Hotel intelligent clothes protection machine based on Internet of Things

Abstract

The invention discloses a hotel intelligent clothes protection machine based on the Internet of Things, and relates to the technical field of hotel intelligent clothes protection machines, and the method comprises the following steps: collecting various parameter information generated when an ultrasonic analysis device analyzes clothes materials in real time during the operation of the ultrasonic analysis device, wherein acoustic impedance characteristic information and signal scattering characteristic information are included. According to the invention, by introducing the intelligent evaluation system based on machine learning, the ultrasonic analysis equipment can identify the clothing material more accurately, and especially under the condition of foreign matter interference, abnormality evaluation and risk division are carried out by collecting acoustic impedance and signal scattering characteristic information in real time, so that the nursing program is optimized. Meanwhile, potential problems can be found in time through dynamic monitoring and an intelligent early warning mechanism of the equipment, the misjudgment risk is reduced, the operation efficiency and maintenance cost management are improved, and the service life of the equipment and the service quality of the hotel are ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of hotel intelligent clothing care machines, and in particular to a hotel intelligent clothing care machine based on the Internet of Things. Background Art

[0002] The hotel intelligent clothing care machine based on the Internet of Things is an innovative product that integrates Internet of Things technology and smart home devices, and is specially designed to provide efficient and convenient clothing care services for hotels. Through the wireless network, the clothing care machine is connected to the hotel's central management system to achieve remote monitoring, data sharing and intelligent management. Customers can make appointments and control the clothing care machine through the hotel's smart terminal or mobile phone application. The device will automatically detect the material of the clothes and select suitable care programs, such as ironing, disinfection and wrinkle removal. This systematic operation not only improves the efficiency of hotel clothing care, reduces manual intervention, but also improves customer experience. With the support of the Internet of Things, hotel managers can monitor the status of equipment in real time, carry out maintenance management in advance, reduce the failure rate, analyze guests' usage habits, optimize service resources, provide personalized care suggestions, enhance hotel competitiveness, and reduce operating costs. When customers are out, they can also remotely control the clothing care machine through their mobile phones to ensure that the clothes are processed, showing the future trend of intelligent hotel management that integrates technology and services.

[0003] In the prior art, hotel smart clothing care machines based on the Internet of Things use ultrasonic analysis equipment, especially in high-end care that requires precise detection of clothing materials. The function of ultrasonic analysis equipment is to analyze the internal structure and fiber density of clothing by emitting high-frequency sound waves and detecting their propagation speed, reflection and attenuation in clothing. Different materials (such as cotton, silk, wool, etc.) react differently to ultrasound, and ultrasonic equipment can judge the thickness, softness and fiber arrangement of clothing based on these differences. Combined with the Internet of Things technology, the clothing care machine can transmit the analysis results to the central system and adjust the ironing, drying or steam care mode in real time. This non-contact and precise detection method effectively improves the safety and efficiency of clothing care, avoids damage to clothing due to misjudgment of materials, and provides users with more intelligent and personalized care services.

[0004] The prior art has the following deficiencies:

[0005] When the hotel intelligent clothing care machine based on the Internet of Things analyzes the material of clothing through ultrasonic analysis equipment, if there are foreign substances (such as stains, detergent residues, etc.) left on the clothing, it will interfere with the propagation of ultrasonic waves, causing the device to be unable to accurately identify the material of the clothing. Accurate identification of materials is the key to the intelligent clothing care machine to select the appropriate care mode. When misjudgment is caused by interference from foreign substances, the clothing care machine may choose the wrong care program. For example, mistaking silk for synthetic fibers may lead to the use of high-temperature ironing or strong drying, which directly damages delicate fabrics, causing them to deform, become brittle or lose their luster, and even over-drying or improper ironing, which seriously affects the appearance and life of the clothes. For hotel customers, the core value of the intelligent clothing care machine lies in providing efficient and convenient high-end care services. However, mishandling caused by residual foreign substances will not only weaken the customer experience, but especially in high-end hotels, any damage to clothing or poor results caused by care errors will cause customer dissatisfaction and complaints, thereby damaging the hotel's reputation and customer trust.

[0006] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0007] The purpose of the present invention is to provide a hotel intelligent clothing care machine based on the Internet of Things. By introducing an intelligent evaluation system based on machine learning, the ultrasonic analysis equipment can more accurately identify the material of clothing, especially in the case of interference from foreign objects, and perform abnormal evaluation and risk division by real-time acquisition of acoustic impedance and signal scattering characteristic information to optimize the nursing procedure. At the same time, the dynamic monitoring and intelligent early warning mechanism of the equipment can timely discover potential problems, reduce the risk of misjudgment, improve operating efficiency and maintenance cost management, ensure the service life of the equipment and the service quality of the hotel, so as to solve the problems in the above-mentioned background technology.

[0008] In order to achieve the above object, the present invention provides the following technical solution: a hotel intelligent clothing care machine based on the Internet of Things, comprising the following steps:

[0009] During the operation of the ultrasonic analysis device, various parameter information generated by the ultrasonic analysis device when analyzing the clothing material is collected in real time, including acoustic impedance characteristic information and signal scattering characteristic information;

[0010] Perform an abnormal analysis on the collected acoustic impedance characteristic information and signal scattering characteristic information, and input the acoustic impedance characteristic information and signal scattering characteristic information after abnormal analysis into a pre-learned machine learning model, generate an acoustic wave transmission coefficient through the machine learning model, and intelligently evaluate the process of ultrasonic analysis equipment analyzing clothing materials through the acoustic wave transmission coefficient;

[0011] Based on the machine learning evaluation results, the clothing material analysis process of the ultrasonic analysis equipment is divided into a normal recognition process or an abnormal recognition process, and the abnormal clothing material recognition process is intelligently perceived;

[0012] When the ultrasonic analysis device analyzes the material of clothing, an abnormal recognition process is generated, the analysis information of the clothing material by the ultrasonic analysis device is continuously obtained, and the process of the ultrasonic analysis device analyzing the material of clothing is comprehensively judged.

[0013] Preferably, the acoustic impedance characteristic information includes ultrasonic propagation impedance, and the signal scattering characteristic information includes ultrasonic signal scattering. Ultrasonic propagation impedance refers to the resistance encountered by ultrasonic waves when propagating in different media, which is specifically determined by the density and sound speed of the medium. Ultrasonic signal scattering refers to the deviation or dispersion of the propagation direction and intensity of the sound wave when the ultrasonic wave encounters inhomogeneities in the material during propagation.

[0014] Preferably, an acoustic impedance matching anomaly index is generated after an abnormal analysis of the ultrasonic propagation impedance, and a scattering deviation fluctuation index is generated after an abnormal analysis of the ultrasonic signal scattering. The impedance matching anomaly index and the scattering deviation fluctuation index after the abnormal analysis are input into a pre-learned machine learning model, and an acoustic wave transfer coefficient is generated through the machine learning model. The acoustic wave transfer coefficient is used to intelligently evaluate the process of ultrasonic analysis equipment analyzing clothing materials.

[0015] Preferably, the logic of performing abnormal analysis on ultrasonic propagation impedance and generating an abnormal index of acoustic impedance matching is as follows:

[0016] Under the detection window, the propagation impedance data of the clothing material is obtained from multiple detection points. The specific parameters include the acoustic impedance Z1 of the ultrasonic emission source, the acoustic impedance Z2(x,y) of the clothing material at different positions, the emission intensity I1 of the initial ultrasonic wave, and the intensity I2(x,y) of the ultrasonic wave reflected from the clothing surface. The position of the clothing material at different positions in the acoustic impedance Z2(x,y) is represented by two-dimensional coordinates x and y.

[0017] Based on the acquired acoustic impedance Z1 of the ultrasonic emission source and the acoustic impedance Z2(x,y) of the clothing material at different positions, the reflection coefficient of each detection point is calculated to comprehensively judge the impedance matching abnormality. The calculation expression is as follows:

[0018]

[0019] , where R(x,y) is the reflection coefficient, which represents the reflection coefficient of each detection point;

[0020] In order to make the detection of anomalies more accurate, a nonlinear fluctuation model is introduced to evaluate the impedance volatility within the detection window. The impedance fluctuation index is defined by the nonlinear fluctuation model. The calculation expression is as follows:

[0021]

[0022] , where W(x,y) is the impedance fluctuation index, is the gradient of impedance change with position, indicating the rate of change of impedance in different areas;

[0023] Based on the impedance fluctuation index, the impedance fluctuation index of the entire detection window is accumulated and calculated to generate a spatial weighted cumulative function. The calculation expression is as follows:

[0024]

[0025] , where S W is the cumulative fluctuation function, and f(x,y) is the weight function of the position (x,y), which is used to adjust the contribution of different positions to the cumulative fluctuation;

[0026] In order to quantify the degree of impedance matching anomaly, the accumulated fluctuation function S W Normalized with the normal fluctuation threshold of the system, and combined with the nonlinear adjustment term of the reflection coefficient, the final acoustic impedance matching anomaly index is generated. The calculation expression is as follows:

[0027]

[0028] , where Impedance Mi is the acoustic impedance matching anomaly index, S norm is the normal fluctuation reference value preset by the system, R avg is the weighted average of the reflection coefficient in the area, R max is the theoretical maximum reflection coefficient, It is a nonlinear adjustment term.

[0029] Preferably, the logic of performing abnormal analysis on ultrasonic signal scattering and generating the scattering deviation fluctuation index is as follows:

[0030] In the detection window, the waveform data of the reflected signal is collected in real time. In order to reduce noise interference, the signal is first denoised, and the amplitude information in the waveform is used to calculate the strength of the reflected signal. The strength of the reflection is judged according to the signal strength fluctuation at each moment. The calculation expression is as follows:

[0031] I(t)=|S filtered (t)| 2

[0032] , where I(t) is the intensity of the reflected signal, i.e., the intensity of the reflected signal at time t, S filtered (t) represents the reflection signal after preprocessing;

[0033] In order to capture the nonlinear changes in the ultrasonic reflection process, the nonlinear dynamic analysis method is used to calculate the complexity and change rate of the reflected signal fluctuations. The calculation expression is as follows:

[0034]

[0035] , where λ(t) is the local Lyapunov index, which indicates the nonlinear characteristics of the reflected signal, Δt is the interval between two time points, and S filtered (t+Δt) is the preprocessed reflection signal at time t+Δt;

[0036] In addition to the nonlinear characteristics of the reflected signal, phase change is also an important indicator of reflection anomaly. The deviation of the reflected signal is characterized by calculating the change of the signal phase at different time points. The calculation expression is as follows:

[0037]

[0038] , where is the phase difference, which indicates the phase change of the reflected signal at time t, Re{S filtered (t)} represents the real part of the preprocessed ultrasonic reflection signal at time t, m{S filtered (t)} represents the imaginary part of the preprocessed ultrasonic reflection signal at time t;

[0039] Combining the intensity I(t) of the reflected signal, the local Lyapunov exponent λ(t) and the phase difference , generate the scattering deviation fluctuation index, the calculation expression is as follows:

[0040]

[0041] , where Scattering DF is the scattering deviation fluctuation index, α1 is the weight coefficient of the intensity I(t) of the reflected signal, α2 is the weight coefficient of the local Lyapunov index λ(t), and α3 is the phase difference is the weight coefficient, β is the nonlinear coefficient, t0 and t1 are the starting and ending points of the time interval.

[0042] Preferably, the acoustic impedance matching abnormality index Impedance Mi Scattering DF Input into the pre-learned machine learning model, and generate the acoustic wave transmission coefficient Acoustic through the machine learning model WP , based on the formula:

[0043]

[0044] , where f1 and f2 are the acoustic impedance matching anomaly index Impedance Mi Scattering DF The preset proportional coefficient, and f1 and f2 are both greater than 0.

[0045] Preferably, the sound wave transmission coefficient generated by the machine learning model is compared and analyzed with a preset reference threshold of the sound wave transmission coefficient, and the process of the ultrasonic analysis device analyzing the clothing material is divided as follows:

[0046] If the sound wave transmission coefficient is greater than or equal to a preset sound wave transmission reference threshold, the process of analyzing the clothing material by the ultrasonic analysis device is classified as an abnormality recognition process;

[0047] If the sound wave transmission coefficient is less than a preset sound wave transmission reference threshold, the process of analyzing the clothing material by the ultrasonic analysis equipment is classified as a normal recognition process.

[0048] Preferably, after the process of analyzing the clothing material by the ultrasonic analysis device is divided into the abnormality identification process, a plurality of acoustic wave transmission coefficients subsequently generated when the ultrasonic analysis device analyzes the clothing material are continuously acquired to establish a data set for comprehensive analysis, and the abnormality identification process is further divided;

[0049] The average values ​​and standard deviations of several acoustic wave transmission coefficients in the data set are calculated, and the calculated average values ​​and standard deviations of the acoustic wave transmission coefficients are compared with the preset reference threshold values ​​of the average values ​​and standard deviations of the acoustic wave transmission coefficients, respectively. The comparison results are as follows:

[0050] If the average value of the acoustic wave transmission coefficient is greater than or equal to a preset reference threshold value of the average value of the acoustic wave transmission coefficient, the abnormal identification process generated when the ultrasonic analysis device analyzes the material of the clothing is further divided into a high-risk identification state, and an early warning message is issued for the high-risk identification state, prompting the staff that the ultrasonic analysis device makes an error when analyzing the material of the clothing;

[0051] If the average value of the acoustic wave transmission coefficient is less than the preset reference threshold value of the average value of the acoustic wave transmission coefficient and the standard deviation of the acoustic wave transmission coefficient is greater than or equal to the preset reference threshold value of the standard deviation of the acoustic wave transmission coefficient, the abnormal identification process generated when the ultrasonic analysis device analyzes the material of the clothing is further divided into a medium-risk identification state, and a warning signal is also issued for the medium-risk identification state, reminding relevant staff that the ultrasonic analysis device is in an unstable state when analyzing the material of the clothing;

[0052] If the average value of the sound wave transmission coefficient is less than a preset reference threshold value of the average value of the sound wave transmission coefficient and the standard deviation of the sound wave transmission coefficient is less than a preset standard deviation of the sound wave transmission coefficient, the abnormal identification process generated by the ultrasonic analysis equipment when analyzing the material of clothing is further divided into a low-risk identification state, indicating that the interference received by the ultrasonic analysis equipment when analyzing the material of clothing is within a controllable range, and no warning signal is issued for the low-risk identification state.

[0053] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0054] By introducing an intelligent evaluation system based on machine learning, the present invention enables ultrasonic analysis equipment to more accurately identify clothing materials, especially when interfered by foreign objects. By real-time acquisition of information on acoustic impedance characteristics and signal scattering characteristics, and combining the acoustic impedance matching anomaly index and scattering deviation fluctuation index, the equipment can intelligently evaluate anomalies encountered during ultrasonic propagation. This evaluation can not only detect the abnormal recognition state of the equipment, but also conduct in-depth risk classification of material analysis based on different scattering and impedance characteristics. This intelligent feedback mechanism greatly improves the accuracy of ultrasonic analysis equipment and avoids the selection of inappropriate care procedures due to material identification errors. For example, by distinguishing between silk and synthetic fibers, the equipment can accurately control the ironing temperature and drying time to avoid damage to delicate fabrics caused by high temperature. This effectively prevents the impact of incorrect care on the appearance and life of clothing, and reduces customer complaints and service problems caused by clothing damage in hotels.

[0055] The present invention continuously monitors the operation process of the ultrasonic analysis equipment. When an abnormal recognition state is detected, the risk level can be further judged based on the fluctuation of the acoustic wave transmission coefficient, and different early warning signals can be issued. For high-risk recognition states, the system will promptly prompt the equipment that there is a major recognition error, reminding the staff to intervene and maintain immediately; for medium-risk recognition states, the equipment will issue an early warning that the equipment state is unstable, reminding the staff that the equipment may be in a fluctuating state, and make appropriate inspections and adjustments. For low-risk states, the system will not issue an early warning to reduce unnecessary interference. This intelligent early warning mechanism helps to discover potential problems of the equipment in advance and avoid high-cost maintenance and customer complaints caused by equipment misjudgment. It not only improves the operating efficiency of the equipment, but also reduces the maintenance cost of the equipment, so that the service life of the equipment can be extended. Through dynamic monitoring and risk grading, hotels can achieve efficient management of smart clothing care machines to ensure the stability of service quality and customer experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0057] Figure 1 The present invention is a method flow chart of a hotel intelligent clothing care machine based on the Internet of Things. DETAILED DESCRIPTION

[0058] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of the present disclosure will be more comprehensive and complete, and the concept of the example embodiments will be fully conveyed to those skilled in the art.

[0059] The present invention provides Figure 1 The hotel intelligent clothing care machine based on the Internet of Things shown includes the following steps:

[0060] During the operation of the ultrasonic analysis device, various parameter information generated by the ultrasonic analysis device when analyzing the clothing material is collected in real time, including acoustic impedance characteristic information and signal scattering characteristic information;

[0061] Acoustic impedance characteristic information includes ultrasonic propagation impedance, and signal scattering characteristic information includes ultrasonic signal scattering. Ultrasonic propagation impedance refers to the resistance encountered by ultrasonic waves when propagating in different media, which is specifically determined by the density and sound speed of the medium. Ultrasonic signal scattering refers to the deviation or dispersion of the propagation direction and intensity of the sound wave when the ultrasonic wave encounters inhomogeneities in the material during propagation.

[0062] Perform an abnormal analysis on the collected acoustic impedance characteristic information and signal scattering characteristic information, and input the acoustic impedance characteristic information and signal scattering characteristic information after abnormal analysis into a pre-learned machine learning model, generate an acoustic wave transmission coefficient through the machine learning model, and intelligently evaluate the process of ultrasonic analysis equipment analyzing clothing materials through the acoustic wave transmission coefficient;

[0063] After abnormal analysis of ultrasonic propagation impedance, an acoustic impedance matching abnormality index is generated. After abnormal analysis of ultrasonic signal scattering, a scattering deviation fluctuation index is generated. The impedance matching abnormality index and scattering deviation fluctuation index after abnormal analysis are input into a pre-learned machine learning model. The acoustic wave transmission coefficient is generated through the machine learning model. The process of ultrasonic analysis equipment analyzing clothing materials is intelligently evaluated through the acoustic wave transmission coefficient.

[0064] When the ultrasonic analysis device is analyzing the material of clothing, if the ultrasonic propagation impedance is abnormal, the device will not be able to accurately identify the material of the clothing, which may cause the intelligent clothing care machine to incorrectly select the care mode. Ultrasonic propagation impedance is the resistance encountered by ultrasonic waves when propagating in different materials, which is determined by the density and sound speed of the material. When ultrasonic waves enter clothing, the impedance difference determines the reflection, absorption and transmission characteristics of ultrasonic waves. If there are foreign substances on the surface of the clothing (such as stains or detergent residues), or the clothing material is complex (such as multi-layer structure or blended materials), it will cause abnormal changes in ultrasonic propagation impedance. This impedance abnormality will interfere with the propagation path of ultrasonic waves and affect its reflection signal in the clothing. The device may receive distorted echo signals and then incorrectly judge the fiber structure and thickness of the clothing. Since the ultrasonic analysis device relies on this information to select the appropriate care program, impedance abnormality will cause the device to misjudge the material. For example, sensitive silk may be mistaken for high-temperature resistant synthetic fibers, thereby selecting inappropriate high-temperature ironing or strong drying modes. This incorrect care mode may cause irreversible damage to the clothing, causing it to lose its original texture or luster, and in severe cases, even cause the clothing to deform, become brittle or shrink. Therefore, the abnormality of ultrasonic propagation impedance will directly affect the care decision of the intelligent clothing care machine, resulting in clothing care errors.

[0065] The logic of abnormal analysis of ultrasonic propagation impedance and generation of acoustic impedance matching abnormality index is as follows:

[0066] Under the detection window, the propagation impedance data of the clothing material is obtained from multiple detection points. The specific parameters include the acoustic impedance Z1 of the ultrasonic emission source, the acoustic impedance Z2(x,y) of the clothing material at different positions, the emission intensity I1 of the initial ultrasonic wave, and the intensity I2(x,y) of the ultrasonic wave reflected from the clothing surface. The position of the clothing material at different positions in the acoustic impedance Z2(x,y) is represented by two-dimensional coordinates x and y.

[0067] Based on the acquired acoustic impedance Z1 of the ultrasonic emission source and the acoustic impedance Z2(x,y) of the clothing material at different positions, the reflection coefficient of each detection point is calculated to comprehensively judge the impedance matching abnormality. The calculation expression is as follows:

[0068]

[0069] , where R(x,y) is the reflection coefficient, which represents the reflection coefficient of each detection point;

[0070] It should be noted that the reflection coefficient refers to the proportion of waves (such as sound waves or light waves) reflected at the interface between two media when the wave enters from one medium into another. It reflects how much energy is returned to the original medium during the transmission of the wave, and how much energy passes through the interface into the other medium. The size of the reflection coefficient depends on the difference in physical properties between the two media, especially their density and wave speed. If the properties of the two media are very different, the reflection coefficient will be higher, which means that most of the waves are reflected back and fewer waves enter the second medium. On the contrary, if the properties of the two media are similar, the reflection coefficient is smaller, and more waves will pass through the interface into the other medium. The reflection coefficient is very important in the fields of ultrasonic testing, acoustics and optics. It helps analyze the propagation and reflection behavior of waves in different media, especially in material testing and analysis, and is used to evaluate the interaction effects of different materials.

[0071] In order to make the detection of anomalies more accurate, a nonlinear fluctuation model is introduced to evaluate the impedance volatility within the detection window. The impedance fluctuation index is defined by the nonlinear fluctuation model. The calculation expression is as follows:

[0072]

[0073] , where W(x,y) is the impedance fluctuation index, is the gradient of impedance change with position, indicating the rate of change of impedance in different areas;

[0074] This model combines the gradient of impedance change with nonlinear reflection coefficient adjustment, making it easier to capture sudden fluctuations caused by impedance matching anomalies within the detection window.

[0075] The nonlinear wave model is a mathematical model used to describe and analyze the nonlinear relationship between the behavior of waves (such as sound waves or electromagnetic waves) and the properties of the medium when the wave propagates in a complex medium. Unlike the linear wave model, the nonlinear wave model takes into account the nonlinear changes in the propagation speed, amplitude or frequency of the wave with the intensity of the wave itself or the change of the medium. This model is widely used in wave analysis in complex environments, such as the propagation of ultrasound in inhomogeneous or nonlinear materials, because the behavior of waves in these materials often cannot be described by simple linear relationships.

[0076] The specific role of the nonlinear wave model is to more accurately simulate and analyze the scattering, reflection, attenuation and other phenomena of waves in complex media. It can capture the highly complex behavior of waves under different conditions (such as density changes, impedance differences, multi-layer structures of materials, etc.), and can effectively handle the nonlinear effects generated when waves interact with media. In ultrasonic analysis equipment, the nonlinear wave model can improve the accuracy of wave propagation in different materials or structures, thereby helping the equipment to accurately identify and analyze materials in more complex environments.

[0077] Based on the impedance fluctuation index, the impedance fluctuation index of the entire detection window is accumulated and calculated to generate a spatial weighted cumulative function. The calculation expression is as follows:

[0078]

[0079] , where S W is the cumulative fluctuation function, and f(x,y) is the weight function of the position (x,y), which is used to adjust the contribution of different positions to the cumulative fluctuation;

[0080] The impedance fluctuation index W(x,y) is a local quantity calculated at each position (x,y), which reflects the propagation impedance and fluctuation of ultrasonic waves at different positions. However, each point in the detection window may show different impedance fluctuations due to different positions. In order to fully reflect the fluctuation conditions in the entire detection area, it is necessary to accumulate the fluctuation indexes of all positions, so that a total amount representing the degree of fluctuation in the entire area can be obtained. Therefore, the purpose of accumulating the impedance fluctuation index is to integrate local information into a global indicator, so as to better judge whether there are abnormal fluctuations or abnormal phenomena in the area.

[0081] The role of the weight function is to give certain locations greater importance or influence. Different locations may show different responses to the propagation and fluctuation of ultrasound due to their physical properties, material distribution, etc. The weight function is used to adjust the influence of these locations.

[0082] In order to quantify the degree of impedance matching anomaly, the accumulated fluctuation function S W Normalized with the normal fluctuation threshold of the system, and combined with the nonlinear adjustment term of the reflection coefficient, the final acoustic impedance matching anomaly index is generated. The calculation expression is as follows:

[0083]

[0084] , where Impedance Mi is the acoustic impedance matching anomaly index, S norm is the normal fluctuation reference value preset by the system, R avg is the weighted average of the reflection coefficients in the area, indicating the overall reflection intensity, R max is the theoretical maximum reflection coefficient, which is used to control the upper limit of the anomaly index. It is a nonlinear adjustment term, ensuring that the anomaly index is sensitive to changes in the reflection coefficient;

[0085] From the calculation expression of the acoustic impedance matching anomaly index, it can be seen that the larger the acoustic impedance matching anomaly index performance value generated after the abnormal analysis of the ultrasonic propagation impedance is, the greater the impedance fluctuation anomaly encountered by the ultrasonic wave in the detection process of the clothing material, which means that the device is subject to more interference and uncertainty when identifying the clothing material, resulting in a greater probability of not being able to accurately identify the material. On the contrary, if the acoustic impedance matching anomaly index performance value is smaller, it means that the impedance fluctuation is smaller, the ultrasonic wave propagates more smoothly in the material, the device can identify the clothing material more accurately, and the probability of identification errors is lower.

[0086] When the ultrasonic analysis device analyzes the material of clothing, if the ultrasonic signal scattering is abnormal, the device will not be able to accurately identify the material of the clothing, which may cause the smart clothing care machine to select the wrong care mode. Ultrasonic signal scattering is the waveform deviation or energy dispersion phenomenon that occurs when the ultrasonic wave encounters an uneven medium (such as clothing fibers, stains or foreign matter). If the scattering is too strong or irregular, the propagation path and reflected signal of the ultrasonic wave will be seriously disturbed, causing the signal received by the device to be distorted or distorted. Since the ultrasonic analysis device relies on reflected echoes to analyze the material properties of clothing, such as fiber structure, density and thickness, scattering anomalies will make these signals inaccurate, and it is difficult for the device to determine the true material type. Incorrect material identification will cause the smart clothing care machine to select an inappropriate care mode. For example, misjudging thin and temperature-sensitive silk as a high-temperature-resistant synthetic fiber may cause the clothing care machine to select an excessively high temperature for ironing or drying, directly damaging the clothing, causing it to deform, lose its luster or become brittle. This error will not only affect the appearance and service life of the clothing, but also reduce the service quality of the hotel's smart clothing care machine, thereby affecting the customer experience.

[0087] The logic of abnormal analysis of ultrasonic signal scattering and generating scattering deviation fluctuation index is as follows:

[0088] In the detection window, the waveform data of the reflected signal is collected in real time. In order to reduce noise interference, the signal is first denoised, and the amplitude information in the waveform is used to calculate the strength of the reflected signal. The strength of the reflection is judged according to the signal strength fluctuation at each moment. The calculation expression is as follows:

[0089] I(t)=|S filtered (t)| 2

[0090] , where I(t) is the intensity of the reflected signal, i.e., the intensity of the reflected signal at time t, S filtered (t) represents the reflection signal after preprocessing;

[0091] In order to capture the nonlinear changes in the ultrasonic reflection process, the nonlinear dynamic analysis method is used to calculate the complexity and change rate of the reflected signal fluctuations. The calculation expression is as follows:

[0092]

[0093] , where λ(t) is the local Lyapunov index, which indicates the nonlinear characteristics of the reflected signal, Δt is the interval between two time points, and S filtered (t+Δt) is the preprocessed reflection signal at time t+Δt;

[0094] It should be noted that the local Lyapunov exponent is a commonly used method in nonlinear dynamics analysis. It is mainly used to measure the sensitivity of the trajectory to the initial conditions in a dynamic system, especially in a chaotic system, where the local Lyapunov exponent is used to describe the nonlinear behavior of the system in a short period of time. Its core function is to reveal the rate of change of the signal near different time points, indicating how the system responds to small disturbances.

[0095] In ultrasonic analysis equipment, local Lyapunov exponents can be used to analyze the dynamic characteristics of ultrasonic signals, especially when the signal scattering is abnormal, to capture local nonlinear changes, help evaluate the stability of the system and predict future evolution trends. Therefore, local Lyapuov exponents are widely used in nonlinear dynamic analysis as a key indicator for evaluating system stability and complexity.

[0096] In addition to the nonlinear characteristics of the reflected signal, phase change is also an important indicator of reflection anomaly. The deviation of the reflected signal is characterized by calculating the change of the signal phase at different time points. The calculation expression is as follows:

[0097]

[0098] , where is the phase difference, which indicates the phase change of the reflected signal at time t, Re{S filtered (t)} represents the real part of the preprocessed ultrasonic reflection signal at time t, m{S filtered (t)} represents the imaginary part of the preprocessed ultrasonic reflection signal at time t;

[0099] It should be noted that phase difference refers to the change in the phase angle of the signal (i.e. the angle of the signal waveform on the complex plane) between different time points. The phase angle describes the current position of the signal waveform, and the phase difference reflects the degree of phase change of the signal from one time point to another.

[0100] In ultrasonic analysis, the phase difference It represents the difference between the signal phase at time t and the phase at the previous time point t-1. This difference is used to characterize the changes of ultrasonic signals at different time points. In particular, when the signal passes through an inhomogeneous medium (such as foreign matter or stains on clothing), the phase change will be more obvious, indicating that the ultrasonic signal is interfered or scattered.

[0101] If the phase difference is small, it means that the signal fluctuation is relatively stable and the scattering is weak; if the phase difference is large, it means that the signal has experienced strong scattering or interference during the propagation process. Therefore, the phase difference is an important indicator for analyzing whether scattering and abnormal changes occur when the ultrasonic signal propagates in an inhomogeneous medium.

[0102] Combining the intensity I(t) of the reflected signal, the local Lyapunov exponent λ(t) and the phase difference Generate the scattering deviation fluctuation index, the calculation expression is as follows:

[0103]

[0104] , where Scattering DF is the scattering deviation fluctuation index, α1 is the weight coefficient of the intensity I(t) of the reflected signal, α2 is the weight coefficient of the local Lyapunov index λ(t), and α3 is the phase difference The weight coefficient, β is the nonlinear coefficient used to adjust the impact of phase change, t0 and t1 are the starting and ending points of the time interval;

[0105] The nonlinear coefficient is a parameter used to quantify the degree of nonlinearity in a system. It describes whether the response of the system output to the input is linear or nonlinear. In a complex system, the nonlinear coefficient can reflect the strength or complexity of the interaction in the system. The role of the nonlinear coefficient is to adjust the effect of phase change on the scattering fluctuation index. Since the propagation of ultrasonic signals in inhomogeneous media often exhibits nonlinear behavior, the nonlinear coefficient helps capture the nonlinear characteristics of the signal phase change, so that the calculation results can more accurately reflect the complex fluctuations of the signal, thereby better evaluating the degree of scattering anomalies.

[0106] From the calculation expression of the scattering deviation fluctuation index, it can be seen that the larger the scattering deviation fluctuation index performance value generated after the abnormal analysis of the ultrasonic signal scattering, the stronger the scattering anomaly of the ultrasonic signal during the clothing material detection process, indicating that the ultrasonic analysis equipment has been subjected to greater interference when identifying the clothing material. This interference increases the probability that the equipment cannot accurately identify the clothing material, because the greater the scattering fluctuation of the signal, the more difficult it is for the equipment to interpret the reflection characteristics of the signal, resulting in an increased possibility of misjudgment. Conversely, if the scattering deviation fluctuation index performance value is smaller, it means that the signal scattering is weaker and the fluctuation is more stable, the equipment's identification of the material is more reliable, and the probability of abnormality is lower.

[0107] Impedance matching anomaly index Mi Scattering DF Input into the pre-learned machine learning model, and generate the acoustic wave transmission coefficient Acoustic through the machine learning model WP , based on the formula:

[0108]

[0109] , where f1 and f2 are the acoustic impedance matching anomaly index Impedance Mi Scattering DF The preset proportional coefficient, and f1 and f2 are both greater than 0.

[0110] It can be seen from the calculation expression of the acoustic wave transfer coefficient that the larger the acoustic impedance matching anomaly index value generated after the abnormal analysis of the ultrasonic propagation impedance, and the larger the scattering deviation fluctuation index value generated after the abnormal analysis of the ultrasonic signal scattering, the larger the acoustic wave transfer coefficient value, indicating that the probability of abnormality in the process of clothing material analysis by the ultrasonic analysis equipment is greater. Conversely, it means that the process of clothing material analysis by the ultrasonic analysis equipment is in normal working state, and the probability of abnormality is smaller.

[0111] Based on the machine learning evaluation results, the clothing material analysis process of the ultrasonic analysis equipment is divided into a normal recognition process or an abnormal recognition process, and the abnormal clothing material recognition process is intelligently perceived;

[0112] The sound wave transmission coefficient generated by the machine learning model is compared and analyzed with the preset reference threshold of the sound wave transmission coefficient, and the process of clothing material analysis by the ultrasonic analysis equipment is divided as follows:

[0113] If the sound wave transmission coefficient is greater than or equal to a preset sound wave transmission reference threshold, the process of analyzing the clothing material by the ultrasonic analysis device is classified as an abnormality recognition process;

[0114] If the sound wave transmission coefficient is less than the preset sound wave transmission reference threshold, the process of the ultrasonic analysis device analyzing the clothing material is classified as a normal recognition process;

[0115] When the ultrasonic analysis device analyzes the material of clothing, an abnormal identification process is generated, the analysis information of the clothing material by the ultrasonic analysis device is continuously obtained, and the process of the ultrasonic analysis device analyzing the clothing material is comprehensively judged;

[0116] When the process of analyzing the clothing material by the ultrasonic analysis device is divided into the abnormality identification process, a plurality of acoustic wave transmission coefficients subsequently generated by the ultrasonic analysis device when analyzing the clothing material are continuously obtained to establish a data set for comprehensive analysis, and the abnormality identification process is further divided;

[0117] The average values ​​and standard deviations of several acoustic wave transmission coefficients in the data set are calculated, and the calculated average values ​​and standard deviations of the acoustic wave transmission coefficients are compared with the preset reference threshold values ​​of the average values ​​and standard deviations of the acoustic wave transmission coefficients, respectively. The comparison results are as follows:

[0118] If the average value of the acoustic wave transmission coefficient is greater than or equal to a preset reference threshold value of the average value of the acoustic wave transmission coefficient, the abnormal identification process generated when the ultrasonic analysis device analyzes the material of the clothing is further divided into a high-risk identification state, and an early warning message is issued for the high-risk identification state, prompting the staff that the ultrasonic analysis device makes an error when analyzing the material of the clothing;

[0119] It should be noted that when the ultrasonic analysis equipment is in a high-risk identification state, the equipment should be stopped immediately and staff should be arranged to conduct a detailed inspection of the equipment, while focusing on checking for foreign matter residues on the clothes (such as stains, detergents, etc.), and restarting the system after removing the interference source.

[0120] If the average value of the acoustic wave transmission coefficient is less than the preset reference threshold value of the average value of the acoustic wave transmission coefficient and the standard deviation of the acoustic wave transmission coefficient is greater than or equal to the preset reference threshold value of the standard deviation of the acoustic wave transmission coefficient, the abnormal identification process generated when the ultrasonic analysis device analyzes the material of the clothing is further divided into a medium-risk identification state, and a warning signal is also issued for the medium-risk identification state, reminding relevant staff that the ultrasonic analysis device is in an unstable state when analyzing the material of the clothing;

[0121] It should be noted that in the medium-risk identification state, although the equipment is unstable, it has not completely failed, and system optimization and maintenance should be carried out. Staff can confirm the stability of the ultrasonic analysis equipment through remote or on-site inspections, especially to check whether there are intermittent interference sources (such as chemical residues on clothing). If necessary, some functions can be suspended, and the equipment parameter settings can be recalibrated or adjusted to improve the stability of identification.

[0122] If the average value of the acoustic wave transmission coefficient is less than the preset reference threshold value of the average value of the acoustic wave transmission coefficient and the standard deviation of the acoustic wave transmission coefficient is less than the preset standard deviation of the acoustic wave transmission coefficient, the abnormal identification process generated when the ultrasonic analysis device analyzes the material of the clothing is further divided into a low-risk identification state, indicating that the interference received by the ultrasonic analysis device when analyzing the material of the clothing is within a controllable range, and no warning signal is issued for the low-risk identification state;

[0123] It should be noted that for low-risk identification status, the interference is within a controllable range and the equipment does not need to stop working. At this time, routine monitoring and maintenance should be carried out to ensure the normal operation of the system, and the cleanliness of the equipment and clothing should be checked regularly to ensure that foreign matter does not accumulate, so as to reduce the possibility of high-risk or medium-risk status in the future.

[0124] By introducing an intelligent evaluation system based on machine learning, the present invention enables ultrasonic analysis equipment to more accurately identify clothing materials, especially when interfered by foreign objects. By real-time acquisition of information on acoustic impedance characteristics and signal scattering characteristics, and combining the acoustic impedance matching anomaly index and scattering deviation fluctuation index, the equipment can intelligently evaluate anomalies encountered during ultrasonic propagation. This evaluation can not only detect the abnormal recognition state of the equipment, but also conduct in-depth risk classification of material analysis based on different scattering and impedance characteristics. This intelligent feedback mechanism greatly improves the accuracy of ultrasonic analysis equipment and avoids the selection of inappropriate care procedures due to material identification errors. For example, by distinguishing between silk and synthetic fibers, the equipment can accurately control the ironing temperature and drying time to avoid damage to delicate fabrics caused by high temperature. This effectively prevents the impact of incorrect care on the appearance and life of clothing, and reduces customer complaints and service problems caused by clothing damage in hotels.

[0125] The present invention continuously monitors the operation process of the ultrasonic analysis equipment. When an abnormal recognition state is detected, the risk level can be further judged based on the fluctuation of the acoustic wave transmission coefficient, and different early warning signals can be issued. For high-risk recognition states, the system will promptly prompt the equipment that there is a major recognition error, reminding the staff to intervene and maintain immediately; for medium-risk recognition states, the equipment will issue an early warning that the equipment state is unstable, reminding the staff that the equipment may be in a fluctuating state, and make appropriate inspections and adjustments. For low-risk states, the system will not issue an early warning to reduce unnecessary interference. This intelligent early warning mechanism helps to discover potential problems of the equipment in advance and avoid high-cost maintenance and customer complaints caused by equipment misjudgment. It not only improves the operating efficiency of the equipment, but also reduces the maintenance cost of the equipment, so that the service life of the equipment can be extended. Through dynamic monitoring and risk grading, hotels can achieve efficient management of smart clothing care machines to ensure the stability of service quality and customer experience.

[0126] The above description is only by way of illustration of certain exemplary embodiments of the present invention. It is undoubted that those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

Claims

1. A hotel intelligent clothing care machine based on the Internet of Things, characterized in that: The following steps are involved: During the operation of the ultrasonic analysis device, various parameter information generated by the ultrasonic analysis device when analyzing the clothing material is collected in real time, including acoustic impedance characteristic information and signal scattering characteristic information; Perform an abnormal analysis on the collected acoustic impedance characteristic information and signal scattering characteristic information, and input the acoustic impedance characteristic information and signal scattering characteristic information after abnormal analysis into a pre-learned machine learning model, generate an acoustic wave transmission coefficient through the machine learning model, and intelligently evaluate the process of ultrasonic analysis equipment analyzing clothing materials through the acoustic wave transmission coefficient; Based on the machine learning evaluation results, the clothing material analysis process of the ultrasonic analysis equipment is divided into a normal recognition process or an abnormal recognition process, and the abnormal clothing material recognition process is intelligently perceived; When the ultrasonic analysis device analyzes the material of clothing, an abnormal recognition process is generated, the analysis information of the clothing material by the ultrasonic analysis device is continuously obtained, and the process of the ultrasonic analysis device analyzing the material of clothing is comprehensively judged.

2. According to claim 1, the hotel intelligent clothing care machine based on the Internet of Things is characterized by: Acoustic impedance characteristic information includes ultrasonic propagation impedance, and signal scattering characteristic information includes ultrasonic signal scattering. Ultrasonic propagation impedance refers to the resistance encountered by ultrasonic waves when propagating in different media, which is specifically determined by the density and sound speed of the medium. Ultrasonic signal scattering refers to the deviation or dispersion of the propagation direction and intensity of the sound wave when the ultrasonic wave encounters inhomogeneities in the material during propagation.

3. The hotel intelligent clothing care machine based on the Internet of Things according to claim 2 is characterized in that: After performing an abnormal analysis on the ultrasonic propagation impedance, an acoustic impedance matching anomaly index is generated. After performing an abnormal analysis on the ultrasonic signal scattering, a scattering deviation fluctuation index is generated. The impedance matching anomaly index and the scattering deviation fluctuation index after the abnormal analysis are input into a pre-learned machine learning model, and an acoustic wave transfer coefficient is generated through the machine learning model. The acoustic wave transfer coefficient is used to intelligently evaluate the process of ultrasonic analysis equipment analyzing clothing materials.

4. The hotel intelligent clothing care machine based on the Internet of Things according to claim 3 is characterized in that: The logic of abnormal analysis of ultrasonic propagation impedance and generation of acoustic impedance matching abnormality index is as follows: Under the detection window, the propagation impedance data of the clothing material is obtained from multiple detection points. The specific parameters include the acoustic impedance Z1 of the ultrasonic emission source, the acoustic impedance Z2(x,y) of the clothing material at different positions, the emission intensity I1 of the initial ultrasonic wave, and the intensity I2(x,y) of the ultrasonic wave reflected from the clothing surface. The position of the clothing material at different positions in the acoustic impedance Z2(x,y) is represented by two-dimensional coordinates x and y. Based on the acquired acoustic impedance Z1 of the ultrasonic emission source and the acoustic impedance Z2(x,y) of the clothing material at different positions, the reflection coefficient of each detection point is calculated to comprehensively judge the impedance matching abnormality. The calculation expression is as follows: ， Where, R(x,y) is the reflection coefficient, which represents the reflection coefficient of each detection point; In order to make the detection of anomalies more accurate, a nonlinear fluctuation model is introduced to evaluate the impedance volatility within the detection window. The impedance fluctuation index is defined by the nonlinear fluctuation model. The calculation expression is as follows: ， Where W(x,y) is the impedance fluctuation index, is the gradient of impedance change with position, indicating the rate of change of impedance in different areas; Based on the impedance fluctuation index, the impedance fluctuation index of the entire detection window is accumulated and calculated to generate a spatial weighted cumulative function. The calculation expression is as follows: ， In the formula, S W is the cumulative fluctuation function, and f(x,y) is the weight function of the position (x,y), which is used to adjust the contribution of different positions to the cumulative fluctuation; In order to quantify the degree of impedance matching anomaly, the accumulated fluctuation function S W Normalized with the normal fluctuation threshold of the system, and combined with the nonlinear adjustment term of the reflection coefficient, the final acoustic impedance matching anomaly index is generated. The calculation expression is as follows: ， In the formula, Impedance Mi is the acoustic impedance matching anomaly index, S norm is the normal fluctuation reference value preset by the system, R avg is the weighted average of the reflection coefficient in the area, R max is the theoretical maximum reflection coefficient, It is a nonlinear adjustment term.

5. The hotel intelligent clothing care machine based on the Internet of Things according to claim 3 is characterized in that: The logic of abnormal analysis of ultrasonic signal scattering and generating scattering deviation fluctuation index is as follows: In the detection window, the waveform data of the reflected signal is collected in real time. In order to reduce noise interference, the signal is first denoised, and the amplitude information in the waveform is used to calculate the strength of the reflected signal. The strength of the reflection is judged according to the signal strength fluctuation at each moment. The calculation expression is as follows: I(t)=|S filtered (t)| 2 , Where I(t) is the intensity of the reflected signal, that is, the intensity of the reflected signal at time t, S filtered (t) represents the reflection signal after preprocessing; In order to capture the nonlinear changes in the ultrasonic reflection process, the nonlinear dynamic analysis method is used to calculate the complexity and change rate of the reflected signal fluctuations. The calculation expression is as follows: ， Where λ(t) is the local Lyapunov index, which indicates the nonlinear characteristics of the reflected signal, Δt is the interval between two time points, and S filterd (t+Δt) is the preprocessed reflection signal at time t+Δt; In addition to the nonlinear characteristics of the reflected signal, phase change is also an important indicator of reflection anomaly. The deviation of the reflected signal is characterized by calculating the change of the signal phase at different time points. The calculation expression is as follows: ， In the formula, is the phase difference, which indicates the phase change of the reflected signal at time t, Re{S filtered (t)} represents the real part of the preprocessed ultrasonic reflection signal at time t, m{S filtered (t)} represents the imaginary part of the preprocessed ultrasonic reflection signal at time t; Combining the intensity I(t) of the reflected signal, the local Lyapunov exponent λ(t) and the phase difference Generate the scattering deviation fluctuation index, the calculation expression is as follows: ， In the formula, Scattering DF is the scattering deviation fluctuation index, α1 is the weight coefficient of the intensity I(t) of the reflected signal, α2 is the weight coefficient of the local Lyapunov index λ(t), and α3 is the phase difference is the weight coefficient, β is the nonlinear coefficient, t0 and t1 are the starting and ending points of the time interval.

6. The hotel intelligent clothing care machine based on the Internet of Things according to claim 3 is characterized by: Impedance matching anomaly index Mi Scattering DF Input into the pre-learned machine learning model, and generate the acoustic wave transmission coefficient Acoustic through the machine learning model WP , based on the formula: ， Where f1 and f2 are the acoustic impedance matching anomaly index Impedance Mi Scattering DF The preset proportional coefficient, and f1 and f2 are both greater than 0.

7. The hotel intelligent clothing care machine based on the Internet of Things according to claim 6 is characterized by: The sound wave transmission coefficient generated by the machine learning model is compared and analyzed with the preset reference threshold of the sound wave transmission coefficient, and the process of clothing material analysis by the ultrasonic analysis equipment is divided as follows: If the sound wave transmission coefficient is greater than or equal to a preset sound wave transmission reference threshold, the process of analyzing the clothing material by the ultrasonic analysis device is classified as an abnormality recognition process; If the sound wave transmission coefficient is less than a preset sound wave transmission reference threshold, the process of analyzing the clothing material by the ultrasonic analysis equipment is classified as a normal recognition process.

8. The hotel intelligent clothing care machine based on the Internet of Things according to claim 7 is characterized in that: When the process of analyzing the clothing material by the ultrasonic analysis device is divided into the abnormality identification process, a plurality of acoustic wave transmission coefficients subsequently generated by the ultrasonic analysis device when analyzing the clothing material are continuously obtained to establish a data set for comprehensive analysis, and the abnormality identification process is further divided; The average values ​​and standard deviations of several acoustic wave transmission coefficients in the data set are calculated, and the calculated average values ​​and standard deviations of the acoustic wave transmission coefficients are compared with the preset reference threshold values ​​of the average values ​​and standard deviations of the acoustic wave transmission coefficients, respectively. The comparison results are as follows: If the average value of the acoustic wave transmission coefficient is greater than or equal to a preset reference threshold value of the average value of the acoustic wave transmission coefficient, the abnormal identification process generated when the ultrasonic analysis device analyzes the material of the clothing is further divided into a high-risk identification state, and an early warning message is issued for the high-risk identification state, prompting the staff that the ultrasonic analysis device makes an error when analyzing the material of the clothing; If the average value of the acoustic wave transmission coefficient is less than the preset reference threshold value of the average value of the acoustic wave transmission coefficient and the standard deviation of the acoustic wave transmission coefficient is greater than or equal to the preset reference threshold value of the standard deviation of the acoustic wave transmission coefficient, the abnormal identification process generated when the ultrasonic analysis device analyzes the material of the clothing is further divided into a medium-risk identification state, and a warning signal is also issued for the medium-risk identification state, reminding relevant staff that the ultrasonic analysis device is in an unstable state when analyzing the material of the clothing; If the average value of the sound wave transmission coefficient is less than a preset reference threshold value of the average value of the sound wave transmission coefficient and the standard deviation of the sound wave transmission coefficient is less than a preset reference threshold value of the standard deviation of the sound wave transmission coefficient, the abnormal identification process generated by the ultrasonic analysis equipment when analyzing the material of clothing is further divided into a low-risk identification state, indicating that the interference received by the ultrasonic analysis equipment when analyzing the material of clothing is within a controllable range, and no warning signal is issued for the low-risk identification state.

Images