A method for controlling the sterilization time of a germicidal lamp based on ultraviolet sensing
By analyzing the fluctuation abnormalities and distribution characteristics of ultraviolet intensity, calculating the non-stable index, and dynamically adjusting the sterilization time, the problem that the ultraviolet induction sterilization lamp cannot reflect changes in ultraviolet intensity is solved, and the sterilization efficiency and stability are improved.
Patent Information
- Application Number
- CN202411203570.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-30
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2044-08-30
AI Technical Summary
Existing ultraviolet induction sterilization lamps cannot effectively reflect changes in ultraviolet intensity, resulting in low sterilization efficiency and insufficient sterilization.
By obtaining the ultraviolet intensity, performing fluctuation anomaly analysis, determining the fluctuation outliers and distribution impact index, combining the overall trend changes and potential trend factors, the non-stable index of ultraviolet intensity is calculated, and the sterilization time is dynamically adjusted to respond to changes in ultraviolet intensity.
The sterilization effect of the ultraviolet sterilization lamp is consistent with the target expected by users, significantly improving the sterilization efficiency and ensuring the stability of the sterilization effect.
Smart Images

Figure CN118718046B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of ultraviolet sterilization, and in particular to a method for controlling the sterilization time of a germicidal lamp based on ultraviolet sensing. Background Art
[0002] UV induction germicidal lamp is a device that uses ultraviolet radiation to destroy the DNA or RNA structure of microorganisms, thereby achieving the purpose of efficient sterilization. As people pay more and more attention to public health and personal hygiene, UV germicidal lamps are favored for their environmental protection and no chemical residue. It can effectively kill pathogens, reduce the risk of disease transmission, and will not produce chemical residues. The sterilization time of UV induction germicidal lamps is not only related to the disinfection effect, but also to the safety of use and energy efficiency. Through intelligent control and timing functions, the sterilization process can be managed more accurately, resource waste can be reduced, and safety of use can be improved. It plays an important role in protecting public health and promoting sustainable development.
[0003] During the use of the germicidal lamp, it is necessary to set the specific ultraviolet intensity and specific sterilization time according to the actual situation to ensure the ideal sterilization effect. Ideally, the ultraviolet intensity released by the germicidal lamp is constant. However, in actual situations, due to interference problems such as the environment or the inside of the germicidal lamp, the ultraviolet intensity is not constant, but changes. At this time, under the changing ultraviolet intensity, if the germicidal lamp still uses the sterilization time set under the ideal ultraviolet intensity, it will lead to insufficient sterilization. The sterilization technology of the existing germicidal lamp cannot reflect the changes in ultraviolet intensity under actual conditions, and there will be problems of low sterilization efficiency and insufficient sterilization. Summary of the invention
[0004] In order to solve the technical problem that the sterilization time set by the germicidal lamp under the ideal ultraviolet intensity will lead to insufficient sterilization, the purpose of the present invention is to provide a method for controlling the sterilization time of a germicidal lamp based on ultraviolet sensing. The technical solution adopted is as follows:
[0005] In a first aspect, an embodiment of the present invention provides a method for controlling the sterilization time of a germicidal lamp based on ultraviolet sensing, the method comprising:
[0006] Get the UV intensity of the UV germicidal lamp;
[0007] The fluctuation anomaly analysis of ultraviolet intensity is carried out according to the time sequence to determine the fluctuation anomaly value; based on the time series distribution and numerical characteristics of the fluctuation anomaly value in the ultraviolet intensity sequence, the ultraviolet distribution impact index is determined; combined with the overall trend change of the fluctuation anomaly value and the ultraviolet distribution impact index, the distribution change characteristic value of the ultraviolet intensity sequence is determined;
[0008] Analyze the dynamic change trend of the UV distribution impact index over time and determine the potential trend factor of the UV distribution impact index; fit the potential trend factor corresponding to the UV distribution impact index with a straight line, and determine the non-steady-state index of UV intensity based on the steepness of the fitted straight line and the characteristic value of the distribution change;
[0009] Based on the non-steady-state index of ultraviolet intensity, the control duration of sterilization by the ultraviolet germicidal lamp is adjusted.
[0010] Furthermore, the abnormal fluctuation analysis of the ultraviolet intensity according to the time sequence to determine the abnormal fluctuation value includes:
[0011] Taking each UV intensity as the center, construct a local window corresponding to each UV intensity;
[0012] Analyze the data discreteness in the local window of each UV intensity and determine the local fluctuation factor corresponding to each UV intensity;
[0013] The local fluctuation factors are sorted in chronological order to obtain a distribution sequence, and the peak value in the distribution sequence and the corresponding collection time are obtained; the collection time corresponding to the peak value in the distribution sequence is recorded as the characteristic time; the peak value in the distribution sequence is taken as the fluctuation anomaly.
[0014] Furthermore, the ultraviolet distribution impact index is determined based on the temporal distribution and numerical characteristics of the fluctuation abnormal value in the ultraviolet intensity sequence, including:
[0015] The characteristic moment corresponding to any peak is taken as the target moment, the temporal distance between the target moment and other characteristic moments is analyzed, and the density weight of the target moment is determined;
[0016] Analyze the degree of outliers of data in a local window of ultraviolet intensity corresponding to a characteristic moment in the ultraviolet intensity sequence, and determine the outlier characteristics of the ultraviolet intensity corresponding to the characteristic moment;
[0017] The ultraviolet distribution impact index is determined by combining fluctuation anomalies, density weights and outlier characteristics. Among them, the fluctuation anomalies are negatively correlated with the ultraviolet distribution impact index, while the density weights and outlier characteristics are positively correlated with the ultraviolet distribution impact index.
[0018] Furthermore, the overall trend change of the fluctuation anomaly value and the ultraviolet distribution impact index are combined to determine the distribution change characteristic value of the ultraviolet intensity sequence, including:
[0019] Analyze the overall trend changes of fluctuation anomalies and determine the overall trend weight;
[0020] According to the overall trend weight and the ultraviolet distribution influence index, the distribution change characteristic value of the ultraviolet intensity sequence is determined.
[0021] Furthermore, analyzing the overall trend change of the fluctuation abnormal value and determining the overall trend weight includes:
[0022] Calculate the mean value of the ultraviolet intensity in the ultraviolet intensity sequence as the first influence weight;
[0023] Calculate the ratio of the maximum value to the minimum value of the fluctuation anomaly as the second influence weight;
[0024] An overall trend weight is determined according to the first influence weight and the second influence weight; wherein the first influence weight and the second influence weight are both positively correlated with the overall trend weight.
[0025] Furthermore, the analysis of the dynamic change trend of the ultraviolet distribution impact index over time to determine the potential trend factor of the ultraviolet distribution impact index includes:
[0026] Based on the data in the local window of the ultraviolet intensity corresponding to the characteristic moment, a straight line fitting is performed, and the slope of the fitted straight line is used as the intensity trend corresponding to the characteristic moment;
[0027] The UV distribution impact indexes of all peak values are arranged in ascending order according to the corresponding collection time of the peak values to obtain a distribution impact sequence; the data are marked according to the position of the data in the distribution impact sequence to obtain an adaptive marking result of the UV distribution impact index of each peak value as a trend similarity weight;
[0028] The potential trend factor of the ultraviolet distribution impact index is determined according to the intensity trend, the trend similarity weight and the outlier feature; wherein the intensity trend and the trend similarity weight are both positively correlated with the potential trend factor of the ultraviolet distribution impact index, and the outlier feature is negatively correlated with the potential trend factor of the ultraviolet distribution impact index.
[0029] Furthermore, the potential trend factor corresponding to the straight line fitting ultraviolet distribution impact index is determined based on the steepness of the fitted straight line and the characteristic value of the distribution change to determine the ultraviolet intensity non-steady-state index, including:
[0030] A straight line fitting is performed on the potential trend factors corresponding to each element in the UV distribution impact index, and the absolute value of the slope of the fitted straight line is taken as the trend impact;
[0031] The non-steady-state index of ultraviolet intensity is determined by combining the trend influence and the distribution change characteristic value; wherein both the trend influence and the distribution change characteristic value are positively correlated with the non-steady-state index of ultraviolet intensity.
[0032] Furthermore, adjusting the control duration of the ultraviolet germicidal lamp sterilization based on the ultraviolet intensity non-steady-state index includes:
[0033] The normalized non-steady-state index of ultraviolet intensity is adjusted to obtain the duration adjustment weight; the ideal duration of sterilization of the germicidal lamp under ideal conditions is weighted by the duration adjustment weight to obtain the adjusted control duration of sterilization of the germicidal lamp.
[0034] Further, the step of analyzing the degree of outliers in the local window of the ultraviolet intensity corresponding to the characteristic moment in the ultraviolet intensity sequence to determine the outlier features of the ultraviolet intensity corresponding to the characteristic moment includes:
[0035] The data mean of all data in the local window of the ultraviolet intensity corresponding to the characteristic moment is calculated; the difference between the ultraviolet intensity corresponding to the characteristic moment and the data mean is used as the outlier feature of the ultraviolet intensity corresponding to the characteristic moment.
[0036] Furthermore, determining the potential trend factor of the ultraviolet distribution impact index according to the intensity trend, the trend similarity weight and the outlier feature includes:
[0037] The negative correlation normalized value of the ratio of the outlier feature and the trend similarity weight was calculated, and the product of the negative correlation normalized value and the intensity trend was used as the potential trend factor of the UV distribution impact index.
[0038] In a second aspect, a germicidal lamp sterilization time control system based on ultraviolet sensing is provided, and the system includes the following modules:
[0039] An acquisition module, used for acquiring the ultraviolet intensity of the ultraviolet germicidal lamp;
[0040] The anomaly analysis module performs an anomaly analysis of the fluctuation of the ultraviolet intensity according to the time sequence to determine the fluctuation anomaly value; determines the ultraviolet distribution impact index based on the time series distribution and numerical characteristics of the fluctuation anomaly value in the ultraviolet intensity sequence; combines the overall trend change of the fluctuation anomaly value and the ultraviolet distribution impact index to determine the distribution change characteristic value of the ultraviolet intensity sequence;
[0041] The steady-state analysis module analyzes the dynamic change trend of the UV distribution impact index over time and determines the potential trend factor of the UV distribution impact index; the linear fitting of the potential trend factor corresponding to the UV distribution impact index determines the non-steady-state index of UV intensity based on the steepness of the fitted straight line and the characteristic value of the distribution change;
[0042] The regulating module adjusts the control duration of the sterilization of the ultraviolet germicidal lamp based on the ultraviolet intensity non-steady-state index.
[0043] In a third aspect, an embodiment of the present invention provides an electronic device, including a memory and a processor, wherein the memory stores executable code, and when the processor executes the executable code, various possible embodiments of the first aspect are implemented.
[0044] In a fourth aspect, an embodiment of the present invention provides a computer program product, which includes: a computer program code, which, when executed on a computer, enables the computer to execute the method in the first aspect or any possible implementation of the first aspect.
[0045] In a fifth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed in a computer, enables the computer to execute various possible implementations of the first aspect.
[0046] The embodiments of the present invention have at least the following beneficial effects:
[0047] Aiming at the problem of insufficient output stability of ultraviolet germicidal lamps, the present invention conducts abnormal analysis on ultraviolet intensity and constructs distribution change characteristic values to reflect the overall volatility and local distribution volatility characteristics of ultraviolet intensity, so as to quantify the fluctuation level and severity of ultraviolet intensity at different time points; in view of the problem that the unstable sterilization effect of ultraviolet germicidal lamps may lead to poor sterilization effect at a preset sterilization time, based on the overall fluctuation change and distribution influence, an ultraviolet intensity non-steady-state index is constructed to reflect the significance and potential fluctuation characteristics of the volatility distribution in ultraviolet intensity, so as to comprehensively consider the influence of the volatility and volatility distribution of ultraviolet intensity; finally, in view of the demand for real-time adjustment of the sterilization time of the ultraviolet germicidal lamp, a sterilization time control based on the ultraviolet intensity non-steady-state index is set, and the control duration of sterilization of the ultraviolet germicidal lamp is adjusted to reflect the real-time change of ultraviolet intensity and the consistency of the sterilization effect; by dynamically adjusting the sterilization time to respond to the non-ideal fluctuation of ultraviolet intensity, it is ensured that the sterilization effect reaches the user's expected goal, and a significant improvement in the sterilization efficiency is achieved. BRIEF DESCRIPTION OF THE DRAWINGS
[0048] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0049] Figure 1 A method flow chart of a method for controlling the sterilization time of a germicidal lamp based on ultraviolet sensing provided by an embodiment of the present invention;
[0050] Figure 2 A method flow chart of a method for obtaining a distribution change characteristic value of an ultraviolet intensity sequence provided by an embodiment of the present invention;
[0051] Figure 3 A method flow chart of a method for obtaining a non-steady-state index of ultraviolet intensity provided by an embodiment of the present invention;
[0052] Figure 4 A schematic diagram of the structure of a computer device provided by an embodiment of the present invention;
[0053] Figure 5 A peak graph corresponding to a distribution sequence provided by an embodiment of the present invention;
[0054] Figure 6 A straight line fitting graph for performing straight line fitting on a potential trend factor corresponding to an ultraviolet distribution impact index provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0055] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined purpose of the invention, the following, in combination with the accompanying drawings and preferred embodiments, a method for controlling the sterilization time of a germicidal lamp based on ultraviolet sensing proposed by the present invention, its specific implementation method, structure, characteristics and effects are described in detail as follows.
[0056] In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.
[0057] Among them, in the description of the embodiments of the present invention, unless otherwise specified, " / " means or, for example, A / B can mean A or B: "and / or" in the text is only a way to describe the association relationship of associated objects, indicating that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present invention, "multiple" refers to two or more than two.
[0058] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features.
[0059] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
[0060] The embodiments of the present invention are described below in conjunction with the accompanying drawings. Those skilled in the art will appreciate that, with the development of technology and the emergence of new scenarios, the technical solutions provided by the embodiments of the present invention are also applicable to similar technical problems.
[0061] The following is a detailed description of a method for controlling the sterilization time of a germicidal lamp based on ultraviolet sensing provided by the present invention in conjunction with the accompanying drawings.
[0062] See also Figure 1 , which shows a flowchart of a method for controlling the sterilization time of a germicidal lamp based on ultraviolet sensing provided by an embodiment of the present invention, the method comprising the following steps:
[0063] Step S100, obtaining the ultraviolet intensity of the ultraviolet germicidal lamp.
[0064] Select a small and light ultraviolet photosensitive tube, use additional components such as a special clamp, bracket or magnetic device to fix the ultraviolet photosensitive tube, and install it outside the symmetric center of the germicidal lamp or the divergent area of the light source to ensure that the intensity of the ultraviolet light released by the germicidal lamp can be accurately collected while avoiding blocking the light, and the intensity of the released ultraviolet light is recorded as the ultraviolet intensity. The ultraviolet intensity released by the germicidal lamp is collected at a preset time interval. In the embodiment of the present invention, the preset time interval t takes an empirical value of 0.5s. In other embodiments, the implementer adjusts the value according to the actual situation. When the ultraviolet germicidal lamp starts working, the sequence composed of ultraviolet intensity data obtained from the start of work to the current collection time is used as the ultraviolet intensity sequence.
[0065] Step S200, performing fluctuation anomaly analysis of ultraviolet intensity according to time sequence to determine fluctuation anomaly values; determining the ultraviolet distribution influence index based on the time series distribution and numerical characteristics of the fluctuation anomaly values in the ultraviolet intensity sequence; and determining the distribution change characteristic value of the ultraviolet intensity sequence in combination with the overall trend change of the fluctuation anomaly values and the ultraviolet distribution influence index.
[0066] During the use of germicidal lamps, the power supply of the ultraviolet lamp may become unstable due to the aging of the lamp tube, voltage fluctuations, etc., which in turn affects the output intensity of the ultraviolet light and causes changes in the intensity of the released ultraviolet light.
[0067] In some embodiments, the distribution change characteristic value of the ultraviolet intensity sequence is determined by performing an abnormal analysis on the ultraviolet intensity, that is, the above step S200 can be performed by Figure 2 The steps shown achieve:
[0068] Step S210, performing fluctuation anomaly analysis of the ultraviolet intensity according to the time sequence to determine the fluctuation anomaly value.
[0069] The fluctuation of ultraviolet intensity can reflect the abnormality of the corresponding ultraviolet intensity. The greater the fluctuation of ultraviolet intensity, the greater the probability of abnormality of the corresponding ultraviolet intensity. Therefore, in the embodiment of the present invention, the peak value in the ultraviolet intensity sequence is analyzed to determine the fluctuation abnormality value corresponding to the ultraviolet intensity.
[0070] In some possible implementations, the fluctuation abnormality of the ultraviolet intensity is analyzed to determine the fluctuation abnormality value, that is, the above step S210 can be implemented by the following steps S211 to S213 (not shown in the figure):
[0071] Step S211, taking each ultraviolet intensity as the center, constructing a local window corresponding to each ultraviolet intensity.
[0072] As an optional embodiment of the present invention, for the collected ultraviolet intensity sequence, a local window of size 1*N is established with each data point in the ultraviolet intensity sequence as the center, that is, each ultraviolet intensity in the ultraviolet intensity sequence as the center. In the embodiment of the present invention, N takes an empirical value of 9, and in other embodiments, the implementer can adjust the value according to actual conditions. It should be noted that N is an odd number to ensure that the number of data on both sides of each ultraviolet intensity is the same, and N≠1.
[0073] When the center of the local window is located near the left or right ends of the ultraviolet intensity sequence, causing the local window to exceed the sequence range, the exceeding part of the local window is filled with data points, and the size of the filled data points is the mean of the data points of the part of the window that does not exceed the sequence.
[0074] Step S212, analyzing the data discreteness in the local window of each ultraviolet intensity, and determining the local fluctuation factor corresponding to each ultraviolet intensity.
[0075] As an embodiment of the present invention, the coefficient of variation of all data points in a local window of ultraviolet intensity can be calculated as the local fluctuation factor of the window center, that is, the coefficient of variation of all ultraviolet intensities in a local window of ultraviolet intensity q1 is calculated as the local fluctuation factor of the ultraviolet intensity q1.
[0076] As another embodiment of the present invention, the variance or standard deviation of all data points in a local window of ultraviolet intensity may be calculated as a local fluctuation factor at the center of the window.
[0077] Step S213, sorting the local fluctuation factors according to the time sequence to obtain a distribution sequence, and obtaining the peak value in the distribution sequence and the corresponding collection time; recording the collection time corresponding to the peak value in the distribution sequence as the characteristic time; and taking the peak value in the distribution sequence as the fluctuation anomaly value.
[0078] The local fluctuation factors are sorted in chronological order to obtain a distribution sequence, and all local fluctuation factors are sorted in ascending chronological order to obtain a distribution sequence. Each data point in the distribution sequence represents the local fluctuation situation near the time when the data point was collected.
[0079] As an optional embodiment of the present invention, the distribution sequence is used as input, and the AMPD peak search algorithm is used to output all peaks of the distribution sequence, and the size of each peak and its corresponding acquisition time are recorded. The acquisition time corresponding to the peak in the distribution sequence is recorded as the characteristic time, and the peak in the distribution sequence is taken as the fluctuation abnormal value. Figure 5 , Figure 5 It is the peak graph corresponding to the distribution sequence, where the F1 curve is the curve fitted by the distribution sequence, the position corresponding to the F2 triangle is all the peaks of the distribution sequence, the horizontal axis of the peak graph is time in seconds, and the vertical axis is the local fluctuation factor.
[0080] Step S220, determining the ultraviolet distribution influence index based on the time series distribution and numerical characteristics of the fluctuation abnormal value in the ultraviolet intensity sequence.
[0081] The characteristic moment corresponding to any peak is taken as the target moment, the temporal distance between the target moment and other characteristic moments is analyzed, and the density weight of the target moment is determined.
[0082] As an optional embodiment of the present invention, the acquisition moments of all peaks are sorted in ascending order of time to obtain the acquisition moment sequence of all peaks; for each element in the acquisition moment sequence, the mean distance of the Euclidean distance between each element and all other elements is calculated, and the mean distance is used as the density weight of each element. The Euclidean distance between the elements actually reflects the temporal distance between different peaks, because the acquisition moment sequence is sorted according to time. The Euclidean distance between elements here can be understood as the distance between elements. For example, for the acquisition moment sequence {a1, a2, a3, a4}, the Euclidean distance between a1 and a2 is 1, the Euclidean distance between a1 and a3 is 2, and the Euclidean distance between a1 and a4 is 3.
[0083] The degree of outlier of data in a local window of ultraviolet intensity corresponding to a characteristic moment in the ultraviolet intensity sequence is analyzed to determine the outlier characteristics of the ultraviolet intensity corresponding to the characteristic moment.
[0084] The data of the ultraviolet intensity sequence at the characteristic moment is used as the maximum gradient data corresponding to each peak in the distribution sequence in the ultraviolet intensity sequence. The gradient mean of all data in the local window corresponding to each maximum gradient data in the ultraviolet intensity sequence is calculated, and the difference between each maximum gradient data and the gradient mean is used as the outlier feature of each maximum gradient data. It can be understood that the method for obtaining the outlier feature is to calculate the data mean of all data in the local window of the ultraviolet intensity corresponding to the characteristic moment; and use the difference between the ultraviolet intensity corresponding to the characteristic moment and the data mean as the outlier feature of the ultraviolet intensity corresponding to the characteristic moment.
[0085] The UV distribution impact index D is determined by combining the fluctuation anomaly, density weight and outlier characteristics. Among them, the fluctuation anomaly is negatively correlated with the UV distribution impact index, and the density weight and outlier characteristics are positively correlated with the UV distribution impact index.
[0086] The larger the normalized fluctuation anomaly value is, the more significant the peak value is relative to all peak values. At the same time, the concentration pattern of each peak at the acquisition time is represented by the density weight and outlier characteristics. The larger the density weight value is, the greater the distribution gap between the peak and other peaks at the corresponding acquisition time is. The greater the significance is, the larger the value of the outlier characteristic is, which means that the abnormality of the ultraviolet intensity at the acquisition time is greater.
[0087] As an embodiment of the present invention, the normalized value of the fluctuation anomaly value can be used as the denominator, the product of the density weight and the outlier feature can be used as the numerator, and the result value of the normalized mapping of the ratio obtained by the numerator and the denominator can be used as the ultraviolet distribution impact index. The purpose of normalizing the ultraviolet distribution impact index is to eliminate the influence of the dimension.
[0088] As an optional embodiment of the present invention, the normalized value of the fluctuation anomaly value can be obtained by using the ratio of each fluctuation anomaly value to the maximum value of the fluctuation anomaly value as the normalized fluctuation anomaly value, and the normalization of the fluctuation anomaly value can also be achieved by a linear normalization method.
[0089] Step S230, combining the overall trend change of the fluctuation abnormal value and the ultraviolet distribution influence index, determining the distribution change characteristic value of the ultraviolet intensity sequence.
[0090] Analyze the overall trend change of the fluctuation anomaly and determine the overall trend weight. The overall trend weight can be understood as the overall fluctuation change weight of the ultraviolet intensity sequence. The local fluctuation level of the ultraviolet intensity sequence at all acquisition times is determined by calculating the mean of all data in the distribution sequence to obtain the first impact weight; that is, the mean of the ultraviolet intensity in the ultraviolet intensity sequence is calculated as the first impact weight; the larger the value of the first impact weight, the greater the fluctuation of the ultraviolet intensity at different time points, which means that the output of the ultraviolet lamp is unstable; at the same time, the fluctuation range of the ultraviolet intensity sequence in the acquisition interval is determined by the ratio of the maximum value to the minimum value of the fluctuation anomaly in the distribution sequence, and the second impact weight is obtained; that is, the ratio of the maximum value to the minimum value of the fluctuation anomaly is calculated as the second impact weight; the larger the value of the second impact weight, the more drastic the change of the ultraviolet intensity at different time points, and the greater the fluctuation anomaly of the ultraviolet intensity.
[0091] Calculate the mean value of the ultraviolet intensity in the ultraviolet intensity sequence as the first influencing weight; calculate the ratio of the maximum value to the minimum value of the fluctuation anomaly as the second influencing weight; determine the overall trend weight according to the first influencing weight and the second influencing weight; wherein the first influencing weight and the second influencing weight are both positively correlated with the overall trend weight.
[0092] As an optional embodiment of the present invention, the product of the first influence weight and the second influence weight may be used as the overall trend weight.
[0093] According to the overall trend weight and the ultraviolet distribution influence index, the distribution change characteristic value of the ultraviolet intensity sequence is determined.
[0094] Calculate the mean of the UV distribution impact index corresponding to all peaks as the initial impact index; use the overall trend weight as the weight, weight the initial impact index, and obtain the weighted result value as the distribution change characteristic value of the UV intensity sequence. It can also be understood as taking the product of the overall trend weight and the initial impact index as the distribution change characteristic value of the UV intensity sequence.
[0095] The overall trend weight is the overall fluctuation change weight of the UV intensity sequence. The larger the value of the overall trend weight is, the greater the change in UV intensity during the observation period and the more unstable the UV output is. The initial impact index is the mean of all peak distribution impact indices. The larger the value of the initial impact index is, the greater the distribution impact of UV intensity is.
[0096] The overall trend weight provides the fluctuation changes of the series, while the UV distribution impact index provides detailed information on the specific local fluctuation distribution in the series. The combination of the two can provide a more comprehensive perspective to evaluate the distribution changes of the UV intensity series, that is, the distribution change characteristic value is positively proportional to the overall trend weight and the UV distribution impact index.
[0097] Step S300, analyzing the dynamic change trend of the ultraviolet distribution impact index over time, and determining the potential trend factor of the ultraviolet distribution impact index; linearly fitting the potential trend factor corresponding to the ultraviolet distribution impact index, and determining the ultraviolet intensity non-steady-state index based on the steepness of the fitted straight line and the distribution change characteristic value.
[0098] In order to more clearly identify and observe the dynamic change trend of ultraviolet intensity over time and evaluate the stability of ultraviolet intensity, the ultraviolet distribution influence index of all peak values is arranged in ascending order according to the order of the peak value corresponding to the collection time to obtain the distribution influence sequence, and the potential trend factor of each element in the distribution influence sequence is calculated. Then, the corresponding ultraviolet intensity non-steady-state index is determined by fitting analysis of the potential trend factors corresponding to each element in the ultraviolet distribution influence index. The ultraviolet intensity non-steady-state index can reflect the output stability of the ultraviolet germicidal lamp. The larger the ultraviolet intensity non-steady-state index, the greater the fluctuation and potential instability of the ultraviolet intensity output of the ultraviolet germicidal lamp, while the smaller the ultraviolet intensity non-steady-state index, the more stable the ultraviolet output.
[0099] In some embodiments, the potential trend factor is determined by analyzing the dynamic change trend of the ultraviolet intensity, and the potential trend factor is fitted to obtain the ultraviolet intensity non-steady-state index that can reflect the stability of the ultraviolet germicidal lamp. That is, the above step S300 can be performed by Figure 3 The steps shown achieve:
[0100] Step S310, analyzing the dynamic change trend of the ultraviolet distribution impact index over time, and determining the potential trend factor of the ultraviolet distribution impact index.
[0101] Among them, the distribution characteristics of each element in the distribution influence sequence at the time of collection are determined by the density weight. The larger the value of the density weight, the greater the time difference between the element and the other elements in the distribution influence sequence, and the greater the significance. At this time, the data point corresponding to the ultraviolet intensity of the element is closer to the data points corresponding to the ultraviolet intensity of other elements, and the possibility of a potential trend is smaller.
[0102] The local rate of change of ultraviolet intensity over time is determined by the intensity trend of each element in the distribution influence sequence, and the intensity trend is obtained by taking the data in the local window corresponding to each maximum gradient data on the ultraviolet intensity sequence as input and performing straight line fitting. In the embodiment of the present invention, the straight line fitting can be performed by the least squares method, and in other embodiments, the implementer can also set other existing straight line fitting technologies to perform straight line fitting.
[0103] The slope of the fitted straight line is taken as the intensity trend. The larger the value of the intensity trend is, the faster the ultraviolet intensity changes in the maximum gradient data corresponding to the intensity trend in the ultraviolet intensity sequence, the more significant the increase or decrease of the ultraviolet intensity, and the greater the possibility of a potential trend. It can be understood that the method for obtaining the intensity trend is to perform straight line fitting based on the data in the local window of the ultraviolet intensity corresponding to the characteristic moment, and use the slope of the fitted straight line as the intensity trend corresponding to the characteristic moment.
[0104] The ultraviolet distribution influence indexes of all peak values are arranged in ascending order according to the collection time corresponding to the peak value to obtain the distribution influence sequence.
[0105] According to the position of the data in the distribution influence sequence, the data is marked, and the adaptive marking result of the UV distribution influence index of each peak is obtained as the trend similarity weight.
[0106] More specifically: mark each data point in the distribution influence sequence, and the marking result is M. Taking the i-th data point as an example, the marking result of the i-th data point is , assuming that there are N data points in the distribution influence sequence, if ,but ,like ,but ;in, The symbol for rounding up. Then the order of the distribution in the sequence is the autocorrelation coefficient of each data point. As the trend similarity weight of the data point, the larger the value of the trend similarity weight is, the more similar the potential fluctuation of the corresponding element in the distribution influence sequence is to the fluctuation of other elements in the distribution influence sequence, that is, the element has a higher consistency in trend with other elements in the distribution influence sequence, indicating that the fluctuation of the element is not isolated and has a higher potential volatility.
[0107] The potential trend factor of the ultraviolet distribution impact index is determined according to the intensity trend, the trend similarity weight and the outlier feature, wherein the intensity trend and the trend similarity weight are both positively correlated with the potential trend factor of the ultraviolet distribution impact index, and the outlier feature is negatively correlated with the potential trend factor of the ultraviolet distribution impact index.
[0108] As an optional embodiment of the present invention, a method for obtaining a potential trend factor is as follows: a negative correlation normalized value of a ratio of an outlier feature to a trend similarity weight is calculated, and the product of the negative correlation normalized value and the intensity trend is used as a potential trend factor of the ultraviolet distribution impact index. The potential trend factor is normalized and mapped to facilitate analysis in subsequent steps.
[0109] Among them, the method for negative correlation normalization of the ratio of outlier features and trend similarity weights can be to use the negative value of the ratio of outlier features and trend similarity weights as the exponent and an exponential function with a base of a natural constant to achieve negative correlation normalization of the ratio of outlier features and trend similarity weights.
[0110] Step S320 , a potential trend factor corresponding to the ultraviolet distribution influence index is fitted by a straight line, and a non-steady-state index of ultraviolet intensity is determined based on the steepness of the fitted straight line and the characteristic value of the distribution change.
[0111] Linear fitting is performed on the potential trend factor corresponding to the UV distribution impact index, that is, linear fitting is performed on the potential trend factor corresponding to each element in the UV distribution impact index, and the UV intensity non-steady-state index is determined based on the steepness of the fitted straight line and the characteristic value of the distribution change. Figure 6 , Figure 6 It is a straight line fitting diagram for straight line fitting of the potential trend factor corresponding to the ultraviolet distribution impact index, where F4 represents the straight line obtained by straight line fitting, F3 discrete points are data points corresponding to the potential trend factor of the ultraviolet distribution impact index, the horizontal axis of the straight line fitting diagram is time, in seconds, and the vertical axis is the potential trend factor. Specifically:
[0112] The potential trend factor F of all data points in the distribution influence sequence is used as input, and the least squares method is used for straight line fitting to obtain the slope of the fitted straight line. The absolute value of the slope is used as the steepness of the fitted straight line, which can also be recorded as the trend influence value. Then, the ultraviolet intensity non-steady-state index of the ultraviolet intensity sequence is determined by combining the steepness of the fitted straight line and the characteristic value of the distribution change. Among them, the steepness of the fitted straight line and the characteristic value of the distribution change are positively correlated with the ultraviolet intensity non-steady-state index of the ultraviolet intensity sequence.
[0113] As an optional embodiment of the present invention, the product of the steepness of the fitted straight line and the characteristic value of the distribution change can be used as the ultraviolet intensity non-steady-state index of the ultraviolet intensity sequence.
[0114] The UV intensity non-steady-state index reflects the output stability of the UV germicidal lamp. The larger the value of the UV intensity non-steady-state index, the greater the fluctuation and potential instability of the UV intensity output of the UV germicidal lamp. The smaller the value of the UV intensity non-steady-state index, the more stable the UV output.
[0115] Step S400, adjusting the control duration of the ultraviolet germicidal lamp sterilization based on the ultraviolet intensity non-steady-state index.
[0116] Finally, based on the non-ideal changes of ultraviolet rays, the time adjustment amount of the sterilization time is calculated, and the output of the ultraviolet lamp is dynamically adjusted in sections according to the PID controller to respond to the real-time changes in ultraviolet intensity.
[0117] A sterilization time controller based on the non-steady-state index of ultraviolet intensity is set. When using the ultraviolet sterilization lamp, the user will set the specific ultraviolet intensity and sterilization time of the ultraviolet lamp, that is, the user hopes to use a fixed ultraviolet intensity for a fixed duration to achieve the sterilization effect. It is understandable that the expected sterilization effect of the customer can only be achieved when the lamp is in an ideal sterilization state under the duration set by the user. However, due to the non-ideal ultraviolet intensity output of the ultraviolet sterilization lamp, the ultraviolet intensity will fluctuate in an unstable state, resulting in the actual sterilization effect failing to meet the user's expectations. Due to the non-ideal fluctuation of ultraviolet rays, it is believed that the sterilization time set by the user has an error, which will result in the sterilization effect not meeting the standard.
[0118] Therefore, based on the non-steady-state index of ultraviolet intensity, the control duration of the sterilization of the germicidal lamp is adjusted.
[0119] The normalized non-steady-state index of ultraviolet intensity is adjusted to obtain the duration adjustment weight; the ideal duration of sterilization of the germicidal lamp under ideal conditions is weighted by the duration adjustment weight to obtain the adjusted control duration of sterilization of the germicidal lamp. Specifically: the collected ultraviolet intensity sequence is used as input, and the sterilization duration set by the user is evenly divided into a preset number of segments. In an embodiment of the present invention, the preset number is 4, and in other embodiments, the preset number can be set by the implementer. In an embodiment of the present invention, the sterilization duration set by the user is evenly divided into four segments. The last moment of each segment is recorded as a time exchange node, except for the last segment.
[0120] Taking four segments as an example, the UV intensity sequence contains three time exchange nodes. The UV intensity non-steady-state index at each time exchange node is calculated. The calculation formula for the standard time of the n+1 segment is, that is, the calculation formula for the control time of the n+1 segment is:
[0121] ;
[0122] in, is the standard duration of the n+1 segment; It is the sigmoid function, also known as the S-type function; is the non-steady-state index of ultraviolet intensity in the nth segment; The sterilization time is set by the user according to actual needs; is the duration adjustment right; q is the preset number, which is 4 here.
[0123] Among them, the sigmoid function realizes the purpose of normalizing the non-steady-state index of ultraviolet intensity. The larger the non-steady-state index of ultraviolet intensity, the more violent the fluctuation of ultraviolet intensity, and the more unstable the sterilization effect may be. The sterilization time set by the user is evenly divided into four sections, and a time exchange node is set at the last moment of each section. The purpose is to monitor and adjust the ultraviolet intensity in different time periods to maintain the consistency of the sterilization effect. The sterilization time of the next section is adjusted according to the standard time calculated in the previous period to ensure that the sterilization effect expected by the user is achieved.
[0124] The standard durations of the preset number of segments are added together to obtain the adjusted control duration of the sterilization of the germicidal lamp.
[0125] The embodiment of the present invention provides a sterilization time control system of a germicidal lamp based on ultraviolet sensing, the system comprising:
[0126] An acquisition module, used for acquiring the ultraviolet intensity of the ultraviolet germicidal lamp;
[0127] The anomaly analysis module performs an anomaly analysis of the fluctuation of the ultraviolet intensity according to the time sequence to determine the fluctuation anomaly value; determines the ultraviolet distribution impact index based on the time series distribution and numerical characteristics of the fluctuation anomaly value in the ultraviolet intensity sequence; combines the overall trend change of the fluctuation anomaly value and the ultraviolet distribution impact index to determine the distribution change characteristic value of the ultraviolet intensity sequence;
[0128] The steady-state analysis module analyzes the dynamic change trend of the UV distribution impact index over time and determines the potential trend factor of the UV distribution impact index; the linear fitting of the potential trend factor corresponding to the UV distribution impact index determines the non-steady-state index of UV intensity based on the steepness of the fitted straight line and the characteristic value of the distribution change;
[0129] The regulating module adjusts the control duration of the sterilization of the ultraviolet germicidal lamp based on the ultraviolet intensity non-steady-state index.
[0130] Optionally, the transmission medium may be a wired link, such as but not limited to coaxial cable, optical fiber, and digital subscriber line, or a wireless link, such as but not limited to Wireless Fidelity (WIFI), Bluetooth, and mobile device network.
[0131] It should be noted that: the device provided in the above embodiment is only illustrated by the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the computer device is divided into different functional modules to complete all or part of the functions described above. In addition, the shopping guide device provided in the above embodiment and the image extension method embodiment belong to the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.
[0132] Figure 4 is a schematic diagram of the structure of a computer device provided by an embodiment of the present invention. Figure 4 As shown, the computer device 500 includes: a memory 510, a processor 520, and a computer program 530 stored in the memory 510 and running on the processor 520, wherein when the processor 520 executes the computer program 530, the computer device can execute any one of the above-mentioned methods for controlling the sterilization time of a sterilization lamp based on ultraviolet sensing.
[0133] In addition, an embodiment of the present invention also protects a device, which may include a memory and a processor, wherein the memory stores an executable program code, and the processor is used to call and execute the executable program code to execute a method for controlling the sterilization time of a sterilization lamp based on ultraviolet sensing provided in an embodiment of the present invention.
[0134] The embodiment of the present invention can divide the functional modules of the device according to the above method example. For example, each functional module can be corresponded, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware. It should be noted that the division of modules in this embodiment is schematic and is only a logical function division. There may be other division methods in actual implementation.
[0135] In the case of dividing each module according to each function, the device may also include a signal uploading module, a determining module, an adjusting module, etc. It should be noted that all relevant contents of each step involved in the above method embodiment can be referred to the functional description of the corresponding functional module, which will not be repeated here.
[0136] It should be understood that the device provided in the embodiment of the present invention is used to execute the above-mentioned method for controlling the sterilization time of a germicidal lamp based on ultraviolet sensing, and thus can achieve the same effect as the above-mentioned implementation method.
[0137] In the case of an integrated unit, the device may include a processing module and a storage module. When the device is applied to a device, the processing module may be used to control and manage the actions of the device. The storage module may be used to support the device to execute mutual program codes, etc. The processing module may be a processor or a controller, which may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of the present invention. The processor may also be a combination that implements a computing function, such as a combination of one or more microprocessors, a combination of digital signal processing (DSP) and a microprocessor, etc. The storage module may be a memory.
[0138] In addition, the device provided in an embodiment of the present invention may specifically be a chip, a component or a module, and the chip may include a connected processor and a memory; wherein the memory is used to store instructions, and when the processor calls and executes the instructions, the chip can execute a method for controlling the sterilization time of a sterilization lamp based on ultraviolet sensing provided in the above embodiment.
[0139] An embodiment of the present invention also provides a computer-readable storage medium, which stores a computer program code. When the computer program code runs on a computer, the computer executes the above-mentioned related method steps to implement a method for controlling the sterilization time of a sterilization lamp based on ultraviolet sensing provided in the above embodiment.
[0140] An embodiment of the present invention further provides a computer program product. When the computer program product is run on a computer, the computer executes the above-mentioned related steps to implement a method for controlling the sterilization time of a germicidal lamp based on ultraviolet sensing provided in the above embodiment.
[0141] Among them, the device, computer-readable storage medium, computer program product or chip provided in the embodiments of the present invention are all used to execute the corresponding methods provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding methods provided above, and will not be repeated here. Through the description of the above implementation methods, technicians in the relevant field can understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In the embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways.
[0142] The device embodiments described above are merely illustrative. For example, the division of modules or units is only a logical function division. There may be other divisions in actual implementation. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, indirect coupling or communication connection of devices or units, which may be electrical, mechanical or other forms.
[0143] It should also be noted that, in this article, the terms "include", "comprises" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.
[0144] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
[0145] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.
[0146] The above contents are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims
1. A method for controlling the sterilization time of a germicidal lamp based on ultraviolet sensing, characterized in that: The method comprises the following steps: Get the UV intensity of the UV germicidal lamp; The fluctuation anomaly analysis of ultraviolet intensity is carried out according to the time sequence to determine the fluctuation anomaly value; based on the time series distribution and numerical characteristics of the fluctuation anomaly value in the ultraviolet intensity sequence, the ultraviolet distribution impact index is determined; combined with the overall trend change of the fluctuation anomaly value and the ultraviolet distribution impact index, the distribution change characteristic value of the ultraviolet intensity sequence is determined; Analyze the dynamic change trend of the UV distribution impact index over time and determine the potential trend factor of the UV distribution impact index; fit the potential trend factor corresponding to the UV distribution impact index with a straight line, and determine the non-steady-state index of UV intensity based on the steepness of the fitted straight line and the characteristic value of the distribution change; Based on the non-steady-state index of ultraviolet intensity, adjusting the control duration of sterilization by the ultraviolet germicidal lamp; The abnormal fluctuation analysis of the ultraviolet intensity according to the time sequence to determine the abnormal fluctuation value includes: Taking each UV intensity as the center, construct a local window corresponding to each UV intensity; Analyze the data discreteness in the local window of each UV intensity and determine the local fluctuation factor corresponding to each UV intensity; The local fluctuation factors are sorted in time order to obtain a distribution sequence, and the peak value in the distribution sequence and the corresponding collection time are obtained; the collection time corresponding to the peak value in the distribution sequence is recorded as the characteristic time; the peak value in the distribution sequence is taken as the fluctuation anomaly value; The method of determining the ultraviolet distribution impact index based on the temporal distribution and numerical characteristics of the fluctuation abnormal value in the ultraviolet intensity sequence includes: The characteristic moment corresponding to any peak is taken as the target moment, the temporal distance between the target moment and other characteristic moments is analyzed, and the density weight of the target moment is determined; Analyze the degree of outliers of data in a local window of ultraviolet intensity corresponding to a characteristic moment in the ultraviolet intensity sequence, and determine the outlier characteristics of the ultraviolet intensity corresponding to the characteristic moment; The UV distribution impact index is determined by combining the fluctuation anomaly, density weight and outlier characteristics. The fluctuation anomaly is negatively correlated with the UV distribution impact index, while the density weight and outlier characteristics are positively correlated with the UV distribution impact index. The analysis of the dynamic change trend of the ultraviolet distribution impact index over time and determination of potential trend factors of the ultraviolet distribution impact index include: Based on the data in the local window of the ultraviolet intensity corresponding to the characteristic moment, a straight line fitting is performed, and the slope of the fitted straight line is used as the intensity trend corresponding to the characteristic moment; The UV distribution impact indexes of all peak values are arranged in ascending order according to the corresponding collection time of the peak values to obtain a distribution impact sequence; the data are marked according to the position of the data in the distribution impact sequence to obtain an adaptive marking result of the UV distribution impact index of each peak value as a trend similarity weight; Determine the potential trend factor of the ultraviolet distribution impact index according to the intensity trend, the trend similarity weight and the outlier feature; wherein the intensity trend and the trend similarity weight are both positively correlated with the potential trend factor of the ultraviolet distribution impact index, and the outlier feature is negatively correlated with the potential trend factor of the ultraviolet distribution impact index; The potential trend factor corresponding to the straight line fitting ultraviolet distribution impact index is used to determine the ultraviolet intensity non-steady-state index based on the steepness of the straight line after fitting and the characteristic value of distribution change, including: A straight line fitting is performed on the potential trend factor corresponding to the UV distribution impact index, and the absolute value of the slope of the fitted straight line is taken as the trend impact; Combining the trend influence and the distribution change characteristic value, determining the ultraviolet intensity non-steady-state index; wherein the trend influence and the distribution change characteristic value are both positively correlated with the ultraviolet intensity non-steady-state index; Determining the potential trend factor of the ultraviolet distribution impact index according to the intensity trend, the trend similarity weight and the outlier feature includes: The negative correlation normalized value of the ratio of the outlier feature and the trend similarity weight was calculated, and the product of the negative correlation normalized value and the intensity trend was used as the potential trend factor of the UV distribution impact index.
2. The method for controlling the sterilization duration of a germicidal lamp based on ultraviolet sensing according to claim 1, characterized in that: The overall trend change of the fluctuation anomaly value and the ultraviolet distribution impact index are combined to determine the distribution change characteristic value of the ultraviolet intensity sequence, including: Analyze the overall trend changes of fluctuation anomalies and determine the overall trend weight; According to the overall trend weight and the ultraviolet distribution influence index, the distribution change characteristic value of the ultraviolet intensity sequence is determined.
3. The method for controlling the sterilization time of a germicidal lamp based on ultraviolet sensing according to claim 2 is characterized in that: The analyzing the overall trend change of the fluctuation abnormal value and determining the overall trend weight include: Calculate the mean value of the ultraviolet intensity in the ultraviolet intensity sequence as the first influence weight; Calculate the ratio of the maximum value to the minimum value of the fluctuation anomaly as the second influence weight; An overall trend weight is determined according to the first influence weight and the second influence weight; wherein the first influence weight and the second influence weight are both positively correlated with the overall trend weight.
4. The method for controlling the sterilization time of a germicidal lamp based on ultraviolet sensing according to claim 1, characterized in that: The step of adjusting the control duration of sterilization by the ultraviolet germicidal lamp based on the ultraviolet intensity non-steady-state index comprises: The normalized non-steady-state index of ultraviolet intensity is adjusted to obtain the duration adjustment weight; the ideal duration of sterilization of the germicidal lamp under ideal conditions is weighted by the duration adjustment weight to obtain the adjusted control duration of sterilization of the germicidal lamp.
5. The method for controlling the sterilization time of a germicidal lamp based on ultraviolet sensing according to claim 1, characterized in that: The step of analyzing the outlier degree of data in a local window of ultraviolet intensity corresponding to a characteristic moment in the ultraviolet intensity sequence and determining the outlier feature of the ultraviolet intensity corresponding to the characteristic moment comprises: The data mean of all data in the local window of the ultraviolet intensity corresponding to the characteristic moment is calculated; the difference between the ultraviolet intensity corresponding to the characteristic moment and the data mean is used as the outlier feature of the ultraviolet intensity corresponding to the characteristic moment.
