable data and the environmental data into a high-pass filter, and output the first detail component through the high-pass filter; The second layer decomposition process is to input the first approximate component into a low-pass filter, output the second approximate component through the low-pass filter, input the first approximate component into a high-pass filter, and output the second detail component through the high-pass filter; … The mth layer decomposition process is to input the m-1th approximation component into a low-pass filter, output the mth approximation component through the low-pass filter, input the m-1th detail component into a high-pass filter, and output the mth detail component through the high-pass filter.

[0031] Specifically, the wavelet decomposition refers to a method of decomposing a signal into components of different scales, the target decomposition layer number refers to the number of decomposition operations on the electrical variable data and the environmental data, the embodiment does not limit the decomposition layer number, for example, m=2 layers are set, the low-pass filter refers to a mechanism for allowing low-frequency signals to pass through while suppressing high-frequency signals, the high-pass filter refers to a mechanism for allowing high-frequency signals to pass through while suppressing low-frequency signals, wherein signals higher than a preset frequency are regarded as high-frequency signals, and signals lower than the preset frequency are regarded as low-frequency signals, the embodiment does not limit the preset frequency, for example, the preset frequency is set to 30 Hz in the embodiment, the approximation component refers to a low-frequency part obtained after low-pass filter processing, and the detail component refers to a high-frequency part obtained after high-pass filter processing.

[0032] Specifically, the data processing unit filters the mth approximation component and the mth detail component by a filtering processing method, and the filtering processing method includes: Step Q11, the mth approximation component and the mth detail component are segmented according to a preset number and a preset length L to obtain each small window xi, i=1, 2, 3……i-1, i, i is the total number of small windows; Step Q12, the mean value μ of each small window xi is calculated according to each small window xi and the preset length L, and is set to The local variance X` of each small window is calculated according to each small window xi, the preset length L, and the mean value μ of each small window xi, and is set to Step Q13, each small window xi is compared with the local variance X` of each small window, the effectiveness of each small window xi is judged according to the comparison result, and each small window xi is processed according to the judgment result, wherein: When xi≤X`, the data processing unit determines that the effectiveness of the small window xi is invalid, and the small window xi is set to zero; When xi>X`, the data processing unit determines that the effectiveness of the small window xi is valid, and the small window xi is retained; Step Q14, the mth approximation component and the mth detail component after filtering processing are taken as target processing components, the target processing components are reconstructed from the mth layer by inverse operation of the low-pass filter and the high-pass filter, and the reconstructed target processing components are taken as target reconstruction data. ​

[0033] Specifically, the preset number refers to the number of small windows preset when the detail component Dm is divided into small windows, the embodiment does not limit the preset number, for example, the preset number is set to 100, the preset length L refers to the number of data points contained in each small window, the embodiment does not limit the preset length L, for example, the preset length L is set to 10 ms, the small window xi refers to a plurality of subintervals obtained by dividing the detail component Dm according to the preset number and the preset length L, the mean value μ of the small window xi refers to the average value of all data points in the small window, the local variance X' of the small window refers to a value for measuring the degree of dispersion of data in the small window, the inverse operation of the low-pass filter and the high-pass filter refers to an operation of reconstructing the target processing component, the inverse operation includes upsampling and filtering operation, the upsampling refers to increasing the length of the target processing component to recover to the length before decomposition, the filtering operation refers to processing the target processing component using an inverse filter, the inverse filter refers to a prior art of reconstructing a signal, the embodiment does not limit the existing form of the inverse filter, for example, software form and physical form, and the reconstruction refers to a process of recombining the target processing component by inverse operation of the low-pass filter and the high-pass filter.

[0034] Specifically, the data processing unit performs energy enhancement on the target reconstruction data according to an energy enhancement method, and the energy enhancement method includes: Step Q21, performing wavelet decomposition on the target reconstruction data to obtain each descendant coefficient, calculating the energy Ej of each descendant coefficient according to the second target decomposition layer j, the descendant coefficient k, the number Nj,k of the descendant coefficient k, and the wavelet coefficient Cj,k(n) of the jth layer and the kth subband, n=1,2,3……n-1,n, n is the number of descendants, and setting ; Step Q22, comparing the energy Ej of each descendant coefficient with a preset energy E0, judging the importance of the energy Ej of each descendant coefficient according to the comparison result, and enhancing the energy Ej of each descendant coefficient according to the judgment result, wherein: When Ej≥E0, the data processing unit determines that the importance of the energy Ej of the descendant coefficient is important, and enhances the energy Ej of the descendant coefficient, sets the enhancement factor as α, and the energy of the enhanced descendant coefficient is Ej`, Ej`=α×Ej; When Ej<E0, the data processing unit determines that the importance of the energy Ej of the descendant coefficient is not important, and does not enhance the energy Ej of the descendant coefficient.

[0035] Step Q23, taking the target reconstruction data after energy enhancement as the target processing data.

[0036] Specifically, the sub-generation coefficient refers to a coefficient obtained after wavelet decomposition of the target reconstructed data, the energy Ej of each sub-generation coefficient refers to an index for measuring the importance of information contained in the sub-generation coefficient at the decomposition level, the second target decomposition level refers to the number of decomposition operations on the target reconstructed data, the preset energy E0 refers to a preset value for judging the importance of the energy Ej of the sub-generation coefficient, and the present embodiment does not limit the preset energy E0, such as setting E0=10 -3 KJ, the enhancement factor refers to a preset coefficient for enhancing the energy of the sub-generation coefficient, and the present embodiment does not limit the enhancement factor, such as setting the enhancement factor a=1.5 in the present embodiment.

[0037] Specifically, the data processing unit removes low-frequency noise by layering through a wavelet decomposition method, so as to retain high-frequency effective signals, the data processing unit segments and reconstructs the mth approximation component and the mth detail component through a filtering processing method, so as to restore the data after removing low-frequency noise through wavelet decomposition into complete data signals, and the data processing unit amplifies the energy of the effective signal of the reconstructed data through an energy enhancement method, so as to improve the effectiveness of the target surgical data, thereby improving the accuracy of measurement and calibration.

[0038] Specifically, the instrument monitoring unit constructs the electrical variable prediction model according to an electrical variable prediction model construction method, and the electrical variable prediction model construction method comprises: Step U01, 70% of the electrical variable historical data is divided into an electrical variable training set, and 30% of the electrical variable historical data is divided into an electrical variable verification set; Step U02, a recurrent neural network model is selected as the electrical variable prediction model, the weights and biases of the electrical variable prediction model are initialized, the electrical variable training set is input into the electrical variable prediction model, and the output of the electrical variable prediction model is calculated; Step U03, the loss function value is calculated according to the output of the electrical variable prediction model and the label, the gradient is calculated through the back propagation algorithm, and the weights and biases of the electrical variable prediction model are updated, the processes of forward propagation, loss function calculation and back propagation are repeated, and the trained electrical variable prediction model is obtained; Step U04, the electrical variable verification set is input into the trained electrical variable prediction model for testing, the trained electrical variable prediction model with a correct rate of 90% is output, and the trained electrical variable prediction model is taken as the electrical variable prediction model; The instrument monitoring unit constructs the environment prediction model according to an environment prediction model construction method, and the environment prediction model construction method comprises: Step Z01, 70% of the environment historical data is divided into an environment training set, and 30% of the environment historical data is divided into an environment verification set; Step Z02, selecting a recurrent neural network model as the environment prediction model, initializing the weights and biases of the environment prediction model, inputting the environment training set into the environment prediction model, and calculating the output of the environment prediction model; Step Z03, calculating the loss function value according to the output of the environment prediction model and the label, calculating the gradient by the back propagation algorithm, and updating the weights and biases of the environment prediction model, repeating the process of forward propagation, loss function calculation and back propagation to obtain the trained environment prediction model; Step Z04, inputting the environment verification set into the trained environment prediction model for testing, outputting the trained environment prediction model with a correct rate of 90%, and taking it as the environment prediction model.

[0039] Specifically, the electrical variable historical data includes historical electrical variable data as input data of the electrical variable prediction model, and the equipment working state feature data corresponding to the historical electrical variable data as the output result of the electrical variable prediction model, the equipment working state feature data includes equipment normal working probability, equipment slight fault state probability and equipment serious fault probability, the electrical variable training set refers to a data set for training the electrical variable prediction model, the electrical variable verification set refers to a data set for verifying the performance of the electrical variable prediction model in the training process of the electrical variable prediction model, the environment training set refers to a data set for training the environment prediction model, the environment verification set refers to a data set for verifying the performance of the environment prediction model in the training process of the environment prediction model, the initialization refers to the process of setting initial values for the weights and biases of the model when building the model, and the embodiment does not limit the initialization method. The related technical personnel can freely choose according to the actual needs, as long as the requirement of setting initial values for the weights and biases of the model is met, such as random initialization, the loss function value refers to a quantitative index for measuring the error between the model prediction result and the true label, the embodiment sets the loss function as mean square error, the label refers to the output result corresponding to the input data in the model, and the correct rate test refers to the process of evaluating the model to determine the proportion of the consistent model prediction result and the true result.

[0040] Specifically, the equipment monitoring unit constructs the electrical variable prediction model and the environment prediction model to accurately judge the equipment working state, thereby improving the calibration accuracy.

[0041] Specifically, the equipment monitoring unit judges the equipment working state according to the equipment working state judgment method, and the equipment working state judgment method includes: Step U01, inputting the electrical variable data into the electrical variable prediction model, outputting the first instrument normal working state probability mk1(θ1), the first instrument slight fault state probability mk1(θ2) and the first instrument serious fault state probability mk1(θ3) according to the electrical variable prediction model; Step U02, inputting the environmental data into the environmental prediction model, outputting the second instrument normal working state probability mk2(θ1), the second instrument slight fault state probability mk2(θ2) and the second instrument serious fault state probability mk2(θ3) according to the environmental prediction model; Step U03, calculating the instrument normal working synthesis probability m(θ1) according to the first instrument slight fault state probability mk1(θ2) and the second instrument serious fault state probability mk2(θ3), setting , wherein θ1 represents the instrument normal working state, θ2 represents the instrument slight fault state, θ3 represents the instrument serious fault state, and ∅ represents the empty set; Step U04, calculating the instrument slight fault synthesis probability m(θ2) according to the first instrument serious fault state probability mk1(θ3) and the second instrument normal working state probability mk2(θ1), setting ; Step U05, calculating the instrument serious fault synthesis probability m(θ3) according to the first instrument slight fault state probability mk1(θ2) and the second instrument normal working state probability mk2(θ1), setting ; Step U06, calculating the instrument working state value Ep according to the first preset weight w1, the second preset weight w2 and the third preset weight w3, w1+w2+w3=1, setting Ep=w1×m(θ1)+w2×m(θ2)+w3×m(θ3); Step U07, comparing the instrument working state value Ep with each preset working state value, the each preset working state value including the first preset working state value Ep1 and the second preset working state value Ep2, judging the state of the instrument working state value Ep according to the comparison result, and outputting the instrument working state according to the judgment result, wherein: when Ep≥Ep2, the instrument monitoring unit determines that the state of the instrument working state value Ep is normal, and outputs the instrument normal working state as the instrument working state; when Ep1≤Ep<Ep2, the instrument monitoring unit determines that the state of the instrument working state value Ep is slight abnormal, and outputs the instrument slight fault state as the instrument working state; when Ep<Ep1, the instrument monitoring unit determines that the state of the instrument working state value Ep is abnormal, and outputs the instrument serious fault state as the instrument working state.

[0042] Specifically, the instrument normal working state probability refers to a probability value of the instrument being in a normal working state, the instrument slight failure state probability refers to a probability value of the instrument being in a slight failure state, the instrument serious failure state probability refers to a probability value of the instrument being in a serious failure state, the preset function value refers to a range value preset for determining the instrument state, the embodiment does not limit the acquisition manner of the preset function value, and a person skilled in the art can freely select according to actual needs, as long as the requirement of acquiring the preset function value is met, such as a medical instrument supervision specification, the instrument normal working synthesis probability refers to an overall probability value of the instrument being in a normal working state calculated by a first synthesis formula, the empty set refers to a set without any element, the instrument slight failure synthesis probability refers to an overall probability value of the instrument being in a slight failure state calculated by a second synthesis formula, the instrument serious failure synthesis probability refers to an overall probability value of the instrument being in a serious failure state calculated by a third synthesis formula, the instrument working state value Ep refers to an overall state value of the instrument for evaluating the running condition of the instrument, the first preset weight refers to a coefficient preset for measuring the influence degree of the instrument normal working synthesis probability on the instrument working state value, the second preset weight refers to a coefficient preset for measuring the influence degree of the instrument slight failure synthesis probability on the instrument working state value, and the third preset weight refers to a coefficient preset for measuring the influence degree of the instrument serious failure synthesis probability on the instrument working state value, the embodiment does not limit the first preset weight, the second preset weight and the third preset weight, a person skilled in the art can freely select according to actual needs, as long as the requirement of distributing the weights is met, such as setting w1=0.7, w2=0.2, and w3=0.1, the first preset working state value Ep1 refers to a preset lower limit of the preset value for measuring the instrument working state value, and the second preset working state value Ep2 refers to a preset upper limit of the preset value for measuring the instrument working state value, the embodiment does not limit the first preset working state value Ep1 and the second preset working state value Ep2, a person skilled in the art can freely select according to actual needs, as long as the requirement of measuring the instrument working state value is met, such as setting Ep1=0.4 and Ep2=0.6 in the embodiment.

[0043] Specifically, the instrument monitoring unit outputs the instrument working state through the electrical variable prediction model and the environmental prediction model, thereby improving the efficiency of calibration of the device.

[0044] Specifically, when the instrument monitoring unit adjusts the state of the instrument working state value Ep according to the state of the instrument vibration frequency, the instrument vibration frequency F is compared with the preset vibration frequency F0, the state of the instrument vibration frequency is judged according to the comparison result, and the state of the instrument working state value Ep is adjusted according to the judgment result, wherein: When F≤F0, the instrument monitoring unit determines that the state of the instrument vibration frequency is low frequency, and does not adjust the state of the instrument working state value Ep; When F>F0, the instrument monitoring unit determines that the state of the instrument vibration frequency is high frequency, adjusts the state of the instrument working state value Ep, sets the vibration adjustment coefficient as α1, The adjusted instrument working state value is Ep`, Ep`=α1×Ep; When the instrument monitoring unit updates the state according to the process of the surgical complexity index, the surgical complexity index Fs is calculated according to the surgical time aa, the number of surgical steps ab, the technical difficulty value ac and the risk degree value ad, and set Fs=0.2×aa+0.2×ab+0.3×ac+0.2×ad. The surgical complexity index Fs is compared with the preset complexity index Fs0, the degree of the surgical complexity index Fs is judged according to the comparison result, and the state of the instrument vibration frequency F is updated according to the judgment result, wherein: When Fs≤Fs0, the instrument monitoring unit determines that the degree of the surgical complexity index Fs is low, and does not update the state of the instrument vibration frequency F; When Fs>Fs0, the instrument monitoring unit determines that the degree of the surgical complexity index Fs is high, and updates the state of the instrument vibration frequency F, sets the complexity update coefficient as β, The updated instrument vibration frequency is F`, F`=β×F.

[0045] Specifically, the preset vibration frequency F0 refers to a preset value used to judge the condition of the instrument vibration frequency, and the preset vibration frequency F0 is not limited in the embodiment, and a person skilled in the art can freely select according to actual needs, as long as the numerical setting of the preset vibration frequency is met. For example, F0 = 100 kHz in the embodiment, the vibration adjustment coefficient refers to a coefficient for adjusting the instrument working state value according to the condition of the instrument vibration frequency, the surgical complexity index Fs refers to a numerical value used to represent the complexity of the surgery, which is calculated based on the surgery time, the number of surgery steps, the technical difficulty value and the risk degree value, the surgery time refers to the length of time required to complete the surgery, and the embodiment does not limit the acquisition method of the surgery time, and a person skilled in the art can freely select according to actual needs, as long as the requirement of obtaining the surgery time is met, such as the operating room timing device, the number of surgery steps refers to the total number of steps required to complete the surgery, and the embodiment does not limit the acquisition method of the number of surgery steps, and a person skilled in the art can freely select according to actual needs, as long as the requirement of obtaining the number of surgery steps is met, such as the surgery operation specification document, the technical difficulty value refers to an index representing the difficulty of the surgery, and the embodiment does not limit the acquisition method of the technical difficulty value, and a person skilled in the art can freely select according to actual needs, as long as the requirement of obtaining the technical difficulty value is met, such as expert evaluation, the risk degree value refers to an index representing the risk degree of the surgery, and the embodiment does not limit the acquisition method of the risk degree value, and a person skilled in the art can freely select according to actual needs, as long as the requirement of obtaining the risk degree value is met, such as the risk assessment scale, the preset complexity index Fs0 refers to a preset value used to judge the degree of the surgical complexity index Fs, and the preset complexity index Fs0 is not limited in the embodiment, and the embodiment sets Fs0 = 0.38, the complexity update coefficient refers to a coefficient for updating the instrument vibration frequency F according to the surgical complexity index Fs, the preset surgery time aa0 refers to a preset value of the surgery time reflecting the complexity of the surgery, and is set to 2 hours ≤ aa0 ≤ 5 hours, the preset number of surgery steps ab0 refers to a preset value of the number of surgery steps reflecting the complexity of the surgery, and is set to 95 ≤ ab0 ≤ 110, the preset technical difficulty value ac0 refers to a preset value of the technical difficulty value reflecting the complexity of the surgery, and is set to 60 ≤ ac0 ≤ 90, and the preset risk degree value ad0 refers to a preset value of the risk degree value reflecting the complexity of the surgery, and is set to 20 ≤ ad0 ≤ 60.

[0046] Specifically, the instrument monitoring unit adjusts the instrument working state by setting a vibration adjustment coefficient, so that the instrument working state value Ep decreases with the increase of the instrument vibration frequency F, and sets a complexity update coefficient, so that the instrument vibration frequency F increases with the increase of the surgery complexity index Fs, thereby adjusting the instrument working state and improving the accuracy of the instrument working state.

[0047] Specifically, the dynamic calibration unit algorithmically calibrates the electrical variable prediction model and the environment prediction model by an algorithmic calibration method, which comprises: Step S01, self-calibration of the instrument to generate a standard electrical signal value Db; Step S02, calculation of the calibration deviation value Dp according to the target processing data Ds and the standard electrical signal value Db, set Dp=Ds-D; Step S03, comparison of the calibration deviation value Dp with the preset deviation value Dp0, judgment of the deviation degree of the calibration deviation value Dp according to the comparison result, and algorithmic calibration of the electrical variable prediction model and the environment prediction model according to the judgment result, wherein: When Dp≤Dp0, the dynamic calibration unit determines that the deviation degree of the calibration deviation value Dp is low, and does not algorithmically calibrate the electrical variable prediction model and the environment prediction model; When Dp>Dp0, the dynamic calibration unit determines that the deviation degree of the calibration deviation value Dp is high, and algorithmically calibrates the electrical variable prediction model and the environment prediction model; Step S04, self-calibration of the instrument to generate a standard electrical signal value sequence d(n`); Step S05, set the measurement value sequence of the target processing data as x(n`) and the gain parameter as w(n`), wherein n`=1,2,3……n`-1,n`, n` is the number of time points; Step S06, gain initialization of the gain parameter w(n`); Step S07, calculation of the error signal g(n`) according to the standard electrical signal value sequence d(n`) and the gain parameter w(n`) and the measurement value sequence x(n`) of the target processing data, set g(n`)=d(n`)-w(n`)×x(n`); Step S08, calculation of the adjusted gain parameter w(n1) according to the gain parameter w(n`+1) of the next time, the step parameter v, the error signal g(n`) and the measurement value sequence x(n`) of the target processing data, set w(n`)=w(n+1)×v×g(n`)×x(n`); Step S09, calculation of the mean square error gh of the error signal according to the total number of samples np and the error signal g(n`), set ; Step S10, comparing the mean square error gh of the error signal with the preset convergence preset value gh0, judging the compliance of the mean square error gh of the error signal according to the comparison result, and outputting the optimal gain parameter w(n`)` according to the judgment result, wherein: When gh≤gh0, the dynamic calibration unit determines that the compliance of the mean square error gh of the error signal is up to standard, and outputs the adjusted gain parameter w(n1) as the optimal gain parameter w(n`)`; When gh>gh0, the dynamic calibration unit determines that the compliance of the mean square error gh of the error signal is not up to standard, and repeats steps S04 to S07 until gh≤gh0; Step S11, calculating the calibration signal x(t)` according to the measurement value sequence x(t) of the target processing data at the current time and the optimal gain parameter w(n`)`, and setting x(t)`=x(t)×w(n`)`; Step S12, inputting the calibration signal x(t)` into the electrical variable prediction model and the environment prediction model to obtain the calibrated electrical variable prediction model and the calibrated environment prediction model.

[0048] Specifically, the self-calibration refers to a process of automatically calibrating the calibration module in the whole process during the idle period of the instrument through the built-in self-calibration reference source device, the self-calibration reference source device refers to a device for providing a high-precision standard signal and automatically completing the calibration process, the standard electrical signal value Db refers to an ideal electrical signal reference value generated in the self-calibration process, such as a rated voltage value, the calibration deviation value Dp refers to a value of the deviation degree of the quantitative acquisition data based on the target processing data and the standard electrical signal value Db, the preset deviation value Dp0 refers to a preset value for judging the deviation degree of the calibration deviation value Dp, and the preset deviation value Dp0 is not limited in the embodiment, and a person skilled in the art can freely select it according to actual needs, as long as the requirement of limiting the preset deviation value Dp0 is met, for example, the preset deviation value Dp0 is set to 2 in the embodiment, the standard electrical signal value sequence d(n`) refers to the standard electrical signal value on the discrete time sequence generated by the self-calibration, the measurement value sequence of the target processing data refers to the sequence of the electrical variable data and the environmental data collected in real time, the gain parameter refers to a coefficient for adjusting the measurement value sequence of the target processing data, the gain initialization refers to a process of setting the initial value of the parameter of the gain parameter w(n`), and the initial value setting of the parameter is not limited in the embodiment, and a person skilled in the art can freely select it according to actual needs, as long as the requirement of limiting the initial value of the parameter is met, for example, the initial value of the parameter is set to n`=0 and w(0)=1 in the embodiment, the error signal g(n`) refers to a parameter reflecting the calibration error under the current gain parameter, the step parameter refers to a parameter for controlling the iteration speed, and the step parameter is not limited in the embodiment, and a person skilled in the art can freely select it according to actual needs, as long as the requirement of controlling the iteration speed is met, for example, the step parameter is set to v=0.2, the total number of samples refers to the number of error signals for calculating the mean square error of the error signals, the preset convergence preset value gh0 refers to a preset value for judging whether the mean square error gh of the error signals meets the standard, and the preset convergence preset value gh0 is not limited in the embodiment, and a person skilled in the art can freely select it according to actual needs, as long as the requirement of limiting the preset convergence preset value gh0 is met, for example, the preset convergence preset value gh0 is set to 0.1 in the embodiment, the optimal gain parameter w(n`)` refers to a gain parameter value making the mean square error less than the preset convergence preset value, and the measurement value sequence of the target processing data at the current moment refers to the continuous time signal of the target processing data collected in real time.

[0049] Specifically, the dynamic calibration unit sets the preset convergence preset value gh0 to obtain the optimal gain parameter w(n`)`, and calibrates the electrical variable prediction model and the environmental prediction model according to the optimal gain parameter w(n`)` to improve the accuracy of the electrical variable prediction model and the environmental prediction model, thereby improving the accuracy of the working state of the instrument.

[0050] Specifically, when the dynamic calibration unit adjusts the process of algorithm calibration according to the current algorithm matching calibration frequency, it compares the current algorithm matching calibration frequency Fj with the preset calibration frequency Fj0, judges the frequency state of the current algorithm matching calibration frequency Fj according to the comparison result, and adjusts the optimal gain parameter w(n`)` according to the judgment result, wherein: When Fj≤Fj0, the dynamic calibration unit determines that the frequency state of the current algorithm matching calibration frequency Fj is low frequency, and does not adjust the optimal gain parameter w(n`)`; When Fj>Fj0, the dynamic calibration unit determines that the frequency state of the current algorithm matching calibration frequency Fj is high frequency, adjusts the optimal gain parameter w(n`)`, sets the momentum adjustment coefficient as β1, , the adjusted optimal gain parameter is w(n`)1`, w(n`)1`=w(n`)`×β1; When the dynamic calibration unit updates the process of calibration according to the current surgical instrument precision index, it compares the current surgical instrument precision index Jc with the previous surgical precision index Jc0 according to the national standard, judges the precision attribute of the current surgical instrument precision index Jc according to the comparison result, and updates the current algorithm matching calibration frequency Fj according to the judgment result, wherein: When Jc>Jc0, the dynamic calibration unit determines that the precision attribute of the current surgical instrument precision index Jc is low precision, updates the current algorithm matching calibration frequency Fj, sets the frequency update coefficient as β2, , the updated current algorithm matching calibration frequency is Fj`, Fj`=Fj×β2; When Jc≤Jc0, the dynamic calibration unit determines that the precision attribute of the current surgical instrument precision index Jc is high precision, and does not update the current algorithm matching calibration frequency Fj.

[0051] Specifically, the current computing power matching calibration frequency Fj refers to the real-time matching calibration operation execution frequency of the current hardware computing power resource. The current hardware computing power resource is not limited in the embodiment, such as processor performance and memory bandwidth. The embodiment does not limit the acquisition method of the current computing power matching calibration frequency Fj. Those skilled in the art can freely choose according to actual needs, as long as the requirement of acquiring the current computing power matching calibration frequency Fj is met, such as using a hardware monitoring tool. The preset calibration frequency Fj0 refers to a preset value for judging the frequency state of the current computing power matching calibration frequency Fj. The preset calibration frequency Fj0 is not limited in the embodiment, such as Fj0 = 2 times per operation in the embodiment. The national standard refers to the standard formulated by the standardization administrative department of the State Council, which uniformly regulates the technical requirements of medical devices nationwide. The acquisition method of the national standard is not limited in the embodiment, such as through the China National Standard Full Text Public System. The current surgical instrument precision index Jc refers to a quantitative parameter for measuring the key performance of the instrument in actual use. The previous operation precision index Jc0 refers to the standard instrument index of the previous operation. The preset value does not limit the acquisition method of the previous operation precision index Jc0. Those skilled in the art can freely choose according to actual needs, as long as the requirement of acquiring the previous operation precision index Jc0 is met, such as through the national standard.

[0052] Specifically, the dynamic calibration unit obtains the current surgical instrument precision index through the national standard, compares the current surgical instrument precision index with the previous operation precision index, so as to calibrate the precision requirement difference between the two operations. When the required precision of the current operation is higher than that of the previous operation, the current computing power matching calibration frequency is increased, so as to improve the precision of the current operation.

[0053] Specifically, the power distribution unit obtains the target allocation weight set through the target allocation weight set acquisition method. The target allocation weight set acquisition method includes: Step B01, obtaining the instrument voltage Vp1 of the data acquisition unit, the instrument voltage Vp2 of the data processing unit, the instrument voltage Vp3 of the instrument monitoring unit and the instrument voltage Vp4 of the dynamic calibration unit through the voltage sensor, and obtaining the instrument current Ip1 of the data acquisition unit, the instrument current Ip2 of the data processing unit, the instrument current Ip3 of the instrument monitoring unit and the instrument current Ip4 of the dynamic calibration unit through the current sensor; Step B02, calculating the power P1 of the data acquisition unit according to the instrument voltage Vp1 of the data acquisition unit and the instrument current Ip1 of the data acquisition unit, setting P1=Vp1×Ip1, calculating the power P2 of the data processing unit according to the instrument voltage Vp2 of the data processing unit and the instrument current Ip2 of the data processing unit, setting P2=Vp2×Ip2, calculating the power P3 of the instrument monitoring unit according to the instrument voltage Vp3 of the instrument monitoring unit and the instrument current Ip3 of the instrument monitoring unit, setting P3=Vp3×Ip3, calculating the power P4 of the dynamic calibration unit according to the instrument voltage Vp4 of the dynamic calibration unit and the instrument current Ip4 of the dynamic calibration unit, setting P4=Vp4×Ip4; Step B03, calculating the total demand power Pt according to the power weight coefficient k1 of the data acquisition unit, the power P1 of the data acquisition unit, the power weight coefficient k2 of the data processing unit, the power P2 of the data processing unit, the power weight coefficient k3 of the instrument monitoring unit, the power P3 of the instrument monitoring unit, the power weight coefficient k4 of the dynamic calibration unit and the power P4 of the dynamic calibration unit, setting Pt=k1×P1+k2×P2+k3×P3+k4×P4; Step B04, taking the power weight coefficient k1 of the data acquisition unit, the power weight coefficient k2 of the data processing unit, the power weight coefficient of the instrument monitoring unit and the power weight coefficient k4 of the dynamic calibration unit as the target allocation weight set; The power distribution unit corrects the target allocation weight set according to the instrument working state through a target allocation weight set correction method, and the target allocation weight set correction method comprises: Step C01, power weight initialization is performed on the target allocation weight set; Step C02, when the instrument working state is the normal instrument working state, the target allocation weight set is not corrected; When the instrument working state is the slight instrument fault state, the total demand power Pt is compared with the preset total demand power Pt0, the demand degree of the total demand power Pt is judged according to the comparison result, and the target allocation weight set is corrected according to the judgment result, wherein: When Pt When Pt≥Pt0, the power distribution unit determines that the demand degree of the total demand power Pt is high demand, and the target allocation weight set is corrected, and the power weight coefficient of the dynamic calibration unit is set to 0; When the working state of the instrument is the instrument serious fault state, the current computing power matching calibration frequency Fj and the surgical complexity index Fs are corrected, the corrected current computing power matching calibration frequency is set as Fj1`, Fj1` is set as (1+(Pt-P4) / Pt)xFj, and the corrected surgical complexity index is set as Fs1`, Fs1` is set as (P4-Pt) / Pt)xFs.

[0054] Specifically, the power weight coefficient of the data acquisition unit refers to a quantitative distribution coefficient of the importance degree of the power of the data acquisition unit in the calculation of the total demand power, the power weight coefficient of the data processing unit refers to a quantitative distribution coefficient of the importance degree of the power of the data processing unit in the calculation of the total demand power, the power weight coefficient of the instrument monitoring unit refers to a quantitative distribution coefficient of the importance degree of the power of the instrument monitoring unit in the calculation of the total demand power, the power weight coefficient of the dynamic calibration unit refers to a quantitative distribution coefficient of the importance degree of the power of the dynamic calibration unit in the calculation of the total demand power, and the power weight initialization refers to initial value setting of the target distribution weight set. The initial value setting is not limited in the embodiment, and a person skilled in the art can freely select according to actual needs, as long as the requirement of k4

[0055] Specifically, the power distribution unit adjusts the power distribution and related parameters of each module according to the working state of the instrument, so as to improve the efficiency and stability of the energy consumption distribution of the device.

[0056] So far, the technical scheme of the present application has been described in combination with the preferred embodiments shown in the drawings, but a person skilled in the art can easily understand that the protection scope of the present application is obviously not limited to these specific embodiments. A person skilled in the art can make equivalent changes or replacements to the related technical features without departing from the principles of the present application, and the technical scheme after the changes or replacements will fall within the protection scope of the present application.

Claims

1. An intelligent electrical variable measurement and calibration device for orthopedic surgical instruments, characterized by, The device comprises: a display screen connected with the shell, for displaying the working state of the instrument, the electrical variable data in the target surgery data and the environmental data in the target surgery data; a shell connected with the display screen, the intelligent processing module, the power supply and the sensor set, for providing mechanical support and protection for the display screen, the intelligent processing module, the power supply and the sensor set; an intelligent processing module connected with the shell, for intelligent processing of the target surgery data, the intelligent processing including acquisition of the target surgery data, surgery data processing of the target surgery data, judgment of the working state of the instrument and pushing of the working state of the instrument to the display screen, calibration of the working state of the instrument and power distribution of the instrument; a power supply connected with the shell, for providing power for the operation of the device; a sensor set for collecting the target surgery data, the sensor set including a humidity sensor, a temperature sensor, a voltage sensor, a current sensor and a vibration sensor.

2. The intelligent electrical parameter measurement and calibration device for orthopaedic surgical instruments as claimed in claim 1 wherein, The intelligent processing module comprises: a data acquisition unit for acquiring the target surgery data, the target surgery data including electrical variable data, environmental data and instrument vibration frequency, the electrical variable data including instrument voltage and instrument current, the environmental data including environmental humidity and environmental temperature, the data acquisition unit acquiring the instrument voltage through the voltage sensor, the data acquisition unit acquiring the instrument current through the current sensor, the data acquisition unit acquiring the environmental humidity through the humidity sensor, the data acquisition unit acquiring the environmental temperature through the temperature sensor, and the data acquisition unit acquiring the instrument vibration frequency through the vibration sensor; a data processing unit for surgery data processing of the target surgery data according to a surgery data processing method, to obtain target processing data; an instrument monitoring unit for constructing an electrical variable prediction model according to the electrical variable data through an electrical variable prediction model construction method, for constructing an environmental prediction model according to the environmental data through an environmental prediction model construction method, for judging the working state of the instrument according to the electrical variable prediction model and the environmental prediction model and pushing the working state of the instrument to the display screen, for adjusting the process of judging the working state of the instrument according to the instrument vibration frequency, and for updating the process of adjustment according to a surgery complexity index; a dynamic calibration unit for algorithm calibration of the electrical variable prediction model and the environmental prediction model through an algorithm calibration method, to obtain a calibrated electrical variable prediction model and a calibrated environmental prediction model, for adjusting the process of algorithm calibration according to the current algorithm power matching the calibration frequency, and for updating the process of adjustment according to a current surgery instrument precision index. The power distribution unit is configured to obtain a target distribution weight set by a target distribution weight set obtaining method, and correct the target distribution weight set according to a working state of the instrument by a target distribution weight set correction method, wherein the target distribution weight set comprises a power weight coefficient of the data acquisition unit, a power weight coefficient of the data processing unit, a power weight coefficient of the instrument monitoring unit, and a power weight coefficient of the dynamic calibration unit.

3. The intelligent electrical parameter measurement and calibration device for orthopaedic surgical instruments as claimed in claim 2 wherein, The data processing unit is configured to perform surgical data processing on target surgical data according to a surgical data processing method, wherein the surgical data processing method comprises a wavelet decomposition method, a filtering processing method, and an energy enhancement method. The data processing unit is configured to perform wavelet decomposition on the target surgical data according to the wavelet decomposition method, wherein the wavelet decomposition comprises: Step Q01: setting a target decomposition layer number as m; Step Q02: a first layer decomposition process comprises inputting the electrical variable data and the environmental data into a low-pass filter, outputting a first approximation component through the low-pass filter, inputting the electrical variable data and the environmental data into a high-pass filter, and outputting a first detail component through the high-pass filter; a second layer decomposition process comprises inputting the first approximation component into a low-pass filter, outputting a second approximation component through the low-pass filter, inputting the first approximation component into a high-pass filter, and outputting a second detail component through the high-pass filter; …… a mth layer decomposition process comprises inputting an (m-1)th approximation component into a low-pass filter, outputting an mth approximation component through the low-pass filter, inputting an (m-1)th detail component into a high-pass filter, and outputting an mth detail component through the high-pass filter; The data processing unit is configured to perform filtering processing on the mth approximation component and the mth detail component by a filtering processing method, wherein the filtering processing method comprises: Step Q11: segmenting the mth approximation component and the mth detail component according to a preset number and a preset length L to obtain each small window xi, i=1, 2, 3……i-1, i, i being a total number of small windows; Step Q12, calculating the mean value μ of each small window xi according to each small window xi and the preset length L, setting Step Q13, calculating the local variance X' of each small window according to each small window xi, the preset length L and the mean value μ of each small window xi, setting ; Step Q13: comparing each small window xi with a local variance X' of each small window, judging the effectiveness of each small window xi according to a comparison result, and processing each small window xi according to a judgment result, wherein: when xi≤X', the data processing unit determines that the effectiveness of the small window xi is invalid, and sets the small window xi to zero; when xi>X', the data processing unit determines that the effectiveness of the small window xi is valid, and retains the small window xi; Step Q14: taking the mth approximation component and the mth detail component after the filtering processing as target processing components, reconstructing the mth approximation component and the mth detail component from the mth layer by inverse operations of the low-pass filter and the high-pass filter, and taking the reconstructed target processing components as target reconstruction data; The data processing unit is configured to perform energy enhancement on the target reconstruction data according to an energy enhancement method, wherein the energy enhancement method comprises: Step Q21, wavelet-decomposing the target reconfiguration data to obtain each sub-generation coefficient, calculating the energy Ej of each sub-generation coefficient according to the second target decomposition layer j, the sub-generation coefficient k, the number Nj,k of the sub-band coefficient k, the wavelet coefficient Cj,k(n) of the jth layer and the kth sub-band, n=1, 2, 3…n-1, n, n being the number of sub-generations, setting ; Step Q22, comparing the energy Ej of each sub-coefficient with a preset energy E0, judging the importance of the energy Ej of the sub-coefficient according to the comparison result, and enhancing the energy Ej of the sub-coefficient according to the judgment result, wherein: When Ej≥E0, the data processing unit determines that the importance of the energy Ej of the sub-coefficient is important, and enhances the energy Ej of the sub-coefficient, sets the enhancement factor as α, and the enhanced energy of the sub-coefficient is Ej`, Ej`=α×Ej; When Ej<E0, the data processing unit determines that the importance of the energy Ej of the sub-coefficient is not important, and does not enhance the energy Ej of the sub-coefficient.

4. The intelligent electrical parameter measurement and calibration device for orthopaedic surgical instruments as claimed in claim 2 wherein, The instrument monitoring unit constructs the electrical variable prediction model according to the electrical variable data through the electrical variable prediction model construction method, and the electrical variable prediction model construction method comprises: Step U01, 70% of the electrical variable historical data is divided into an electrical variable training set, and 30% of the electrical variable historical data is divided into an electrical variable verification set; Step U02, a recurrent neural network model is selected as the electrical variable prediction model, the weights and biases of the electrical variable prediction model are initialized, the electrical variable training set is input into the electrical variable prediction model, and the output of the electrical variable prediction model is calculated; Step U03, the loss function value is calculated according to the output of the electrical variable prediction model and the label, the gradient is calculated through the back propagation algorithm, and the weights and biases of the electrical variable prediction model are updated, the processes of forward propagation, loss function calculation and back propagation are repeated, and the trained electrical variable prediction model is obtained; Step U04, the electrical variable verification set is input into the trained electrical variable prediction model for testing, the trained electrical variable prediction model with a correct rate of 90% is output, and is taken as the electrical variable prediction model; The instrument monitoring unit constructs the environment prediction model according to the environment data through the environment prediction model construction method, and the environment prediction model construction method comprises: Step Z01, 70% of the environment historical data is divided into an environment training set, and 30% of the environment historical data is divided into an environment verification set; Step Z02, a recurrent neural network model is selected as the environment prediction model, the weights and biases of the environment prediction model are initialized, the environment training set is input into the environment prediction model, and the output of the environment prediction model is calculated; Step Z03, the loss function value is calculated according to the output of the environment prediction model and the label, the gradient is calculated through the back propagation algorithm, and the weights and biases of the environment prediction model are updated, the processes of forward propagation, loss function calculation and back propagation are repeated, and the trained environment prediction model is obtained; Step Z04, the environment verification set is input into the trained environment prediction model for testing, the trained environment prediction model with a correct rate of 90% is output, and is taken as the environment prediction model.

5. The intelligent electrical parameter measurement and calibration device for orthopaedic surgical instruments as claimed in claim 4 wherein, The instrument monitoring unit judges the instrument working state according to the instrument working state judgment method, and the instrument working state judgment method comprises: Step U01, inputting the electrical variable data into the electrical variable prediction model, and outputting the first instrument normal working state probability mk1(θ1), the first instrument slight fault state probability mk1(θ2) and the first instrument serious fault state probability mk1(θ3) according to the electrical variable prediction model; Step U02, inputting the environmental data into the environmental prediction model, and outputting the second instrument normal working state probability mk2(θ1), the second instrument slight fault state probability mk2(θ2) and the second instrument serious fault state probability mk2(θ3) according to the environmental prediction model; Step U03, calculating the instrument normal working synthesis probability m(θ1) according to the first instrument slight fault state probability mk1(θ2) and the second instrument serious fault state probability mk2(θ3), setting , wherein θ1 represents the instrument normal working state, θ2 represents the instrument slight fault state, θ3 represents the instrument serious fault state, and ∅ represents an empty set; Step U04, the probability of the minor malfunction of the instrument m(θ2) is calculated according to the probability of the first instrument severe malfunction state mk1(θ3) and the probability of the second instrument normal working state mk2(θ1), set ; Step U05, calculating the instrument serious failure synthesis probability m(θ3) according to the first instrument slight failure state probability mk1(θ2) and the second instrument normal working state probability mk2(θ1), setting ; Step U06, calculating the instrument working state value Ep according to the first preset weight w1, the second preset weight w2 and the third preset weight w3, w1+w2+w3=1, and setting Ep=w1×m(θ1)+w2×m(θ2)+w3×m(θ3); Step U07, comparing the instrument working state value Ep with each preset working state value, the each preset working state value including the first preset working state value Ep1 and the second preset working state value Ep2, judging the state of the instrument working state value Ep according to the comparison result, and outputting the instrument working state according to the judgment result, wherein: when Ep≥Ep2, the instrument monitoring unit determines that the state of the instrument working state value Ep is normal, and outputs the instrument normal working state as the instrument working state; when Ep1≤Ep<Ep2, the instrument monitoring unit determines that the state of the instrument working state value Ep is slightly abnormal, and outputs the instrument slight fault state as the instrument working state; when Ep<Ep1, the instrument monitoring unit determines that the state of the instrument working state value Ep is abnormal, and outputs the instrument serious fault state as the instrument working state.

6. The intelligent electrical parameter measurement and calibration device for orthopaedic surgical instruments as claimed in claim 5 wherein, When the instrument monitoring unit adjusts the state of the instrument working state according to the instrument vibration frequency, the instrument monitoring unit compares the instrument vibration frequency F with the preset vibration frequency F0, judges the state of the instrument vibration frequency according to the comparison result, and adjusts the state of the instrument working state value Ep according to the judgment result, wherein: when F≤F0, the instrument monitoring unit determines that the state of the instrument vibration frequency is low frequency, and does not adjust the state of the instrument working state value Ep; When F>F0, the apparatus monitoring unit determines that the vibration frequency of the apparatus is high, adjusts the apparatus working state value Ep, and sets the vibration adjustment coefficient as α1, The adjusted apparatus working state value is Ep`, Ep`=α1×Ep. The instrument monitoring unit updates the state of the process of state adjustment according to the surgical complexity index. The surgical complexity index Fs is calculated according to the surgical time aa, the number of surgical steps ab, the technical difficulty value ac, the risk degree value ad, the preset surgical time aa0, the preset number of surgical steps ab0, the preset technical difficulty value ac0, and the preset risk degree value ad0. Fs=0.2×aa / aa0+0.2×ab / ab0+0.3×ac / ac0+0.2×ad / ad0 is set. The preset surgical time aa0 is a preset value reflecting the complexity of the surgical time, and 2 hours≤aa0≤5 hours is set. The preset number of surgical steps ab0 is a preset value reflecting the complexity of the surgical steps, and 95≤ab0≤110 is set. The preset technical difficulty value ac0 is a preset value reflecting the complexity of the technical difficulty value, and 60≤ac0≤90 is set. The preset risk degree value ad0 is a preset value reflecting the complexity of the risk degree value, and 20≤ad0≤60 is set. The surgical complexity index Fs is compared with the preset complexity index Fs0. The degree of the surgical complexity index Fs is judged according to the comparison result, and the instrument vibration frequency F is updated according to the judgment result, wherein: When Fs≤Fs0, the instrument monitoring unit determines that the degree of the surgical complexity index Fs is low, and does not update the instrument vibration frequency F; When Fs> Fs0, the apparatus monitoring unit determines that the degree of the surgery complexity index Fs is high, updates the state of the apparatus vibration frequency F, sets the complexity update coefficient as β, , and the updated apparatus vibration frequency is F`, F`=β×F.

7. The intelligent electrical parameter measurement and calibration device for orthopaedic surgical instruments as claimed in claim 2 wherein, The dynamic calibration unit calibrates the electrical variable prediction model and the environment prediction model by an algorithm calibration method. The algorithm calibration method includes: Step S01, self-calibration of the instrument to generate a standard electrical signal value Db; Step S02, calculate the calibration deviation value Dp according to the target processing data Ds and the standard electrical signal value Dbb, and set Dp=Ds-D; Step S03, compare the calibration deviation value Dp with the preset deviation value Dp0, judge the deviation degree of the calibration deviation value Dp according to the comparison result, and calibrate the electrical variable prediction model and the environment prediction model according to the judgment result, wherein: When Dp≤Dp0, the dynamic calibration unit determines that the deviation degree of the calibration deviation value Dp is low, and does not calibrate the electrical variable prediction model and the environment prediction model; When Dp>Dp0, the dynamic calibration unit determines that the deviation degree of the calibration deviation value Dp is high, and calibrates the electrical variable prediction model and the environment prediction model; Step S04, self-calibration of the instrument to generate a standard electrical signal value sequence d(n`); Step S05, set the measurement value sequence of the target processing data as x(n`), and the gain parameter as w(n`), where n`=1,2,3……n`-1,n`, n` is the number of time points; Step S06, gain initialization of the gain parameter w(n`); Step S07, set the gain parameter w(n`) as the gain parameter w(n`) of the target processing data, and set the measurement value sequence x(n`) as the measurement value sequence x(n`) of the target processing data, where n`=1,2,3……n`-1,n`, n` is the number of time points; Step S07, the error signal g(n`) is calculated according to the standard electrical signal value sequence d(n`), the gain parameter w(n`) and the measured value sequence x(n`) of the target processing data, and g(n`) is set as d(n`)-w(n`)×x(n`); Step S08, the adjusted gain parameter w(n1) is calculated according to the gain parameter w(n`+1) of the next moment, the step parameter v, the error signal g(n`) and the measured value sequence x(n`) of the target processing data, and w(n`) is set as w(n+1)×v×g(n`)×x(n`); Step S09, the mean square error gh of the error signal is calculated according to the total number of samples np and the error signal g(n'), and is set as ; Step S10, the mean square error gh of the error signal is compared with the preset convergence preset value gh0, the compliance of the mean square error gh of the error signal is judged according to the comparison result, and the optimal gain parameter w(n`)` is output according to the judgment result, wherein: When gh≤gh0, the dynamic calibration unit determines that the compliance of the mean square error gh of the error signal is up to standard, and the adjusted gain parameter w(n1) is output as the optimal gain parameter w(n`)`; When gh>gh0, the dynamic calibration unit determines that the compliance of the mean square error gh of the error signal is not up to standard, and repeats steps S04 to S07 until gh≤gh0; Step S11, the calibration signal x(t`) is calculated according to the measured value sequence x(t) of the target processing data at the current moment and the optimal gain parameter w(n`)`, and x(t`) is set as x(t)×w(n`)`; Step S12, the calibration signal x(t`) is input into the electrical variable prediction model and the environment prediction model to obtain the calibrated electrical variable prediction model and the calibrated environment prediction model.

8. The intelligent electrical parameter measurement and calibration device for orthopaedic surgical instruments as claimed in claim 7 wherein, When Fj≤Fj0, the dynamic calibration unit determines that the frequency state of the current algorithm matching calibration frequency Fj is low frequency, and does not calibrate the optimal gain parameter w(n`)`; When Jc≤Jc0, the dynamic calibration unit determines that the accuracy attribute of the current surgical instrument precision index Jc is high accuracy, and does not calibrate the current algorithm matching calibration frequency Fj. When Fj>Fj0, the dynamic calibration unit determines that the frequency state of the current computing power matching the calibration frequency Fj is high frequency, adjusts the optimal gain parameter w(n`)` and sets the momentum adjustment coefficient as β1, , and the adjusted optimal gain parameter is w(n`)1`, w(n`)1`=w(n`)`×β1; The power distribution unit acquires the target allocation weight set by the target allocation weight set acquisition method, and the target allocation weight set acquisition method comprises: When Jc>Jco, the dynamic calibration unit determines that the precision attribute of the current surgical instrument precision index Jc is low precision, updates the current algorithm matching calibration frequency Fj, and sets the frequency update coefficient as β2, The updated current algorithm matching calibration frequency is Fj', Fj'=Fj x β2; ​ 9. The intelligent electrical parameter measurement and calibration device for orthopaedic surgical instruments as claimed in claim 2 wherein, ​ Step B01, acquiring the instrument voltage Vp1 of the data acquisition unit, the instrument voltage Vp2 of the data processing unit, the instrument voltage Vp3 of the instrument monitoring unit and the instrument voltage Vp4 of the dynamic calibration unit through the voltage sensor, and acquiring the instrument current Ip1 of the data acquisition unit, the instrument current Ip2 of the data processing unit, the instrument current Ip3 of the instrument monitoring unit and the instrument current Ip4 of the dynamic calibration unit through the current sensor; Step B02, calculating the power P1 of the data acquisition unit according to the instrument voltage Vp1 of the data acquisition unit and the instrument current Ip1 of the data acquisition unit, setting P1=Vp1×Ip1, calculating the power P2 of the data processing unit according to the instrument voltage Vp2 of the data processing unit and the instrument current Ip2 of the data processing unit, setting P2=Vp2×Ip2, calculating the power P3 of the instrument monitoring unit according to the instrument voltage Vp3 of the instrument monitoring unit and the instrument current Ip3 of the instrument monitoring unit, setting P3=Vp3×Ip3, and calculating the power P4 of the dynamic calibration unit according to the instrument voltage Vp4 of the dynamic calibration unit and the instrument current Ip4 of the dynamic calibration unit, setting P4=Vp4×Ip4; Step B03, calculating the total demand power Pt according to the power weight coefficient k1 of the data acquisition unit, the power P1 of the data acquisition unit, the power weight coefficient k2 of the data processing unit, the power P2 of the data processing unit, the power weight coefficient k3 of the instrument monitoring unit, the power P3 of the instrument monitoring unit, the power weight coefficient k4 of the dynamic calibration unit and the power P4 of the dynamic calibration unit, setting Pt=k1×P1+k2×P2+k3×P3+k4×P4; Step B04, taking the power weight coefficient k1 of the data acquisition unit, the power weight coefficient k2 of the data processing unit, the power weight coefficient of the instrument monitoring unit and the power weight coefficient k4 of the dynamic calibration unit as the target allocation weight set.

10. The intelligent electrical parameter measurement and calibration device for orthopaedic surgical instruments as claimed in claim 9 wherein, The power distribution unit corrects the target allocation weight set according to the instrument working state through a target allocation weight set correction method, and the target allocation weight set correction method comprises: Step C01, power weight initialization is performed on the target allocation weight set; Step C02, when the instrument working state is the normal instrument working state, the target allocation weight set is not corrected; When the instrument working state is the slight instrument fault state, the total demand power Pt is compared with the preset total demand power Pt0, the demand degree of the total demand power Pt is judged according to the comparison result, and the target allocation weight set is corrected according to the judgment result, wherein: When Pt When Pt≥Pt0, the power distribution unit determines that the demand degree of the total demand power Pt is high demand, and corrects the target allocation weight set, setting the power weight coefficient of the dynamic calibration unit to 0. When the working state of the instrument is the instrument serious fault state, the current computing power matching calibration frequency Fj and the surgical complexity index Fs are corrected, the current computing power matching calibration frequency after correction is set as Fj1`, Fj1` is set as (1+(Pt-P4) / Pt)×Fj, and the surgical complexity index after correction is set as Fs1`, Fs1` is set as (P4-Pt) / Pt)×Fs.

Images