Disinfection distance dynamic adjustment method and device, equipment and storage medium

Abstract

The invention relates to the technical field of data processing, in particular to a disinfection distance dynamic adjustment method and device, equipment and a storage medium, and the method comprises the steps: obtaining object surface information and environment temperature and humidity information to set disinfection parameters; ultraviolet disinfection equipment is controlled to work, and object information, balance wheel position and light intensity are monitored in real time; the LSTM network is utilized to predict distance change, and a balance wheel preset displacement instruction is generated; adjusting the states of a balance wheel and an ultraviolet lamp panel by using a PID algorithm in combination with monitoring information and a preset displacement instruction; after disinfection is completed, a disinfection record is stored in a database; according to the method disclosed by the invention, the distance change of the object is predicted through the LSTM network, and the positioning precision of the balance wheel mechanism is optimized; a PID algorithm and real-time light intensity information are combined, so that the working state of the ultraviolet disinfection equipment is accurately controlled, and the disinfection efficiency and effect are improved; and finally, disinfection records are stored in a database, so that tracking and management are facilitated, and the intelligence and reliability of the disinfection process are integrally improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method, device, equipment and storage medium for dynamically adjusting a disinfection distance. Background Art

[0002] During transportation and storage, cold chain items such as food, medicines and biological samples are susceptible to microbial contamination, so disinfection is a key link to ensure their safety; currently, cold chain disinfection mainly relies on chemical disinfectants and ultraviolet (UVC) technology, and ultraviolet disinfection has gradually become the mainstream due to its high efficiency, no residue and environmental protection characteristics.

[0003] UV disinfection equipment currently on the market generally faces a series of technical challenges and functional limitations, which limit their effectiveness and efficiency in different application scenarios:

[0004] First of all, insufficient intelligence is a major flaw of existing UV disinfection equipment. Current UV disinfection equipment often lacks adaptive capabilities and cannot automatically optimize disinfection parameters such as radiation intensity, irradiation time, and irradiation distance according to the specific size, shape, and surface material of the disinfection object. This fixed-parameter disinfection method often leads to inconsistent disinfection effects, which can easily lead to the disinfection process either taking too long or failing to guarantee the disinfection effect, thereby affecting the overall disinfection efficiency.

[0005] Secondly, the existing ultraviolet disinfection equipment has obvious deficiencies in disinfection coverage. Since most ultraviolet disinfection equipment adopts a fixed design, it is difficult for them to comprehensively disinfect items with complex shapes or irregular surfaces, which easily causes the appearance of shadow areas. These areas become disinfection blind spots because they cannot receive sufficient ultraviolet radiation, thus affecting the thoroughness of disinfection.

[0006] Finally, the lack of real-time monitoring and data analysis of the disinfection process is another major shortcoming of existing UV disinfection equipment. Due to the lack of real-time monitoring and feedback mechanism, it is difficult to ensure the quality of the disinfection process and the consistency of the disinfection results. This not only affects the reliability of the disinfection effect, but also makes it difficult for UV disinfection equipment to meet increasingly stringent hygiene and safety standards.

[0007] It can be seen that the existing technology still needs to be improved and enhanced. Summary of the invention

[0008] In order to overcome the shortcomings of the prior art, the purpose of the present invention is to provide a method for dynamically adjusting the disinfection distance, optimize the positioning accuracy of the balance wheel mechanism through the LSTM network, and combine the PID algorithm and light intensity information to accurately control the working state of the ultraviolet disinfection equipment, so as to improve the disinfection efficiency and disinfection effect.

[0009] The first aspect of the present invention provides a method for dynamically adjusting the disinfection distance, comprising: obtaining surface information of an object to be disinfected and real-time temperature and humidity information fed back by a temperature and humidity sensor to confirm disinfection parameters; controlling an ultraviolet disinfection device to start working based on the confirmed disinfection parameters, and obtaining real-time object information fed back by an optical sensor, real-time position information fed back by a balance wheel encoder included in a balance wheel mechanism, and real-time light intensity information fed back by a light intensity sensor included in an ultraviolet lamp board; based on the object information fed back by the optical sensor, using an LSTM network to predict distance change information to generate a predetermined displacement instruction for the balance wheel; combining the real-time object information, the real-time position information and the predetermined displacement instruction for the balance wheel, using a PID algorithm to adjust the working state of the balance wheel mechanism, and adjusting the working state of the ultraviolet lamp board based on the real-time light intensity information; when the ultraviolet disinfection device completes the disinfection task, the disinfection record corresponding to the disinfection task is stored in a database.

[0010] Optionally, in a first implementation method of the first aspect of the present invention, the obtaining of surface information of the object to be disinfected and real-time temperature and humidity information fed back by a temperature and humidity sensor to confirm the disinfection parameters includes: obtaining surface information of the object to be disinfected and real-time temperature and humidity information fed back by a temperature and humidity sensor, the surface information of the object to be disinfected including the material type, surface roughness and color reflectivity of the object to be disinfected, and the real-time temperature and humidity information including real-time temperature and real-time humidity; performing unique-hot encoding on the material type of the object to be disinfected, normalizing the surface roughness of the object to be disinfected, and describing the color reflectivity in percentage form to achieve preprocessing of the surface information of the object to be disinfected; performing temperature compensation on the real-time temperature, and performing humidity correction on the real-time humidity to complete the calibration of the real-time temperature and humidity information; inputting the preprocessed surface information of the object to be disinfected and the calibrated real-time temperature and humidity information into a pre-trained random forest model to obtain disinfection parameters, the disinfection parameters including disinfection power, ultraviolet lamp panel combination scheme and disinfection time.

[0011] Optionally, in a second implementation method of the first aspect of the present invention, the ultraviolet disinfection equipment is controlled to start working based on the confirmed disinfection parameters, and real-time object information fed back by the optical sensor, real-time position information fed back by the balance wheel encoder included in the balance wheel mechanism, and real-time light intensity information fed back by the light intensity sensor included in the ultraviolet lamp board are obtained, including: controlling the ultraviolet disinfection equipment to start working based on the confirmed disinfection parameters; obtaining real-time object information fed back by the optical sensor, the real-time object information including the object movement direction, object movement speed and object movement acceleration; obtaining real-time position information fed back by the balance wheel encoder included in the balance wheel mechanism, the real-time position information including the real-time angle of the balance wheel and the real-time rotational position of the balance wheel; obtaining real-time light intensity information fed back by the light intensity sensor included in the ultraviolet lamp board, the real-time light intensity information including twelve real-time radiation intensity information corresponding to the ultraviolet disinfection module.

[0012] Optionally, in a third implementation of the first aspect of the present invention, the object information based on the optical sensor feedback uses an LSTM network to predict the distance change information to generate a predetermined displacement instruction for the balance wheel, including: a pre-trained LSTM network prediction model, the trained LSTM network prediction model includes an encoder, a decoder and a fully connected layer connected in sequence, the encoder includes three bidirectional LSTM layers, and the decoder includes two unidirectional LSTM layers; the object information fed back by the optical sensor is input into the pre-trained LSTM network prediction model to obtain a prediction result and its corresponding confidence; a preset confidence threshold corresponding to the color reflectance is obtained, and the confidence of the prediction result is compared with the obtained confidence threshold; if the confidence of the prediction result is ≥ the confidence threshold, a predetermined displacement instruction for the balance wheel is generated based on the prediction result; if the confidence of the prediction result is < the confidence threshold, a Kalman filtering algorithm is used to smooth the prediction result, and the smoothed prediction result is adjusted to obtain an adjusted result, and a predetermined displacement instruction for the balance wheel is generated based on the adjusted result.

[0013] Optionally, in a fourth implementation manner of the first aspect of the present invention, the balance mechanism also includes a laser radar electrically connected to the control device, and the laser radar is used to detect the surface distance between the object to be disinfected and the balance mechanism; generating a predetermined displacement instruction for the balance based on the prediction result includes: obtaining a preset optimal disinfection distance, and generating a target distance based on the prediction result and the optimal disinfection distance; obtaining a real-time surface distance fed back by the laser radar, and confirming the displacement direction and displacement amplitude of the balance mechanism based on the target distance and the real-time surface distance; obtaining a preset maximum linear moving speed of the balance mechanism, and confirming the linear moving speed of the balance mechanism based on the displacement amplitude of the balance mechanism and the obtained maximum linear moving speed; integrating the target distance and the displacement direction, displacement amplitude and linear moving speed of the balance mechanism to obtain a predetermined displacement instruction for the balance.

[0014] Optionally, in a fifth implementation method of the first aspect of the present invention, generating a predetermined displacement instruction for the balance wheel based on the prediction result includes: obtaining a preset optimal disinfection distance, and generating a target distance based on the prediction result and the optimal disinfection distance; obtaining a real-time surface distance fed back by a lidar, and confirming the displacement direction and displacement amplitude of the balance wheel mechanism based on the target distance and the real-time surface distance; obtaining a preset maximum linear moving speed of the balance wheel mechanism, and confirming the linear moving speed of the balance wheel mechanism based on the displacement amplitude of the balance wheel mechanism and the obtained maximum linear moving speed; integrating the target distance and the displacement direction, displacement amplitude and linear moving speed of the balance wheel mechanism to obtain a predetermined displacement instruction for the balance wheel.

[0015] Optionally, in a sixth implementation method of the first aspect of the present invention, when the ultraviolet disinfection equipment completes the disinfection task, the disinfection record corresponding to the disinfection task is stored in a database, and then includes: when a preset attenuation prediction time is reached, obtaining the historical disinfection records stored in the database; inputting the historical disinfection records into a pre-trained XGBoost model to obtain the lamp board attenuation prediction result of the XGBoost model; obtaining a preset attenuation threshold, and if the lamp board attenuation prediction result is ≤ the preset attenuation threshold, generating a lamp board replacement warning instruction.

[0016] The second aspect of the present invention provides a dynamic adjustment device for disinfection distance, including: a confirmation module, which is used to obtain surface information of an object to be disinfected and real-time temperature and humidity information fed back by a temperature and humidity sensor to confirm disinfection parameters; an acquisition module, which is used to control the ultraviolet disinfection equipment to start working based on the confirmed disinfection parameters, and obtain real-time object information fed back by an optical sensor, real-time position information fed back by a balance wheel encoder included in a balance wheel mechanism, and real-time light intensity information fed back by a light intensity sensor included in an ultraviolet lamp board; a generation module, which is used to predict distance change information based on the object information fed back by the optical sensor, using an LSTM network to generate a predetermined displacement instruction for the balance wheel; an adjustment module, which is used to combine real-time object information, real-time position information and predetermined displacement instructions for the balance wheel, use a PID algorithm to adjust the working state of the balance wheel mechanism, and adjust the working state of the ultraviolet lamp board based on the real-time light intensity information; a recording module, which is used to store the disinfection record corresponding to the disinfection task in a database when the ultraviolet disinfection equipment completes the disinfection task.

[0017] The third aspect of the present invention provides a dynamic adjustment device for the disinfection distance, which includes: a memory and at least one processor, wherein instructions are stored in the memory; at least one of the processors calls the instructions in the memory so that the dynamic adjustment device for the disinfection distance performs each step of the dynamic adjustment method for the disinfection distance described in any one of the above items.

[0018] The fourth aspect of the present invention provides a computer-readable storage medium, on which instructions are stored. When the instructions are executed by a processor, the various steps of any of the above-mentioned methods for dynamically adjusting the disinfection distance are implemented.

[0019] In the technical solution of the present invention, the distance change of the object is predicted by the LSTM network, thereby optimizing the positioning accuracy of the balance wheel mechanism; combining the PID algorithm and the real-time light intensity information, the precise control of the working state of the ultraviolet disinfection equipment is realized, thereby improving the disinfection efficiency and effect; finally, the disinfection records are stored in a database for easy tracking and management, thereby improving the intelligence and reliability of the disinfection process as a whole. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1A first flow chart of the method for dynamically adjusting the disinfection distance provided by an embodiment of the present invention;

[0021] Figure 2 A schematic diagram of the structure of a dynamic adjustment device for disinfection distance provided in an embodiment of the present invention;

[0022] Figure 3 A schematic diagram of the structure of a disinfection distance dynamic adjustment device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0023] The present invention provides a method, device, equipment and storage medium for dynamically adjusting the disinfection distance. In the present invention, the terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described herein can be implemented in a sequence other than the content illustrated or described herein. In addition, the terms "including" or "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0024] The disinfection distance adjustment method disclosed in the present application is used to realize the working control of ultraviolet disinfection equipment. The ultraviolet disinfection equipment includes a control device and an optical sensor, a balance wheel mechanism, an ultraviolet lamp board and a temperature and humidity sensor electrically connected to the control device respectively. The optical sensor is used to obtain surface information of the object to be disinfected, and the temperature and humidity sensor is used to obtain ambient temperature and humidity information; the balance wheel mechanism is transmission-connected to the ultraviolet lamp board to realize the angle adjustment of the ultraviolet lamp board; in this embodiment, the control device includes multiple control chips, and the model of the control chip can be STM32.

[0025] Furthermore, the balance wheel mechanism is an existing dual-axis mechanical balance wheel structure, with a swing range of ±45° on the X / Y axis, and is driven by a high-precision stepper motor with a resolution of up to 0.1°, ensuring the accuracy and stability of the balance wheel movement; at the same time, the balance wheel mechanism is integrated with an adaptive spring damping system, which can effectively buffer and absorb the vibration generated by the balance wheel during movement, further improving the performance and reliability of the mechanism.

[0026] Furthermore, the balance wheel mechanism also includes a laser radar electrically connected to the control device, and the laser radar is used to detect the surface distance between the object to be sterilized and the balance wheel mechanism.

[0027] Furthermore, the ultraviolet lamp board includes an annular frame, and six first ultraviolet disinfection modules with a wavelength of 265nm are arranged on the upper side of the annular frame, and the first ultraviolet disinfection modules are evenly distributed at intervals of 30° and each first ultraviolet disinfection module is tilted downward by 30°; six second ultraviolet disinfection modules with a wavelength of 280nm are arranged on the lower side of the annular frame, and the second ultraviolet disinfection modules are evenly distributed at intervals of 30° and each second ultraviolet disinfection module is tilted upward by 45°; each first disinfection module and each second disinfection module are correspondingly provided with a light intensity sensor; the annular frame is transmission-connected to the balance wheel mechanism, and 0-360° dead-angle irradiation is achieved through the movement of the balance wheel.

[0028] For ease of understanding, the specific process of the embodiment of the present invention is described below. Figure 1 , an embodiment of the method for dynamically adjusting the disinfection distance in an embodiment of the present invention includes:

[0029] 101. Obtain surface information of the object to be disinfected and real-time temperature and humidity information fed back by the temperature and humidity sensor to confirm disinfection parameters;

[0030] 102. Control the ultraviolet disinfection equipment to start working based on the confirmed disinfection parameters, and obtain real-time object information fed back by the optical sensor, real-time position information fed back by the balance wheel encoder included in the balance wheel mechanism, and real-time light intensity information fed back by the light intensity sensor included in the ultraviolet lamp board;

[0031] In this embodiment, an optical sensor is used to capture the dynamic changes of objects during the disinfection process in real time. At the same time, the real-time position information fed back by the balance wheel encoder built into the balance wheel mechanism and the real-time light intensity data provided by the light intensity sensor equipped on the UV lamp board are combined to form a multi-dimensional information feedback system.

[0032] 103. Based on the object information fed back by the optical sensor, the LSTM network is used to predict the distance change information to generate a predetermined displacement instruction of the balance wheel;

[0033] In this embodiment, a long short-term memory network (LSTM) is used to perform in-depth analysis on the object information fed back by the optical sensor, predict the changing trend of the object distance, and generate accurate balance wheel predetermined displacement instructions, which not only improves the response speed of the balance wheel mechanism, but also significantly improves the positioning accuracy.

[0034] 104. Combining the real-time object information, the real-time position information and the predetermined displacement instruction of the balance wheel, a PID algorithm is used to adjust the working state of the balance wheel mechanism, and the working state of the ultraviolet lamp panel is adjusted based on the real-time light intensity information;

[0035] In this embodiment, the PID algorithm is used to finely adjust the working state of the balance wheel mechanism in combination with real-time object information, real-time position information and predetermined displacement instructions of the balance wheel, ensuring that the UV lamp board always maintains the optimal disinfection position during the disinfection process, so that the distribution of ultraviolet light meets the disinfection requirements; at the same time, according to the real-time light intensity information of the light intensity sensor, the working state of the UV lamp board is dynamically adjusted to ensure that the intensity of ultraviolet rays meets the disinfection requirements, thereby maximizing the disinfection effect.

[0036] 105. When the ultraviolet disinfection equipment completes the disinfection task, the disinfection record corresponding to the disinfection task is stored in the database;

[0037] In this embodiment, when the ultraviolet disinfection equipment successfully completes the disinfection task, the control device will automatically record and store in detail all key data related to the disinfection task, including disinfection parameters, object information, location information, light intensity information, etc. in the database, which not only provides valuable data support for subsequent disinfection work, but also facilitates the management personnel to track and evaluate the disinfection process, thereby significantly improving the overall intelligence level of the disinfection process, the convenience of operation and the controllability of the disinfection effect.

[0038] The present application discloses a method for dynamically adjusting the disinfection distance. The LSTM network is used to predict the distance change of an object and optimize the positioning accuracy of the balance wheel mechanism. The PID algorithm and real-time light intensity information are combined to achieve precise control of the working state of the ultraviolet disinfection equipment and improve the disinfection efficiency and effect. Finally, the disinfection records are stored in a database for easy tracking and management, thereby improving the intelligence and reliability of the disinfection process as a whole.

[0039] Further, in an embodiment of the present invention, the step of obtaining the surface information of the object to be disinfected and the real-time temperature and humidity information fed back by the temperature and humidity sensor to confirm the disinfection parameters includes:

[0040] 201. Obtaining surface information of an object to be disinfected and real-time temperature and humidity information fed back by a temperature and humidity sensor, wherein the surface information of the object to be disinfected includes a material type, surface roughness, and color reflectivity of the object to be disinfected, and the real-time temperature and humidity information includes real-time temperature and real-time humidity;

[0041] In this embodiment, by obtaining the surface information of the object to be disinfected, including material type, surface roughness and color reflectivity, as well as real-time temperature and humidity information, it is possible to have a more comprehensive understanding of the characteristics and environmental conditions of the object to be disinfected, providing an accurate data basis for the subsequent disinfection process, and ensuring the pertinence and effectiveness of the generated disinfection parameters.

[0042] 202. Perform unique hot encoding on the material type of the object to be disinfected, normalize the surface roughness of the object to be disinfected, and describe the color reflectance in percentage form to achieve preprocessing of the surface information of the object to be disinfected;

[0043] In this embodiment, the surface information of the object to be disinfected is preprocessed, such as one-hot encoding the material type, normalizing the surface roughness, and describing the color reflectance in percentage form, so that the preprocessed information can be easier to be understood and utilized by the subsequent random forest model, thereby improving the accuracy and reliability of the generated disinfection parameters.

[0044] 203. Perform temperature compensation on the real-time temperature and humidity correction on the real-time humidity to complete the calibration of the real-time temperature and humidity information;

[0045] In this embodiment, the real-time temperature can be compensated by a pre-constructed temperature compensation relationship, and the real-time humidity can be compensated by a pre-constructed humidity correction relationship; by performing temperature compensation and humidity correction, the influence of environmental factors on the generation of disinfection parameters can be eliminated, ensuring that under different temperature and humidity conditions, the disinfection process performed based on the generated disinfection parameters can achieve the expected effect.

[0046] 204. Input the pre-treated surface information of the object to be disinfected and the calibrated real-time temperature and humidity information into the pre-trained random forest model to obtain disinfection parameters, wherein the disinfection parameters include disinfection power, ultraviolet light panel combination scheme and disinfection time;

[0047] In this embodiment, the pre-treated surface information of the object to be disinfected and the calibrated real-time temperature and humidity information are input into the pre-trained random forest model, and the disinfection parameters can be automatically and quickly obtained, including disinfection power, UV lamp panel combination scheme and disinfection time, which not only improves the automation degree of the disinfection process, but also ensures the disinfection efficiency and safety; for example, for Escherichia coli on the surface of stainless steel, a wavelength of 265nm and 30mJ / cm 2 The irradiation intensity is 100%, and the disinfection time is 45 seconds.

[0048] Further, in an embodiment of the present invention, the ultraviolet disinfection equipment is controlled to start working based on the confirmed disinfection parameters, and real-time object information fed back by the optical sensor, real-time position information fed back by the balance wheel encoder included in the balance wheel mechanism, and real-time light intensity information fed back by the light intensity sensor included in the ultraviolet lamp board are obtained, including:

[0049] 301. Control the ultraviolet disinfection equipment to start working based on the confirmed disinfection parameters;

[0050] 302. Acquire real-time object information fed back by the optical sensor, where the real-time object information includes object moving direction, object moving speed, and object moving acceleration;

[0051] In this embodiment, the optical sensor can be a laser rangefinder; after the optical sensor feeds back real-time object information, the image captured by the sensor is preprocessed, and the position of the object is detected in the preprocessed image, and then the motion of the detected object is tracked using the optical flow method, and its position change between consecutive frames is recorded. Finally, the position data is subjected to differential and integral operations to calculate the moving direction, moving speed and moving acceleration of the object.

[0052] 303. Acquire real-time position information fed back by a balance wheel encoder included in the balance wheel mechanism, wherein the real-time position information includes a real-time angle of the balance wheel and a real-time rotation position of the balance wheel;

[0053] 304. Acquire real-time light intensity information fed back by a light intensity sensor included in the ultraviolet lamp panel, wherein the real-time light intensity information includes twelve pieces of real-time radiation intensity information corresponding to the ultraviolet disinfection module.

[0054] Further, in an embodiment of the present invention, the object information fed back by the optical sensor is used to predict the distance change information using the LSTM network to generate a predetermined displacement instruction of the balance wheel, including:

[0055] 401. Pre-training an LSTM network prediction model, wherein the trained LSTM network prediction model includes an encoder, a decoder, and a fully connected layer connected in sequence, wherein the encoder includes three bidirectional LSTM layers, and the decoder includes two unidirectional LSTM layers;

[0056] In this embodiment, the encoder includes three bidirectional LSTM layers and the decoder includes two unidirectional LSTM layers, which can effectively extract and process the object information fed back by the optical sensor and improve the accuracy and reliability of the prediction results.

[0057] 402. Input the object information fed back by the optical sensor into the pre-trained LSTM network prediction model to obtain a prediction result and its corresponding confidence level;

[0058] 403. Obtain a preset confidence threshold corresponding to the color reflectance, and compare the confidence of the prediction result with the obtained confidence threshold;

[0059] In this embodiment, different confidence thresholds can be set for different object types (such as high-reflectivity metal or low-reflectivity cloth). For example, the confidence threshold for metal objects is set to 0.6, and the confidence threshold for cloth objects is set to 0.8. By comparing the prediction results and their corresponding confidence levels with the pre-set confidence thresholds, the reliability of the prediction results can be effectively evaluated, thereby improving the reliability of the generated predetermined displacement instructions for the balance wheel.

[0060] 404. If the confidence of the prediction result is greater than or equal to the confidence threshold, a predetermined displacement instruction of the balance wheel is generated based on the prediction result;

[0061] In this embodiment, if the confidence level of the prediction result meets or exceeds the set threshold standard, a predetermined balance wheel displacement instruction is generated based on the prediction result to ensure the accuracy and timeliness of the instruction, thereby achieving the best performance in practical applications.

[0062] 405. If the confidence of the prediction result is less than the confidence threshold, the prediction result is smoothed by using a Kalman filter algorithm, and the smoothed prediction result is adjusted to obtain an adjustment result, and a predetermined displacement instruction of the balance wheel is generated based on the adjustment result;

[0063] In this embodiment, if the confidence level of the prediction result fails to reach the threshold, the Kalman filter algorithm will be used to smooth the prediction result; the Kalman filter algorithm is a powerful data smoothing technology that can effectively reduce noise and uncertainty in the prediction; the prediction result after smoothing will be further adjusted and optimized, specifically, the execution speed of the displacement instruction will be reduced (such as reducing the maximum speed limit from 5cm / s to 3cm / s) to ensure the accuracy and stability of the balance wheel of the cross brace and the predetermined displacement instruction.

[0064] Furthermore, in an embodiment of the present invention, the balance wheel mechanism further includes a laser radar electrically connected to the control device, and the laser radar is used to detect the surface distance between the object to be sterilized and the balance wheel mechanism; the generating of the predetermined displacement instruction of the balance wheel based on the prediction result includes:

[0065] 501. Obtain a preset optimal disinfection distance, and generate a target distance based on the prediction result and the optimal disinfection distance;

[0066] In this embodiment, the optimal disinfection distance can be pre-set by the staff according to the surface information of the disinfected object and the requirements of the disinfection task, such as 20 cm; the target distance is the sum of the predicted result and the optimal disinfection distance.

[0067] 502. Obtain the real-time surface distance fed back by the laser radar, and confirm the displacement direction and displacement amplitude of the balance wheel mechanism based on the target distance and the real-time surface distance;

[0068] In this embodiment, if the real-time surface distance is greater than the target distance, the balance wheel mechanism needs to drive the UV lamp board away from the object to be disinfected, that is, the displacement direction is negative displacement; if the real-time surface distance is less than the target distance, the balance wheel mechanism needs to drive the UV lamp board closer to the object to be disinfected, that is, the displacement direction is positive displacement; the displacement amplitude is the difference between the target distance and the real-time surface distance.

[0069] 503. Obtain a preset maximum linear moving speed of the balance mechanism, and confirm the linear moving speed of the balance mechanism based on the displacement amplitude of the balance mechanism and the obtained maximum linear moving speed;

[0070] In this embodiment, the maximum linear movement speed is pre-set by the staff according to the design parameters and working parameters of the balance wheel mechanism; further, the linear movement speed is calculated based on the displacement amplitude of the balance wheel and the maximum physical stroke of the balance wheel, and the calculation formula is: 0.5+0.5*(|displacement amplitude| / maximum physical stroke); if the calculated linear movement speed is greater than the maximum linear movement speed, the maximum linear movement speed is taken as the actual linear movement speed.

[0071] 504. Integrate the target distance and the displacement direction, displacement amplitude and linear moving speed of the balance mechanism to obtain a predetermined balance displacement instruction.

[0072] Further, in an embodiment of the present invention, the method of combining the real-time object information, the real-time position information and the predetermined displacement instruction of the balance wheel, using the PID algorithm to adjust the working state of the balance wheel mechanism, and adjusting the working state of the ultraviolet lamp board based on the real-time light intensity information includes:

[0073] 601. Obtaining initial PID parameters pre-set based on a trial-and-error method;

[0074] In this embodiment, the initial PID parameters are pre-tuned by the trial and error method, which provides a basis for subsequent parameter optimization and improves the efficiency of parameter tuning. The trial and error method is an empirical parameter adjustment method. By trying different parameter combinations multiple times and observing the response of the ultraviolet disinfection equipment, a parameter combination with better performance is selected as the final result.

[0075] 602. Based on the real-time object information, the real-time position information and the predetermined displacement instruction of the balance wheel, a Moth-Flame optimization algorithm is used to optimize the PID parameters, wherein the objective function of the Moth-Flame optimization algorithm is to minimize the integral of the radiation intensity error;

[0076] In this embodiment, the Moth-Flame optimization algorithm is used to optimize the PID parameters. The Moth-Flame optimization algorithm is a new meta-heuristic optimization algorithm, which is mainly inspired by the navigation method of moths in nature, namely lateral positioning. In the MFO algorithm, individual moths represent candidate solutions to the optimization problem, the position of moths in the optimization space represents the variables for solving the optimization problem, and the flame is the best position found by the moth at the current number of iterations. The algorithm simulates the behavior of moths flying around the flame through three main operations: moths selecting flames, moths flying around flames, and moths flying into flames, and finally selects the optimal solution. When the Moth-Flame optimization algorithm is applied to PID parameter optimization, the minimization of the integral of radiation intensity error is used as the objective function, so as to optimize the control parameters of the balance mechanism. This optimization method effectively improves the control accuracy and response speed of the balance mechanism, so that the balance mechanism can work more accurately according to the predetermined displacement instruction.

[0077] 603. Adjust the working state of the balance wheel mechanism based on the optimized PID parameters;

[0078] 604. Obtain a preset irradiation adjustment threshold, and calculate an irradiance error according to real-time illumination information and disinfection power;

[0079] In this embodiment, first, a preset irradiance adjustment threshold is read from a configuration file or input through a user interface, and the irradiance adjustment threshold is used to determine whether to perform a pulse width modulation (PWM) adjustment operation on the ultraviolet lamp panel; then, the current light information is collected in real time through a light intensity sensor, covering the real-time light intensity data of twelve disinfection modules, and at the same time, the current disinfection power is obtained. The power is closely related to the working state of the irradiation source (such as an ultraviolet lamp), which can be achieved by reading the power output or control signal of the irradiation source; based on the real-time collected light information and disinfection power, the current irradiance value is calculated using a pre-constructed irradiance calculation formula or model; finally, the calculated irradiance value is compared with the preset irradiation adjustment threshold to obtain an irradiance error.

[0080] 605. If the irradiance error is greater than or equal to the preset irradiance adjustment threshold, a PWM duty cycle adjustment value is generated based on the irradiance error, and the working state of the ultraviolet lamp panel is adjusted based on the generated PWM duty cycle adjustment value;

[0081] In this embodiment, if the irradiance error is less than the preset irradiance adjustment threshold, the working state of the ultraviolet lamp panel is not adjusted.

[0082] In this embodiment, first, an initial duty cycle is obtained. The initial duty cycle can be obtained through the disinfection parameters generated by the aforementioned steps, and specifically, can be confirmed based on the disinfection power; then, an adjusted PWM duty cycle is generated according to the irradiance error, and the adjusted PWM duty cycle is equal to the initial duty cycle plus an adjustment amount, and the adjustment amount can be the product of the irradiance error and a certain proportional coefficient, that is, the adjustment amount is equal to the irradiance error multiplied by the proportional coefficient; the selection of the proportional coefficient needs to be determined according to the specific requirements and characteristics of the disinfection task, which determines the degree of influence of the irradiance error on the PWM duty cycle adjustment; the formula is: new duty cycle = initial duty cycle plus an adjustment amount.

[0083] Further, in an embodiment of the present invention, when the ultraviolet disinfection equipment completes the disinfection task, the disinfection record corresponding to the disinfection task is stored in the database, and then includes:

[0084] 701. When the preset attenuation prediction time is reached, the historical disinfection records stored in the database are obtained;

[0085] In this embodiment, the preset attenuation prediction time can be pre-set by the staff according to the design parameters of the ultraviolet disinfection equipment, and can be predicted once a week, once a month, or once when the number of times the ultraviolet disinfection equipment is turned on reaches a certain set value; the historical disinfection record includes multiple recent disinfection records. If it is predicted once a week, the historical disinfection record includes disinfection records within the past week; the number of times the ultraviolet disinfection equipment is turned on is confirmed by counting the number of disinfection records.

[0086] 702. Input the historical disinfection records into the pre-trained XGBoost model to obtain the light board attenuation prediction result of the XGBoost model;

[0087] In this embodiment, the input parameters of the XGBoost model include the cumulative number of switching times, the cumulative working time, and the working temperature corresponding to each disinfection record, and the working temperature can be fed back by a temperature sensor arranged in the ultraviolet lamp panel.

[0088] In this embodiment, the acquired historical disinfection records are input into the pre-trained XGBoost model to obtain the prediction results of the lamp board attenuation; as an efficient machine learning algorithm, the XGBoost model can make full use of the information in the historical data to accurately predict the attenuation of the lamp board, thereby improving the accuracy and reliability of the prediction.

[0089] 703. Obtain a preset attenuation threshold value. If the lamp board attenuation prediction result is less than or equal to the preset attenuation threshold value, generate a lamp board replacement warning instruction.

[0090] In this embodiment, if the predicted result of the lamp board attenuation is less than or equal to the preset attenuation threshold, the control device will automatically generate a lamp board replacement warning instruction, thereby realizing real-time monitoring and early warning of the lamp board status, avoiding problems such as reduced disinfection effect or equipment failure due to lamp board attenuation, and improving the use efficiency and safety of ultraviolet disinfection equipment.

[0091] The above describes the method for dynamically adjusting the disinfection distance in the embodiment of the present invention. The following describes the device for dynamically adjusting the disinfection distance in the embodiment of the present invention. Figure 2 In one embodiment of the present invention, a dynamic adjustment device for disinfection distance includes:

[0092] Confirmation module 801, used to obtain surface information of the object to be disinfected and real-time temperature and humidity information fed back by the temperature and humidity sensor to confirm the disinfection parameters;

[0093] The acquisition module 802 is used to control the ultraviolet disinfection equipment to start working based on the confirmed disinfection parameters, and obtain the real-time object information fed back by the optical sensor, the real-time position information fed back by the balance wheel encoder included in the balance wheel mechanism, and the real-time light intensity information fed back by the light intensity sensor included in the ultraviolet lamp board;

[0094] A generating module 803 is used to predict the distance change information using an LSTM network based on the object information fed back by the optical sensor, so as to generate a predetermined displacement instruction of the balance wheel;

[0095] An adjustment module 804 is used to adjust the working state of the balance wheel mechanism by using a PID algorithm in combination with the real-time object information, the real-time position information and the predetermined displacement instruction of the balance wheel, and to adjust the working state of the ultraviolet lamp panel based on the real-time light intensity information;

[0096] The recording module 805 is used to store the disinfection record corresponding to the disinfection task in the database when the ultraviolet disinfection equipment completes the disinfection task.

[0097] Based on the same idea as the method in the above embodiment, the device provided by the present application can implement the method in the above embodiment.

[0098] above Figure 2 The disinfection distance dynamic adjustment device in the embodiment of the present invention is described in detail from the perspective of modular functional entities, and the disinfection distance dynamic adjustment device in the embodiment of the present invention is described in detail from the perspective of hardware processing.

[0099] Figure 3It is a structural diagram of a dynamic adjustment device for disinfection distance provided by an embodiment of the present invention. The dynamic adjustment device 900 for disinfection distance may have relatively large differences due to different configurations or performances, and may include one or more processors (central processing units, CPU) 910 (for example, one or more processors) and a memory 920, and one or more storage media 930 (for example, one or more mass storage devices) storing application programs 933 or data 932. Among them, the memory 920 and the storage medium 930 may be short-term storage or permanent storage. The program stored in the storage medium 930 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations in the dynamic adjustment device 900 for disinfection distance. Furthermore, the processor 910 may be configured to communicate with the storage medium 930, and execute a series of instruction operations in the storage medium 930 on the dynamic adjustment device 900 for disinfection distance to implement the steps of the dynamic adjustment method for disinfection distance provided by the above-mentioned various method embodiments.

[0100] The disinfection distance dynamic adjustment device 900 may also include one or more power supplies 940, one or more wired or wireless network interfaces 950, one or more input and output interfaces 960, and / or one or more operating systems 931, such as Windows Serve, Mac OS X, Unix, Linux, FreeBSD, etc. It will be appreciated by those skilled in the art that Figure 3 The structure of the disinfection distance dynamic adjustment device shown does not constitute a limitation on the disinfection distance dynamic adjustment device, and may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0101] The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. Instructions are stored in the computer-readable storage medium. When the instructions are executed on a computer, the computer executes the steps of the method for dynamically adjusting the disinfection distance.

[0102] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described system, device, or unit can refer to the corresponding process in the aforementioned method embodiment and will not be repeated here.

[0103] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program codes.

[0104] Finally, it should be noted that the above description is only a preferred example of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for dynamically adjusting the disinfection distance, characterized in that: The ultraviolet disinfection equipment includes a control device and an optical sensor, a balance wheel mechanism, an ultraviolet lamp panel and a temperature and humidity sensor electrically connected to the control device respectively, wherein the optical sensor is used to obtain surface information of the object to be disinfected, and the temperature and humidity sensor is used to obtain ambient temperature and humidity information; The balance wheel mechanism is transmission-connected to the ultraviolet lamp panel to realize the angle adjustment of the ultraviolet lamp panel. The disinfection distance adjustment method includes: Obtain surface information of the object to be disinfected and real-time temperature and humidity information fed back by the temperature and humidity sensor to confirm the disinfection parameters; Based on the confirmed disinfection parameters, the ultraviolet disinfection equipment is controlled to start working, and real-time object information fed back by the optical sensor, real-time position information fed back by the balance wheel encoder included in the balance wheel mechanism, and real-time light intensity information fed back by the light intensity sensor included in the ultraviolet lamp board are obtained; Based on the object information fed back by the optical sensor, the LSTM network is used to predict the distance change information to generate the predetermined displacement instruction of the balance wheel; Combining real-time object information, real-time position information and the predetermined displacement instruction of the balance wheel, the PID algorithm is used to adjust the working state of the balance wheel mechanism, and the working state of the UV lamp board is adjusted based on the real-time light intensity information; When the ultraviolet disinfection equipment completes the disinfection task, the disinfection record corresponding to the disinfection task is stored in the database.

2. The method for dynamically adjusting the disinfection distance according to claim 1, characterized in that: The step of obtaining the surface information of the object to be disinfected and the real-time temperature and humidity information fed back by the temperature and humidity sensor to confirm the disinfection parameters includes: Obtaining surface information of the object to be disinfected and real-time temperature and humidity information fed back by the temperature and humidity sensor, wherein the surface information of the object to be disinfected includes the material type, surface roughness and color reflectivity of the object to be disinfected, and the real-time temperature and humidity information includes real-time temperature and real-time humidity; The material type of the object to be disinfected is uniquely encoded, the surface roughness of the object to be disinfected is normalized, and the color reflectance is described in percentage form to achieve preprocessing of the surface information of the object to be disinfected; Perform temperature compensation on the real-time temperature and humidity correction on the real-time humidity to complete the calibration of the real-time temperature and humidity information; The pretreated surface information of the object to be disinfected and the calibrated real-time temperature and humidity information are input into the pre-trained random forest model to obtain disinfection parameters, which include disinfection power, ultraviolet light panel combination scheme and disinfection time.

3. The method for dynamically adjusting the disinfection distance according to claim 1, characterized in that: The ultraviolet lamp board includes an annular frame, and six first ultraviolet disinfection modules with a wavelength of 265nm are arranged on the upper side of the annular frame, and the first ultraviolet disinfection modules are evenly distributed at intervals of 30° and each first ultraviolet disinfection module is tilted downward by 30°; six second ultraviolet disinfection modules with a wavelength of 280nm are arranged on the lower side of the annular frame, and the second ultraviolet disinfection modules are evenly distributed at intervals of 30° and each second ultraviolet disinfection module is tilted upward by 45°; the ultraviolet disinfection equipment is controlled to start working based on the confirmed disinfection parameters, and real-time object information fed back by the optical sensor, real-time position information fed back by the balance wheel encoder included in the balance wheel mechanism, and real-time light intensity information fed back by the light intensity sensor included in the ultraviolet lamp board are obtained, including: Controlling the ultraviolet disinfection equipment to start working based on the confirmed disinfection parameters; Acquire real-time object information fed back by the optical sensor, wherein the real-time object information includes the object moving direction, the object moving speed and the object moving acceleration; Acquire real-time position information fed back by a balance wheel encoder included in the balance wheel mechanism, wherein the real-time position information includes a real-time angle of the balance wheel and a real-time rotation position of the balance wheel; The real-time light intensity information fed back by the light intensity sensor included in the ultraviolet lamp panel is obtained, wherein the real-time light intensity information includes twelve real-time radiation intensity information corresponding to the ultraviolet disinfection module.

4. The method for dynamically adjusting the disinfection distance according to claim 2, characterized in that: The object information fed back by the optical sensor is used to predict the distance change information using the LSTM network to generate a predetermined displacement instruction of the balance wheel, including: A pre-trained LSTM network prediction model, wherein the trained LSTM network prediction model includes an encoder, a decoder, and a fully connected layer connected in sequence, wherein the encoder includes three bidirectional LSTM layers, and the decoder includes two unidirectional LSTM layers; The object information fed back by the optical sensor is input into the pre-trained LSTM network prediction model to obtain the prediction result and its corresponding confidence level; Obtaining a preset confidence threshold corresponding to the color reflectance, and comparing the confidence of the prediction result with the obtained confidence threshold; If the confidence level of the prediction result is greater than or equal to the confidence level threshold, a predetermined displacement instruction of the balance wheel is generated based on the prediction result; If the confidence of the prediction result is less than the confidence threshold, the Kalman filter algorithm is used to smooth the prediction result, and the smoothed prediction result is adjusted to obtain an adjustment result, and a predetermined displacement instruction of the balance wheel is generated based on the adjustment result.

5. The method for dynamically adjusting the disinfection distance according to claim 4, characterized in that: The balance wheel mechanism further includes a laser radar electrically connected to the control device, and the laser radar is used to detect the surface distance between the object to be sterilized and the balance wheel mechanism; the generating of the predetermined displacement instruction of the balance wheel based on the prediction result includes: Obtain a preset optimal disinfection distance, and generate a target distance based on the prediction result and the optimal disinfection distance; Obtain the real-time surface distance fed back by the laser radar, and confirm the displacement direction and displacement amplitude of the balance wheel mechanism based on the target distance and the real-time surface distance; Acquire a preset maximum linear movement speed of the balance mechanism, and confirm the linear movement speed of the balance mechanism based on the displacement amplitude of the balance mechanism and the acquired maximum linear movement speed; The target distance and the displacement direction, displacement amplitude and linear movement speed of the balance wheel mechanism are integrated to obtain the predetermined displacement instruction of the balance wheel.

6. The method for dynamically adjusting the disinfection distance according to claim 4, characterized in that: The method combines the real-time object information, the real-time position information and the predetermined displacement instruction of the balance wheel, uses the PID algorithm to adjust the working state of the balance wheel mechanism, and adjusts the working state of the ultraviolet lamp panel based on the real-time light intensity information, including: Obtain the initial PID parameters pre-tuned based on the trial and error method; Based on the real-time object information, the real-time position information and the predetermined displacement instruction of the balance wheel, the Moth-Flame optimization algorithm is used to optimize the PID parameters, and the objective function of the Moth-Flame optimization algorithm is to minimize the integral of the radiation intensity error; Adjust the working state of the balance wheel mechanism based on the optimized PID parameters; Obtain a preset irradiation adjustment threshold and calculate the irradiance error based on real-time light information and disinfection power; If the irradiance error is greater than or equal to the preset irradiance adjustment threshold, a PWM duty cycle adjustment value is generated based on the irradiance error, and the working state of the ultraviolet lamp panel is adjusted based on the generated PWM duty cycle adjustment value.

7. The method for dynamically adjusting the disinfection distance according to claim 1, characterized in that: When the ultraviolet disinfection equipment completes the disinfection task, the disinfection record corresponding to the disinfection task is stored in the database, and then includes: When the preset attenuation prediction time is reached, the historical disinfection records stored in the database are obtained; Input the historical disinfection records into the pre-trained XGBoost model to obtain the light board attenuation prediction results of the XGBoost model; The preset attenuation threshold is obtained. If the lamp board attenuation prediction result is ≤ the preset attenuation threshold, a lamp board replacement warning instruction is generated.

8. A dynamic adjustment device for disinfection distance, characterized in that: include: The confirmation module is used to obtain the surface information of the object to be disinfected and the real-time temperature and humidity information fed back by the temperature and humidity sensor to confirm the disinfection parameters; An acquisition module is used to control the ultraviolet disinfection equipment to start working based on the confirmed disinfection parameters, and to obtain real-time object information fed back by the optical sensor, real-time position information fed back by the balance wheel encoder included in the balance wheel mechanism, and real-time light intensity information fed back by the light intensity sensor included in the ultraviolet lamp board; A generation module is used to predict distance change information based on object information fed back by the optical sensor using an LSTM network to generate a predetermined displacement instruction for the balance wheel; An adjustment module, for adjusting the working state of the balance wheel mechanism by using a PID algorithm in combination with real-time object information, real-time position information and a predetermined displacement instruction of the balance wheel, and adjusting the working state of the ultraviolet lamp panel based on real-time light intensity information; The recording module is used to store the disinfection record corresponding to the disinfection task in the database when the ultraviolet disinfection equipment completes the disinfection task.

9. A disinfection distance dynamic adjustment device, characterized in that: The disinfection distance dynamic adjustment device comprises: a memory and at least one processor, wherein instructions are stored in the memory; At least one of the processors calls the instructions in the memory to enable the disinfection distance dynamic adjustment device to perform each step of the disinfection distance dynamic adjustment method as described in any one of claims 1-7.

10. A computer-readable storage medium having instructions stored thereon, characterized in that: When the instructions are executed by the processor, the various steps of the method for dynamically adjusting the disinfection distance as described in any one of claims 1 to 7 are implemented.

Images