Cooperative control method and system for ultraviolet sterilization equipment group

Abstract

The invention provides an ultraviolet sterilization equipment group cooperative control method and system, and relates to the technical field of ultraviolet sterilization equipment control, and the method comprises the steps: obtaining equipment working state information, and dividing a master-slave equipment group; collecting microorganism information to generate a sensitivity distribution diagram and calculating a frequency band weight coefficient; generating a frequency spectrum adjustment instruction and monitoring the sterilization effect; collecting energy consumption data, calculating total energy consumption and generating an energy efficiency score; and combining to generate a cooperative control instruction. Accurate regulation and control according to the characteristics of microorganisms are realized, the sterilization efficiency is improved, the energy consumption is reduced, and the service life of equipment is prolonged.

Description

Technical Field

[0001] This invention relates to the field of ultraviolet sterilization equipment control technology, and in particular to a method and system for the coordinated control of a group of ultraviolet sterilization equipment. Background Technology

[0002] Ultraviolet (UV) sterilization technology is widely used in medical, food processing, water treatment, and public environment disinfection fields due to its high efficiency and lack of chemical residues. Traditional UV sterilization equipment mainly uses a single wavelength UV light source, typically 254nm UVC, which achieves sterilization by destroying the DNA / RNA structure of microorganisms. With technological advancements, UV sterilization equipment has evolved from single-unit operation to a multi-device collaborative system to improve sterilization coverage and efficiency in large spaces or complex environments.

[0003] Current ultraviolet (UV) sterilization equipment cluster control technology has significant limitations: existing UV sterilization equipment clusters typically use uniform parameter configurations, failing to differentiate control based on the types and distribution characteristics of microorganisms in different areas. This results in insufficient sterilization in some areas while energy is wasted in others. Traditional UV sterilization systems lack real-time monitoring and adaptive adjustment capabilities, unable to dynamically adjust UV irradiation intensity and spectral characteristics according to changes in the microbial load in the environment, reducing sterilization efficiency and increasing energy consumption. Furthermore, when multiple devices work collaboratively, existing technologies lack intelligent grouping and cooperation mechanisms based on performance indicators, making it difficult to achieve optimal allocation of equipment resources, resulting in low overall system energy efficiency and inadequate lifespan management.

[0004] These technical limitations restrict the effectiveness of ultraviolet sterilization equipment in large-scale application scenarios. There is an urgent need for an ultraviolet sterilization control method that can accurately adjust the spectrum according to the characteristics of microorganisms, adaptively control based on real-time monitoring data, and achieve intelligent collaboration among equipment groups, so as to improve sterilization efficiency while reducing energy consumption. Summary of the Invention

[0005] The present invention provides a method and system for coordinated control of a group of ultraviolet sterilization equipment, which can solve the problems in the prior art.

[0006] A first aspect of the present invention provides a method for coordinated control of a group of ultraviolet sterilization devices, comprising: The working status information of multiple ultraviolet sterilization devices is obtained, and the comprehensive performance index of each ultraviolet sterilization device is calculated based on the working status information. The ultraviolet sterilization device group is divided into a master control device group and a slave control device group based on a preset threshold. The system collects information on the types and density of microorganisms within the coverage area in real time using photoelectric sensors. It then extracts the sensitive spectrum information corresponding to different microorganisms from a pre-set ultraviolet spectrum feature database to generate a microbial spectrum sensitivity distribution map of the target area. Based on this map, it calculates the weighting coefficients for each frequency band and, combined with the spatial distribution of the master control device group and the slave control device group, generates a spectrum adjustment command for the ultraviolet germicidal lamps. This command is then sent to the corresponding ultraviolet germicidal devices. The system monitors the sterilization effect of each ultraviolet germicidal device after executing the spectrum adjustment command in real time and calculates the sterilization compliance rate. The system collects energy consumption data of each device in the master control device group and the slave control device group in real time, and calculates the total energy consumption of the device group based on the spatial distribution of the devices; it generates an energy efficiency score based on the sterilization compliance rate and the total energy consumption, and compares the energy efficiency score with a preset target energy efficiency range; it generates energy-saving control instructions for the device group based on the comparison results. The spectrum adjustment command and the energy-saving control command are combined to generate a coordinated control command for the ultraviolet sterilization equipment group.

[0007] Based on the aforementioned operating status information, the comprehensive performance index of each ultraviolet sterilization device is calculated. Combined with preset thresholds, the ultraviolet sterilization device group is divided into a master control device group and a slave control device group, including: The working status information is used to construct a working status time series matrix according to the time series. Long-term and short-term features are extracted from the working status time series matrix using a temporal convolutional network to obtain a temporal feature vector. The feature weights of each feature component in the temporal feature vector are calculated based on the attention mechanism. The temporal feature vector is then weighted according to the feature weights to obtain a feature fusion value. Calculate the basic performance index of each of the ultraviolet sterilization devices. The basic performance index is the sum of the first weighted value of the ratio of irradiance intensity to rated irradiance intensity and the second weighted value of the remaining life ratio. The remaining life ratio is the ratio of the rated life minus the device operating time to the rated life. The third weighted value of the basic performance index is added to the fourth weighted value of the feature fusion value to obtain the comprehensive performance index of each ultraviolet sterilization device; a grouping threshold is calculated based on the comprehensive performance index of all ultraviolet sterilization devices in the ultraviolet sterilization device group; the master control device group and the slave control device group are divided by comparing the comprehensive performance index with the grouping threshold. Based on the time-series feature vector, the performance change trend of each ultraviolet sterilization device is predicted. When the prediction result shows that the performance of the ultraviolet sterilization device in the slave device group is on the rise, the ultraviolet sterilization device is adjusted to the master device group; when the prediction result shows that the performance of the ultraviolet sterilization device in the master device group is on the fall, the ultraviolet sterilization device is adjusted to the slave device group.

[0008] The sensitive spectrum information corresponding to different microorganisms is extracted from a pre-set ultraviolet spectrum feature database to generate a microbial spectrum sensitivity distribution map of the target area, including: Based on the microbial species and density information, microbial feature vectors are formed in a preset dimensional order; the product of the microbial feature vectors with each dimension of the feature vectors in the preset feature database is calculated, and the product is multiplied by the feature weight of the corresponding dimension and summed to obtain a weighted sum of products; the square root of the product of the sum of squares of the microbial feature vectors and the sum of squares of the feature vectors in the preset feature database is calculated, and the weighted sum of products is divided by the square root to obtain the weighted cosine similarity; The recognition probability of each microorganism in the target area is determined based on the weighted cosine similarity. The recognition probability of each microorganism is multiplied by the corresponding spectral sensitivity feature stored in the preset feature database, and then multiplied by the environmental factor correction coefficient and summed to obtain the spectral sensitivity function of the microorganism in the target area. The microbial spectral sensitivity function is integrated with the microbial density within the target area within a preset wavelength range to generate a microbial spectral sensitivity distribution map characterizing the distribution features of microorganisms in the target area. Calculate the second partial derivative of the microbial spectral sensitivity distribution map in the spatial dimension, multiply the second partial derivative by the diffusion coefficient, and add it to the response function of the microbial density to obtain the rate of change of the microbial spectral sensitivity distribution map in the time dimension; The microbial spectral sensitivity distribution map is updated based on the rate of change to obtain a dynamic distribution map of the microbial distribution characteristics of the target area over time.

[0009] Based on the microbial spectral sensitivity distribution map, the weighting coefficients of each frequency band are calculated, and combined with the spatial distribution of the master control device group and the slave control device group, a spectral adjustment command for the ultraviolet germicidal lamp is generated, including: The microbial spectral sensitivity distribution map is discretized within a preset wavelength range to obtain sensitivity distributions for multiple frequency bands; spatial importance weight values ​​are set according to the degree of disinfection importance at different locations within the target area, and the weight coefficient of the corresponding frequency band is calculated by combining the sensitivity distribution of the corresponding frequency band. The irradiance intensity distribution of each ultraviolet sterilization device in the master control device group and the slave control device group is obtained respectively. The power coefficient of each ultraviolet sterilization device is calculated according to its rated power. The total irradiance intensity distribution of the target area is obtained by multiplying the irradiance intensity distribution with the power coefficient and superimposing them. Calculate the integral value of the product of the irradiance intensity distributions of adjacent ultraviolet sterilization devices in the target area, and divide the integral value by the square root of the product of the integral values ​​of the squares of the irradiance intensity distributions of the two ultraviolet sterilization devices in the target area to obtain the complementarity coefficient between the devices. The objective function for spectrum optimization is obtained by multiplying the square of the difference between the ratio of the actual irradiance intensity to the total irradiance intensity distribution in each frequency band and the target spectrum ratio, and then summing the results by multiplying the corresponding frequency band weighting coefficients. Under the constraints that the total power does not exceed the maximum power limit and the wavelength of the frequency band is within the preset range, the spectrum optimization objective function is optimized and solved using the gradient descent algorithm to obtain the spectrum adjustment parameters.

[0010] Real-time monitoring of the sterilization effect of each ultraviolet sterilization device after executing the spectrum adjustment command, and calculation of the sterilization compliance rate, including: Ultraviolet spectral data of each monitoring point within the target area are collected. The correlation between the ultraviolet spectral data and the target spectral data is calculated to obtain the spectral matching degree. Cell activity data and microbial integrity data of each monitoring point are collected simultaneously to obtain cell activity value and microbial damage value, respectively. The spectrum matching degree is divided by the preset target matching degree to obtain the spectrum matching degree ratio. The cell activity value is divided by the preset standard activity value to obtain the activity ratio. The microbial damage value is divided by the preset allowable damage threshold and the supplementary value is taken to obtain the integrity ratio. The spectrum matching degree ratio, activity ratio and integrity ratio are multiplied together to obtain the local sterilization compliance rate of each monitoring point. The location criticality is set according to the spatial location of each monitoring point in the target area and the disinfection requirements. The location criticality is multiplied by a preset weight adjustment coefficient and the negative value is taken. The negative value is substituted into the exponential function to obtain the exponential term. The spatial importance weight of each monitoring point is obtained according to the exponential term. The spatial importance weight is positively correlated with the location criticality. The local sterilization compliance rate of each monitoring point is multiplied by the spatial importance weight of the corresponding location, and then double-integrated within the spatial coordinate range of the entire target area and integrated over the monitoring time period to obtain a weighted cumulative effect. The spatial importance weight of each monitoring point is triple-integrated within the same spatial and time range to obtain a weight normalization benchmark. The weighted cumulative effect is divided by the weight normalization benchmark to obtain the global sterilization compliance rate, which reflects the sterilization effect of the entire target area.

[0011] Real-time collection of energy consumption data from each device in the master control device group and the slave control device group, combined with the spatial distribution of the devices, to calculate the total energy consumption of the device group, including: The basic energy consumption, radiation energy consumption, and auxiliary system energy consumption of each ultraviolet sterilization device in the main control device group and the slave control device group are collected separately. The basic energy consumption, radiation energy consumption, and auxiliary system energy consumption are added together to obtain the total energy consumption of each ultraviolet sterilization device. The output power and input power of each ultraviolet sterilization device are collected, and the temperature and humidity data of the device's operating environment are acquired simultaneously. The temperature correction coefficient is calculated based on the temperature data, and the humidity correction coefficient is calculated based on the humidity data. The ratio of output power to input power is multiplied by the temperature correction coefficient and the humidity correction coefficient to obtain the dynamic efficiency of each ultraviolet sterilization device. Obtain the spatial coordinates of each ultraviolet sterilization device within the target area, calculate the distance between each ultraviolet sterilization device and the center point of the target area, multiply the distance by a preset attenuation coefficient and take the negative exponent, and then multiply it by the importance index of the location of each ultraviolet sterilization device to obtain the position weight of each ultraviolet sterilization device. Multiply the total energy consumption of each ultraviolet sterilization device in the main control equipment group by the dynamic efficiency and the first equipment weight, respectively. Multiply the total energy consumption of each ultraviolet sterilization device in the slave control equipment group by the dynamic efficiency and the second equipment weight, respectively. Sum the two products to obtain the total energy consumption of the equipment group. Multiply the mutual coupling coefficient of any two UV sterilization devices by their corresponding location weights and collaborative working coefficients, and sum the results. Multiply the summation by the total energy consumption of the device group to obtain the corrected total energy consumption considering spatial distribution.

[0012] A second aspect of the present invention provides a collaborative control system for a group of ultraviolet sterilization devices, comprising: The first unit is used to acquire the working status information of multiple ultraviolet sterilization devices, calculate the comprehensive performance index of each ultraviolet sterilization device based on the working status information, and divide the ultraviolet sterilization device group into a master control device group and a slave control device group based on a preset threshold. The second unit is used to collect information on the types and density of microorganisms within the coverage area in real time using photoelectric sensors, extract sensitive spectrum information corresponding to different microorganisms from a preset ultraviolet spectrum feature database, and generate a microorganism spectrum sensitivity distribution map of the target area; calculate the weight coefficient of each frequency band based on the microorganism spectrum sensitivity distribution map, and generate a spectrum adjustment command for the ultraviolet germicidal lamps by combining the spatial distribution of the master control device group and the slave control device group, and send the spectrum adjustment command to the corresponding ultraviolet germicidal device; monitor the sterilization effect of each ultraviolet germicidal device after executing the spectrum adjustment command in real time, and calculate the sterilization compliance rate; The third unit is used to collect energy consumption data of each device in the master control device group and the slave control device group in real time, and calculate the total energy consumption of the device group in combination with the spatial distribution of the devices; calculate and generate an energy efficiency score based on the sterilization compliance rate and the total energy consumption, compare the energy efficiency score with the preset target energy efficiency range; and generate energy-saving control instructions for the device group based on the comparison results. The fourth unit is used to combine the spectrum adjustment command and the energy-saving control command to generate a coordinated control command for the ultraviolet sterilization equipment group.

[0013] A third aspect of the embodiments of the present invention, An electronic device is provided, comprising: processor; Memory used to store processor-executable instructions; The processor is configured to invoke instructions stored in the memory to execute the aforementioned method.

[0014] Fourth aspect of the present invention, A computer-readable storage medium is provided, having stored thereon computer program instructions that, when executed by a processor, implement the aforementioned method.

[0015] The beneficial effects of this application are as follows: This invention acquires the working status information of multiple ultraviolet sterilization devices and divides them into master control device groups and slave control device groups, thereby realizing hierarchical management among the devices, improving the overall system's collaborative efficiency and control accuracy, and enabling the device group to flexibly adjust its working mode according to the actual needs of different areas.

[0016] This invention generates a microbial spectrum sensitivity distribution map based on real-time collected information on microbial species and density, and calculates the weighting coefficient of each frequency band accordingly. This enables precise control of the spectrum of ultraviolet germicidal lamps, significantly improving the targeted killing efficiency of different microorganisms while reducing energy consumption, making the sterilization process more environmentally friendly and efficient.

[0017] This invention achieves an optimal balance between sterilization effect and energy consumption by real-time monitoring of sterilization effect and energy consumption data, calculating energy efficiency score and comparing it with the target energy efficiency range, and generating energy-saving control commands. It reduces operating costs while ensuring sterilization quality and is suitable for places with high requirements for disinfection and sterilization, such as hospitals and food processing plants. Attached Figure Description

[0018] Figure 1 This is a schematic flowchart of the collaborative control method for a group of ultraviolet sterilization devices according to an embodiment of the present invention; Figure 2 This is a system architecture diagram for the dynamic distribution of microbial spectrum sensitivity. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0020] The technical solution of the present invention will be described in detail below with reference to specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments.

[0021] Figure 1 This is a schematic flowchart of the collaborative control method for a group of ultraviolet sterilization devices according to an embodiment of the present invention, as shown below. Figure 1 As shown, the method includes: The working status information of multiple ultraviolet sterilization devices is obtained, and the comprehensive performance index of each ultraviolet sterilization device is calculated based on the working status information. The ultraviolet sterilization device group is divided into a master control device group and a slave control device group based on a preset threshold. The system collects information on the types and density of microorganisms within the coverage area in real time using photoelectric sensors. It then extracts the sensitive spectrum information corresponding to different microorganisms from a pre-set ultraviolet spectrum feature database to generate a microbial spectrum sensitivity distribution map of the target area. Based on this map, it calculates the weighting coefficients for each frequency band and, combined with the spatial distribution of the master control device group and the slave control device group, generates a spectrum adjustment command for the ultraviolet germicidal lamps. This command is then sent to the corresponding ultraviolet germicidal devices. The system monitors the sterilization effect of each ultraviolet germicidal device after executing the spectrum adjustment command in real time and calculates the sterilization compliance rate. The system collects energy consumption data of each device in the master control device group and the slave control device group in real time, and calculates the total energy consumption of the device group based on the spatial distribution of the devices; it generates an energy efficiency score based on the sterilization compliance rate and the total energy consumption, and compares the energy efficiency score with a preset target energy efficiency range; it generates energy-saving control instructions for the device group based on the comparison results. The spectrum adjustment command and the energy-saving control command are combined to generate a coordinated control command for the ultraviolet sterilization equipment group.

[0022] In one optional implementation, the comprehensive performance index of each ultraviolet sterilization device is calculated based on the operating status information, and the ultraviolet sterilization device group is divided into a master control device group and a slave control device group based on a preset threshold, including: The working status information is used to construct a working status time series matrix according to the time series. Long-term and short-term features are extracted from the working status time series matrix using a temporal convolutional network to obtain a temporal feature vector. The feature weights of each feature component in the temporal feature vector are calculated based on the attention mechanism. The temporal feature vector is then weighted according to the feature weights to obtain a feature fusion value. Calculate the basic performance index of each of the ultraviolet sterilization devices. The basic performance index is the sum of the first weighted value of the ratio of irradiance intensity to rated irradiance intensity and the second weighted value of the remaining life ratio. The remaining life ratio is the ratio of the rated life minus the device operating time to the rated life. The third weighted value of the basic performance index is added to the fourth weighted value of the feature fusion value to obtain the comprehensive performance index of each ultraviolet sterilization device; a grouping threshold is calculated based on the comprehensive performance index of all ultraviolet sterilization devices in the ultraviolet sterilization device group; the master control device group and the slave control device group are divided by comparing the comprehensive performance index with the grouping threshold. Based on the time-series feature vector, the performance change trend of each ultraviolet sterilization device is predicted. When the prediction result shows that the performance of the ultraviolet sterilization device in the slave device group is on the rise, the ultraviolet sterilization device is adjusted to the master device group; when the prediction result shows that the performance of the ultraviolet sterilization device in the master device group is on the fall, the ultraviolet sterilization device is adjusted to the slave device group.

[0023] In this embodiment, the group control system of the ultraviolet sterilization equipment group calculates the comprehensive performance index based on the working status information of each device, and divides the devices into master control equipment group and slave control equipment group accordingly.

[0024] The system first acquires the operating status information of each device in the UV sterilization equipment group, including data such as irradiance intensity, operating time, current fluctuation, and temperature change. This data is then used to construct a time-series matrix of operating status. For example, for a specific UV sterilization device, the irradiance intensity at 10 consecutive time points is 250, 248, 245, 247, 249, 246, 244, 242, 240, and 238 μW / cm². 2The runtime increased to 5000, 5001, 5002, 5003, 5004, 5005, 5006, 5007, 5008, and 5009 hours, with current fluctuations of 0.01, 0.02, 0.01, 0.03, 0.02, 0.01, 0.02, 0.03, 0.02, and 0.04 A, and temperature changes of 38.5, 38.7, 38.6, 38.8, 39.0, 39.1, 39.0, 38.9, 39.2, and 39.3 °C. This data was organized into a matrix, where rows represent time points and columns represent different state parameters.

[0025] The system employs a temporal convolutional network to extract short- and long-term features from the operating state temporal matrix. This network contains multiple convolutional layers, each using kernels of different sizes to extract features at different time scales. For example, a kernel of size 3 is used to extract short-term features, a kernel of size 5 to extract medium-term features, and a kernel of size 7 to extract long-term features. For the example data above, after processing by the temporal convolutional network, the resulting temporal feature vector [0.85, 0.92, 0.76, 0.88] represents the features of irradiance stability, lifetime consumption rate, current stability, and temperature stability, respectively.

[0026] The system calculates the weights of each feature component in the temporal feature vector based on an attention mechanism. It then calculates the impact of each feature component on device performance, generating a corresponding attention score. For example, for the aforementioned feature vector, the calculated attention scores are [0.35, 0.30, 0.20, 0.15], indicating that irradiance stability has the greatest impact on device performance, while temperature stability has a relatively smaller impact. The system uses these attention scores as feature weights to perform a weighted average on the temporal feature vector, resulting in a feature fusion value of 0.85.

[0027] The system calculates the basic performance indicators for each ultraviolet sterilization device. The rated irradiance of the device is 300 μW / cm². 2 The actual irradiation intensity was 240 μW / cm. 2 The irradiance ratio is 0.8. The rated life of the equipment is 10,000 hours, the operating time is 5,009 hours, and the remaining lifespan is 0.4991. Setting the first weighting value to 0.6 and the second weighting value to 0.4, the basic performance index is 0.8 × 0.6 + 0.4991 × 0.4 = 0.68.

[0028] The system calculates a weighted sum of the basic performance index and the feature fusion value to obtain the comprehensive performance index. With the third weighting value set at 0.7 and the fourth weighting value at 0.3, the comprehensive performance index of the device is 0.68 × 0.7 + 0.85 × 0.3 = 0.731.

[0029] For all devices in the UV sterilization equipment group, the system calculates their respective comprehensive performance indicators using the same method. Assuming the group contains 10 devices with comprehensive performance indicators of 0.731, 0.688, 0.792, 0.645, 0.816, 0.702, 0.673, 0.755, 0.827, and 0.710, the system calculates the grouping threshold using the average of all device comprehensive performance indicators, i.e., (0.731+0.688+0.792+0.645+0.816+0.702+0.673+0.755+0.827+0.710) / 10=0.734. Devices with a comprehensive performance index higher than the threshold of 0.734 were assigned to the master control device group, including devices 3, 5, 8, and 9, with index values ​​of 0.792, 0.816, 0.755, and 0.827, respectively. Devices with a comprehensive performance index lower than the threshold were assigned to the slave control device group, including devices 1, 2, 4, 6, 7, and 10, with index values ​​of 0.731, 0.688, 0.645, 0.702, 0.673, and 0.710, respectively.

[0030] The system predicts the performance trend of each UV sterilization device based on time-series feature vectors. It uses a sliding window method to analyze the changes in the overall performance index of the devices over a period of time. For example, device 2 in the slave control group has an overall performance index of 0.670, 0.675, 0.680, 0.684, and 0.688 over the past five time points, showing an upward trend, and its performance is predicted to continue to improve. The system moves device 2 to the master control group. Meanwhile, device 8 in the master control group has an overall performance index of 0.770, 0.765, 0.762, 0.758, and 0.755 over the past five time points, showing a downward trend, and its performance is predicted to continue to decline. The system moves device 8 to the slave control group.

[0031] By employing the above methods, the system dynamically adjusts the members of the master control equipment group and the slave control equipment group, ensuring that the equipment in the master control equipment group always maintains a high performance level, thereby improving the overall sterilization efficiency and energy utilization of the ultraviolet sterilization equipment group. Simultaneously, by predicting performance change trends, the system adjusts the equipment groupings in advance to avoid the negative impact of sudden performance drops on the sterilization effect.

[0032] In one optional implementation, sensitive spectrum information corresponding to different microorganisms is extracted from a preset ultraviolet spectrum feature database to generate a microbial spectrum sensitivity distribution map of the target area, including: Based on the microbial species and density information, microbial feature vectors are formed in a preset dimensional order; the product of the microbial feature vectors with each dimension of the feature vectors in the preset feature database is calculated, and the product is multiplied by the feature weight of the corresponding dimension and summed to obtain a weighted sum of products; the square root of the product of the sum of squares of the microbial feature vectors and the sum of squares of the feature vectors in the preset feature database is calculated, and the weighted sum of products is divided by the square root to obtain the weighted cosine similarity; The recognition probability of each microorganism in the target area is determined based on the weighted cosine similarity. The recognition probability of each microorganism is multiplied by the corresponding spectral sensitivity feature stored in the preset feature database, and then multiplied by the environmental factor correction coefficient and summed to obtain the spectral sensitivity function of the microorganism in the target area. The microbial spectral sensitivity function is integrated with the microbial density within the target area within a preset wavelength range to generate a microbial spectral sensitivity distribution map characterizing the distribution features of microorganisms in the target area. Calculate the second partial derivative of the microbial spectral sensitivity distribution map in the spatial dimension, multiply the second partial derivative by the diffusion coefficient, and add it to the response function of the microbial density to obtain the rate of change of the microbial spectral sensitivity distribution map in the time dimension; The microbial spectral sensitivity distribution map is updated based on the rate of change to obtain a dynamic distribution map of the microbial distribution characteristics of the target area over time.

[0033] This invention discloses a method for extracting microbial sensitive spectrum information from a preset ultraviolet spectrum feature database and generating a distribution map. The technical implementation process of this invention will be described in detail below with reference to practical application scenarios.

[0034] In practical applications, the first step is to obtain information on the types and densities of microorganisms in the target area. For example, in a 100-square-meter indoor environment, an E. coli density of 200 CFU / m³ was detected. 3 The density of Staphylococcus aureus was 150 CFU / m³. 3 The Aspergillus density was 80 CFU / m³. 3 Microbial feature vectors are constructed based on a preset dimensional order: [microbial species identifier, density value, growth state coefficient]. The feature vector of Escherichia coli can be represented as [1, 200, 0.85], the feature vector of Staphylococcus aureus is [2, 150, 0.92], and the feature vector of Aspergillus is [3, 80, 0.78].

[0035] For each microorganism, calculate the weighted cosine similarity between its feature vector and the vectors in the preset feature database. Assume the standard feature vector for *E. coli* in the preset database is [1, 180, 0.90], and the feature weights are [0.6, 0.3, 0.1]. In the calculation, first, the product of each dimension of the two vectors is obtained as [1×1, 200×180, 0.85×0.90] = [1, 36000, 0.765]. Multiplying the product by the corresponding dimension weights and summing the results, we get the weighted sum of the products as 1×0.6 + 36000×0.3 + 0.765×0.1 = 10800.6765. Then, the sum of squares of the feature vectors is calculated to obtain (1 2 +200 2 +0.85 2 )×(1 2 +180 2 +0.90 2 =40069.7225×32481.81=1301528151.1, taking the square root gives 36076.98. The weighted sum of the products divided by the square root gives a weighted cosine similarity of 0.2994.

[0036] Through similar calculations, the weighted cosine similarity for Staphylococcus aureus was 0.3256, and the weighted cosine similarity for Aspergillus was 0.2718. These weighted cosine similarities correspond to the recognition probabilities of the microorganisms, namely, the recognition probability for Escherichia coli is 0.2994, for Staphylococcus aureus it is 0.3256, and for Aspergillus it is 0.2718.

[0037] The ultraviolet spectral sensitivity features corresponding to each microorganism are extracted from a pre-defined feature database. For example, the sensitivity coefficient for *Escherichia coli* in the wavelength range of 254-265 nm is 0.85, for *Staphylococcus aureus* it is 0.78, and for *Aspergillus* it is 0.92. The microorganism identification probability is multiplied by the corresponding spectral sensitivity feature, and then multiplied by environmental factor correction coefficients (such as a temperature correction coefficient of 0.95 and a humidity correction coefficient of 0.92), and the results are summed to obtain the microbial spectral sensitivity function for the target area.

[0038] For the wavelength range of 254-265nm, the calculated result is (0.2994×0.85+0.3256×0.78+0.2718×0.92)×0.95×0.92=0.6884. Similarly, sensitivity values ​​are calculated for other wavelength ranges (such as 265-280nm, 280-295nm, etc.) to form a spectral sensitivity function covering the 200-400nm wavelength range.

[0039] The microbial spectral sensitivity function is integrated with the microbial density within the target region over a preset wavelength range. Specifically, at each spatial grid point (x, y, z), the product of the spectral sensitivity and the microbial density at that point is calculated and integrated along the wavelength dimension. For example, at coordinates (10, 15, 2), the E. coli density is 180 CFU / m³. 3 The spectral sensitivity response value of this point in the wavelength range of 254-265nm was calculated to be 180 × 0.6884 × 11 = 1364.232. By performing similar calculations on all spatial points within the target area, a three-dimensional spatial distribution map of microbial spectral sensitivity was generated.

[0040] To describe the evolution of this distribution plot over time, the second-order partial derivative of the distribution plot in the spatial dimension is calculated. In practical calculations, the finite difference method can be used. Assuming the spectral sensitivity value at coordinates (10, 15, 2) is 1364.232, and the values ​​at its two adjacent points in the x-direction (9, 15, 2) and (11, 15, 2) are 1328.547 and 1382.168 respectively, then the second-order partial derivative of this point in the x-direction is approximately (1328.547 - 2 × 1364.232 + 1382.168) / 1. 2 =−17.749. Similar to calculating the second-order partial derivatives in the y and z directions.

[0041] Multiplying the second-order partial derivatives in each direction by the diffusion coefficient (e.g., 0.05 for the x-direction, 0.04 for the y-direction, and 0.03 for the z-direction), we get the diffusion term as −17.749×0.05+(-15.362)×0.04+(-10.958)×0.03=−1.5949. Adding the response function of microbial density (e.g., 0.02×180=3.6), we get the rate of change of the spectral sensitivity at this point over time as −1.5949+3.6=2.0051.

[0042] Based on the calculated rate of change, the spectral sensitivity distribution after a time interval Δt can be predicted. Assuming Δt is 1 hour, the spectral sensitivity at coordinates (10, 15, 2) is updated to 1364.232 + 2.0051 × 1 = 1366.2371. By performing similar calculations on all points within the target area, an updated distribution map is obtained. Repeating the above process generates a dynamic distribution map characterizing the evolution of microbial distribution features in the target area over time, providing a basis for precise control of the ultraviolet disinfection system.

[0043] Figure 2This diagram illustrates the architecture of a dynamic distribution system for microbial spectral sensitivity, clearly showcasing the core process and technical implementation path of the invention. Starting with the construction of microbial feature vectors, the diagram calculates weighted cosine similarity using a precise mathematical model, laying the foundation for subsequent processing. In the microbial spectral sensitivity function generation stage, the invention combines recognition probability with preset spectral sensitivity features and introduces an environmental factor correction mechanism, significantly improving adaptability. The microbial spectral sensitivity distribution map generation module fuses the function with microbial density data through integral calculations to form a static distribution representation. Subsequently, the invention innovatively introduces a parallel computing mechanism to simultaneously process spatial distribution features and microbial response functions, optimizing computational efficiency. In the final dynamic distribution map evolution calculation stage, the invention combines the product of the second-order partial derivative and the diffusion coefficient with the microbial density response function, achieving dynamic updates of the distribution map over time. This effectively captures the spatiotemporal evolution of microbial community distribution characteristics, providing a theoretical basis for precise ultraviolet sterilization.

[0044] In one optional implementation, the weighting coefficients of each frequency band are calculated based on the microbial spectral sensitivity distribution map, and combined with the spatial distribution of the master control device group and the slave control device group, a spectral adjustment command for the ultraviolet germicidal lamp is generated, including: The microbial spectral sensitivity distribution map is discretized within a preset wavelength range to obtain sensitivity distributions for multiple frequency bands; spatial importance weight values ​​are set according to the degree of disinfection importance at different locations within the target area, and the weight coefficient of the corresponding frequency band is calculated by combining the sensitivity distribution of the corresponding frequency band. The irradiance intensity distribution of each ultraviolet sterilization device in the master control device group and the slave control device group is obtained respectively. The power coefficient of each ultraviolet sterilization device is calculated according to its rated power. The total irradiance intensity distribution of the target area is obtained by multiplying the irradiance intensity distribution with the power coefficient and superimposing them. Calculate the integral value of the product of the irradiance intensity distributions of adjacent ultraviolet sterilization devices in the target area, and divide the integral value by the square root of the product of the integral values ​​of the squares of the irradiance intensity distributions of the two ultraviolet sterilization devices in the target area to obtain the complementarity coefficient between the devices. The objective function for spectrum optimization is obtained by multiplying the square of the difference between the ratio of the actual irradiance intensity to the total irradiance intensity distribution in each frequency band and the target spectrum ratio, and then summing the results by multiplying the corresponding frequency band weighting coefficients. Under the constraints that the total power does not exceed the maximum power limit and the wavelength of the frequency band is within the preset range, the spectrum optimization objective function is optimized and solved using the gradient descent algorithm to obtain the spectrum adjustment parameters.

[0045] This invention provides a method for adjusting the spectrum of an ultraviolet (UV) sterilization system based on a microbial spectral sensitivity distribution map. This method analyzes and processes the microbial spectral sensitivity distribution map, and combines this with the spatial distribution characteristics of the UV sterilization equipment to achieve precise spectrum adjustment of the UV sterilization lamps, thereby achieving optimal disinfection results.

[0046] During implementation, the first step is to obtain a spectral sensitivity distribution map of microorganisms within the target area. This map reflects the killing effect of different wavelengths of ultraviolet light on microorganisms. To facilitate calculation and processing, the entire ultraviolet wavelength range (typically 200nm-400nm) is divided into multiple frequency bands, for example, each band can be 5nm long, resulting in 40 discrete frequency bands. For each frequency band, the sensitivity value within the corresponding wavelength range is extracted. For example, for E. coli, the sensitivity value at 254nm is 0.85, and the sensitivity value at 280nm is 0.62.

[0047] Spatial importance weight values ​​are set according to the degree of disinfection importance of different locations within the target area. For example, the sterile area of ​​a hospital operating room can be assigned a weight value of 1.0, while a general area can be assigned a weight value of 0.7. The weight value reflects the disinfection priority of the area, and the value range is usually between 0 and 1. The weight coefficient of that frequency band is obtained by multiplying the spatial importance weight value by the sensitivity distribution of the corresponding frequency band and then integrating the results. For example, if the sensitivity integral value corresponding to the 254nm frequency band is 0.82, combined with the spatial distribution of a weight of 1.0 for important areas and 0.7 for general areas, the comprehensive weight coefficient of that frequency band can be calculated to be 0.89.

[0048] To accurately evaluate the irradiation effect of ultraviolet (UV) sterilization equipment, it is necessary to obtain the irradiation intensity distribution of each UV sterilization device in the master control group and slave control group. The irradiation intensity distribution can usually be obtained through experimental measurement or theoretical model calculation, and is expressed as the UV intensity generated by the device at different spatial locations. For example, the irradiation intensity of a 30W UV lamp at a distance of 1 meter is 100 μW / cm². 2 It drops to 25 μW / cm at 2 meters. 2 The power factor of each device is calculated based on the ratio of its rated power to its standard power. For example, if a device has a rated power of 60W and a standard power of 30W, its power factor is 2.0. The irradiance distribution of each device is multiplied by its power factor, and the results of all devices are superimposed to obtain the total irradiance distribution of the target area.

[0049] To evaluate the synergistic effect between different devices, the integral value of the product of the irradiance distributions of adjacent ultraviolet sterilization devices over the target area is calculated. For example, the irradiance of device A and device B at a certain point is 80 μW / cm². 2 and 60μW / cm 2The product is then 4800 (μW / cm²). 2 ) 2 Integrate this product over the entire target area to obtain the total interaction intensity value. Simultaneously, calculate the integral value of the squared irradiance distribution of each device over the target area; for example, the integral value of device A is 15000 (μW / cm²). 2 ) 2 · m 2 Device B has a power rating of 9000 μW / cm³. 2 ) 2 ·m 2 The complementarity coefficient between devices is obtained by dividing the integral value of the interaction intensity by the square root of the product of the square integral values ​​of the two devices. The value is usually between -1 and 1, and the larger the value, the better the synergy between the devices.

[0050] In terms of spectrum optimization, the ratio of actual irradiance to total irradiance in each frequency band is calculated. For example, the irradiance proportion of the 254nm band is 0.4, while the target spectrum proportion might be 0.5. The square of the difference between this ratio and the target proportion is calculated and multiplied by the weighting coefficient for that frequency band. For example, (0.4-0.5). 2 ×0.89=0.0089. Similar calculations are performed on all frequency bands and summed to obtain the spectrum optimization objective function value. The smaller this value, the closer the actual spectrum distribution is to the ideal target.

[0051] During the optimization process, the total power must not exceed the maximum power limit, such as a system maximum power limit of 500W; simultaneously, the wavelength of each frequency band must be within a preset range, such as 200nm-400nm. A gradient descent algorithm is used to iteratively optimize the objective function, updating the frequency band power allocation in each iteration. For example, initially, the power allocation for the 254nm band is 150W, which is adjusted to 180W after optimization; the 280nm band is adjusted from 100W to 80W. When the change in the objective function value is less than a preset threshold (e.g., 0.001) or the maximum number of iterations (e.g., 500 times) is reached, the algorithm stops and outputs the final spectrum adjustment parameters.

[0052] The final generated spectrum adjustment commands include power allocation schemes for each frequency band, such as 180W for the 254nm band and 80W for the 280nm band. These commands are sent to the control module of the ultraviolet sterilization equipment to achieve precise adjustment of the lamp spectrum, thereby maximizing the sterilization effect while ensuring energy efficiency. In practical applications, this method has been successfully applied to space disinfection in medical settings, improving sterilization efficiency by approximately 35% and reducing energy consumption by 20%.

[0053] In one optional implementation, the sterilization effect of each ultraviolet sterilization device after executing the spectrum adjustment command is monitored in real time, and the sterilization compliance rate is calculated, including: Ultraviolet spectral data of each monitoring point within the target area are collected. The correlation between the ultraviolet spectral data and the target spectral data is calculated to obtain the spectral matching degree. Cell activity data and microbial integrity data of each monitoring point are collected simultaneously to obtain cell activity value and microbial damage value, respectively. The spectrum matching degree is divided by the preset target matching degree to obtain the spectrum matching degree ratio. The cell activity value is divided by the preset standard activity value to obtain the activity ratio. The microbial damage value is divided by the preset allowable damage threshold and the supplementary value is taken to obtain the integrity ratio. The spectrum matching degree ratio, activity ratio and integrity ratio are multiplied together to obtain the local sterilization compliance rate of each monitoring point. The location criticality is set according to the spatial location of each monitoring point in the target area and the disinfection requirements. The location criticality is multiplied by a preset weight adjustment coefficient and the negative value is taken. The negative value is substituted into the exponential function to obtain the exponential term. The spatial importance weight of each monitoring point is obtained according to the exponential term. The spatial importance weight is positively correlated with the location criticality. The local sterilization compliance rate of each monitoring point is multiplied by the spatial importance weight of the corresponding location, and then double-integrated within the spatial coordinate range of the entire target area and integrated over the monitoring time period to obtain a weighted cumulative effect. The spatial importance weight of each monitoring point is triple-integrated within the same spatial and time range to obtain a weight normalization benchmark. The weighted cumulative effect is divided by the weight normalization benchmark to obtain the global sterilization compliance rate, which reflects the sterilization effect of the entire target area.

[0054] In this embodiment, the method for real-time monitoring of the sterilization effect of each ultraviolet sterilization device after executing the spectrum adjustment command and calculating the sterilization compliance rate includes several specific steps.

[0055] The system first collects ultraviolet spectral data from various monitoring points within the target area. In practice, a spectral sensor array can be deployed within the target area; for example, 20 spectral sensors can be evenly distributed within a 100-square-meter medical room. Each sensor can detect the intensity distribution of ultraviolet light in the 200-400 nm wavelength range. The spectral data collected by the system is presented as light intensity values ​​at each wavelength, such as a light intensity of 20 mW / cm² measured at 254 nm. 2 The light intensity measured at a wavelength of 280 nm was 15 mW / cm². 2 The collected ultraviolet spectral data is correlated with the pre-set target spectral data to obtain the spectral matching degree. Specifically, the intensity distribution of the two sets of spectral data can be compared point-to-point; for example, the ideal intensity of the target spectrum at 254 nm is 25 mW / cm². 2 The actual measured value was 20 mW / cm. 2The matching degree at this point is calculated to be 0.8. Combining the matching results of each wavelength point, the overall spectral matching degree is obtained, for example, 0.85.

[0056] Cell viability and microbial integrity data are collected simultaneously at each monitoring point. During implementation, fluorescent labeling technology can be used to detect microbial activity, such as using reactive dyes to detect changes in bacterial membrane potential. The detected values ​​are then converted to standardized cell viability values, for example, 0.3, indicating a 70% reduction in cell viability. Simultaneously, molecular probe technology is used to detect microbial membrane structural integrity, yielding microbial damage values, for example, 0.6, indicating that 60% of the microbial membrane structure is damaged.

[0057] The spectral matching degree is further divided by the preset target matching degree to obtain the spectral matching degree ratio. Assuming the preset target matching degree is 0.9 and the actual matching degree is 0.85, the spectral matching degree ratio is 0.85 / 0.9 = 0.944. Similarly, the cell activity value is divided by the preset standard activity value to obtain the activity ratio. For example, if the preset standard activity value is 0.25 and the actual activity value is 0.3, the activity ratio is 0.25 / 0.3 = 0.833. The microbial damage value is divided by the preset allowable damage threshold and the complement is taken to obtain the integrity ratio. For example, if the preset damage threshold is 0.55 and the actual damage value is 0.6, the integrity ratio is 1 - (0.6 / 0.55) = -0.091, which, after taking the complement, is 0.909. Multiplying the three ratios above, we get the local sterilization compliance rate of the monitoring point, which is 0.944×0.833×0.909=0.714, indicating that the sterilization effect of the monitoring point reaches 71.4% of the target requirement.

[0058] The location criticality is set based on the spatial location and disinfection requirements of each monitoring point within the target area. In practical applications, different areas have different disinfection requirements. For example, the criticality for the operating table area can be set to 0.9, for the general ward area to 0.7, and for the corridor area to 0.5. The location criticality is multiplied by a preset weight adjustment coefficient and the result is negative. For example, if the weight adjustment coefficient is set to 2.5, the calculated value for a certain monitoring point is -0.9 × 2.5 = -2.25. Substituting this negative value into the exponential function yields an exponential value of 9.49. The spatial importance weight of the monitoring point is calculated based on the exponential term. This weight is positively correlated with the location criticality; the larger the value, the more important the location.

[0059] The local sterilization compliance rate at each monitoring point is multiplied by the spatial importance weight of its corresponding location. For example, if the local sterilization compliance rate at a monitoring point in a key area is 0.714 and the spatial importance weight is 9.49, the weighted value is 0.714 × 9.49 = 6.776. Double integration is performed over the entire target area's spatial coordinates. For example, on the xy-plane of the entire medical room, the weighted values ​​of all monitoring points are integrated to obtain the spatial cumulative effect. Then, integration is performed over the monitoring time period. For example, during a 4-hour disinfection process, data is recorded every 10 minutes, and the spatial cumulative effect at these 24 time points is integrated to obtain the spatiotemporally weighted cumulative effect, with a value of, for example, 4500.

[0060] Simultaneously, the spatial importance weights of each monitoring point are triple-integrated over the same spatial and temporal range to obtain a weight normalization benchmark, for example, 5600. Dividing the weighted cumulative effect by the weight normalization benchmark yields the global sterilization compliance rate, reflecting the sterilization effect of the entire target area, i.e., 4500 / 5600 = 0.804, indicating that the sterilization effect of the entire target area reaches 80.4% of the target requirement.

[0061] Using the above method, the system can accurately evaluate the actual sterilization effect of ultraviolet sterilization equipment and perform weighted calculations based on the importance of spatial location to obtain sterilization compliance assessment results that better meet actual needs. This method comprehensively considers spectral matching degree, changes in microbial activity and structural damage degree, as well as the importance differences in spatial distribution. It can provide accurate effect assessments for ultraviolet disinfection in different scenarios, helping to adjust disinfection strategies and equipment parameters, and improve disinfection efficiency and reliability.

[0062] In one optional implementation, energy consumption data of each device in the master control device group and the slave control device group are collected in real time, and the total energy consumption of the device group is calculated in combination with the spatial distribution of the devices, including: The basic energy consumption, radiation energy consumption, and auxiliary system energy consumption of each ultraviolet sterilization device in the main control device group and the slave control device group are collected separately. The basic energy consumption, radiation energy consumption, and auxiliary system energy consumption are added together to obtain the total energy consumption of each ultraviolet sterilization device. The output power and input power of each ultraviolet sterilization device are collected, and the temperature and humidity data of the device's operating environment are acquired simultaneously. The temperature correction coefficient is calculated based on the temperature data, and the humidity correction coefficient is calculated based on the humidity data. The ratio of output power to input power is multiplied by the temperature correction coefficient and the humidity correction coefficient to obtain the dynamic efficiency of each ultraviolet sterilization device. Obtain the spatial coordinates of each ultraviolet sterilization device within the target area, calculate the distance between each ultraviolet sterilization device and the center point of the target area, multiply the distance by a preset attenuation coefficient and take the negative exponent, and then multiply it by the importance index of the location of each ultraviolet sterilization device to obtain the position weight of each ultraviolet sterilization device. Multiply the total energy consumption of each ultraviolet sterilization device in the main control equipment group by the dynamic efficiency and the first equipment weight, respectively. Multiply the total energy consumption of each ultraviolet sterilization device in the slave control equipment group by the dynamic efficiency and the second equipment weight, respectively. Sum the two products to obtain the total energy consumption of the equipment group. Multiply the mutual coupling coefficient of any two UV sterilization devices by their corresponding location weights and collaborative working coefficients, and sum the results. Multiply the summation by the total energy consumption of the device group to obtain the corrected total energy consumption considering spatial distribution.

[0063] This embodiment provides a method for collecting and calculating the energy consumption of an ultraviolet sterilization device. The method collects the energy consumption data of each device in the master control device group and slave control device group in real time, and calculates the total energy consumption of the device group in combination with the spatial distribution of the devices.

[0064] In this embodiment, the energy consumption of the ultraviolet sterilization equipment includes three parts: basic energy consumption, radiation energy consumption, and auxiliary system energy consumption. Basic energy consumption refers to the electrical energy consumed by the equipment in standby mode, typically 5%-10% of the rated power. Radiation energy consumption refers to the energy consumed by the equipment to generate ultraviolet radiation, usually accounting for 70%-85% of the total energy consumption. Auxiliary system energy consumption includes the energy consumed by auxiliary components such as the cooling system and control system, accounting for approximately 10%-20% of the total energy consumption. The system collects these three parts of energy consumption data through power sensors and adds them together to obtain the total energy consumption of each ultraviolet sterilization device. For example, if a certain model of ultraviolet sterilization equipment has a basic energy consumption of 15W, a radiation energy consumption of 120W, and an auxiliary system energy consumption of 25W in operating mode, then the total energy consumption of this equipment is 160W.

[0065] The system also collects the output and input power of each UV sterilization device, as well as the temperature and humidity data of the operating environment. Temperature data is used to calculate the temperature correction factor: 1.0 for an ambient temperature of 25°C; the correction factor decreases by 0.05 for every 10°C increase; and by 0.08 for every 10°C decrease. Humidity data is used to calculate the humidity correction factor: 1.0 for a relative humidity of 60%; the correction factor decreases by 0.03 for every 10% increase; and by 0.02 for every 10% decrease. The system multiplies the ratio of output power to input power by the temperature and humidity correction factors to obtain the dynamic efficiency of each UV sterilization device. For example, if a certain ultraviolet sterilization device has an input power of 200W, an output power of 160W, an ambient temperature of 35℃, and a relative humidity of 70%, then the temperature correction factor is 0.95, the humidity correction factor is 0.97, and the dynamic efficiency of the device is (160 / 200)×0.95×0.97=0.74.

[0066] To calculate the spatial distribution impact of each UV sterilization device, the system obtains the spatial coordinates of each device within the target area and calculates the distance between each device and the center point of the target area. Assuming the target area is a rectangle with the center point coordinates (5, 5, 2.5), and the coordinates of a certain sterilization device are (2, 3, 3), then the distance between this device and the center point is 3.61 meters. The system multiplies this distance by a preset attenuation coefficient (typically 0.2) and takes the negative exponent, resulting in 0.484. This value is then multiplied by the importance index of the device's location (assumed to be 1.2), yielding a location weight of 0.581 for the device.

[0067] After calculating the location weights, the system multiplies the total energy consumption of each UV sterilization device in the main control device group by the dynamic efficiency and the first device weight. The first device weight represents the importance of the main control device in the system and is usually set to a value between 1.0 and 1.5. Similarly, the system multiplies the total energy consumption of each UV sterilization device in the slave control device group by the dynamic efficiency and the second device weight, which is usually a value between 0.7 and 1.0. The system then sums the two products to obtain the total energy consumption of the device group.

[0068] For example, a system includes 2 master control devices and 3 slave control devices. Master control device 1 has a total energy consumption of 160W, a dynamic efficiency of 0.74, a position weight of 0.581, and a first device weight of 1.2. Master control device 2 has a total energy consumption of 180W, a dynamic efficiency of 0.78, a position weight of 0.625, and a first device weight of 1.3. Slave control devices 1, 2, and 3 have total energy consumption of 120W, 130W, and 140W, respectively, dynamic efficiencies of 0.72, 0.75, and 0.73, position weights of 0.53, 0.48, and 0.62, and a second device weight of 0.8 for each. The total energy consumption of the equipment group is calculated to be (160×0.74×0.581×1.2)+(180×0.78×0.625×1.3)+(120×0.72×0.53×0.8)+(130×0.75×0.48×0.8)+(140×0.73×0.62×0.8)=232.4W.

[0069] Considering the potential interactions between ultraviolet sterilization devices, the system introduces a mutual coupling coefficient to represent the energy interaction between any two devices. The typical value range of the mutual coupling coefficient is 0.01-0.1. The coefficient is larger when the two devices are close and have similar operating wavelengths, and smaller otherwise. The system multiplies the mutual coupling coefficient of any two ultraviolet sterilization devices by their corresponding location weights and collaborative working coefficients, sums the results, and multiplies the sum by the total energy consumption of the device group to obtain the corrected total energy consumption considering spatial distribution.

[0070] The collaboration coefficient represents the effectiveness of two devices working together. When the two devices have complementary operating modes, the collaboration coefficient is greater than 1; when the two devices have overlapping functions, the collaboration coefficient is less than 1. In the example above, assuming that the mutual coupling coefficient between each pair of the five devices is 0.05 and the collaboration coefficient is 0.9, the corrected total energy consumption is 232.4 × (1 + 0.05 × (0.581 × 0.625 + 0.581 × 0.53 + 0.581 × 0.48 + 0.581 × 0.62 + 0.625 × 0.53 + 0.625 × 0.48 + 0.625 × 0.62 + 0.53 × 0.48 + 0.53 × 0.62 + 0.48 × 0.62) × 0.9) = 246.8 W.

[0071] Using the above methods, the system can accurately calculate the actual energy consumption of a group of ultraviolet sterilization equipment considering spatial distribution, providing a valid basis for equipment layout optimization and energy consumption management.

[0072] A second aspect of the present invention provides a collaborative control system for a group of ultraviolet sterilization devices, comprising: The first unit is used to acquire the working status information of multiple ultraviolet sterilization devices, calculate the comprehensive performance index of each ultraviolet sterilization device based on the working status information, and divide the ultraviolet sterilization device group into a master control device group and a slave control device group based on a preset threshold. The second unit is used to collect information on the types and density of microorganisms within the coverage area in real time using photoelectric sensors, extract sensitive spectrum information corresponding to different microorganisms from a preset ultraviolet spectrum feature database, and generate a microorganism spectrum sensitivity distribution map of the target area; calculate the weight coefficient of each frequency band based on the microorganism spectrum sensitivity distribution map, and generate a spectrum adjustment command for the ultraviolet germicidal lamps by combining the spatial distribution of the master control device group and the slave control device group, and send the spectrum adjustment command to the corresponding ultraviolet germicidal device; monitor the sterilization effect of each ultraviolet germicidal device after executing the spectrum adjustment command in real time, and calculate the sterilization compliance rate; The third unit is used to collect energy consumption data of each device in the master control device group and the slave control device group in real time, and calculate the total energy consumption of the device group in combination with the spatial distribution of the devices; calculate and generate an energy efficiency score based on the sterilization compliance rate and the total energy consumption, compare the energy efficiency score with the preset target energy efficiency range; and generate energy-saving control instructions for the device group based on the comparison results. The fourth unit is used to combine the spectrum adjustment command and the energy-saving control command to generate a coordinated control command for the ultraviolet sterilization equipment group.

[0073] A third aspect of the present invention provides an electronic device, comprising: processor; Memory used to store processor-executable instructions; The processor is configured to invoke instructions stored in the memory to execute the aforementioned method.

[0074] A fourth aspect of the present invention provides a computer-readable storage medium having stored thereon computer program instructions that, when executed by a processor, implement the aforementioned method.

[0075] This invention can be a method, apparatus, system, and / or computer program product. The computer program product may include a computer-readable storage medium having computer-readable program instructions loaded thereon for performing various aspects of the invention.

[0076] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for coordinated control of a group of ultraviolet sterilization equipment, characterized in that, include: The working status information of multiple ultraviolet sterilization devices is obtained, and the comprehensive performance index of each ultraviolet sterilization device is calculated based on the working status information. The ultraviolet sterilization device group is divided into a master control device group and a slave control device group based on a preset threshold. The system collects information on the types and density of microorganisms within the coverage area in real time using photoelectric sensors. It then extracts the sensitive spectrum information corresponding to different microorganisms from a pre-set ultraviolet spectrum feature database to generate a microbial spectrum sensitivity distribution map of the target area. Based on this map, it calculates the weighting coefficients for each frequency band and, combined with the spatial distribution of the master control device group and the slave control device group, generates a spectrum adjustment command for the ultraviolet germicidal lamps. This command is then sent to the corresponding ultraviolet germicidal devices. The system monitors the sterilization effect of each ultraviolet germicidal device after executing the spectrum adjustment command in real time and calculates the sterilization compliance rate. The system collects energy consumption data of each device in the master control device group and the slave control device group in real time, and calculates the total energy consumption of the device group based on the spatial distribution of the devices; it generates an energy efficiency score based on the sterilization compliance rate and the total energy consumption, and compares the energy efficiency score with a preset target energy efficiency range; it generates energy-saving control instructions for the device group based on the comparison results. The spectrum adjustment command and the energy-saving control command are combined to generate a coordinated control command for the ultraviolet sterilization equipment group.

2. The method according to claim 1, characterized in that, Based on the aforementioned operating status information, the comprehensive performance index of each ultraviolet sterilization device is calculated. Combined with preset thresholds, the ultraviolet sterilization device group is divided into a master control device group and a slave control device group, including: The working status information is used to construct a working status time series matrix according to the time series. Long-term and short-term features are extracted from the working status time series matrix using a temporal convolutional network to obtain a temporal feature vector. The feature weights of each feature component in the temporal feature vector are calculated based on the attention mechanism. The temporal feature vector is then weighted according to the feature weights to obtain a feature fusion value. Calculate the basic performance index of each of the ultraviolet sterilization devices. The basic performance index is the sum of the first weighted value of the ratio of irradiance intensity to rated irradiance intensity and the second weighted value of the remaining life ratio. The remaining life ratio is the ratio of the rated life minus the device operating time to the rated life. The third weighted value of the basic performance index is added to the fourth weighted value of the feature fusion value to obtain the comprehensive performance index of each ultraviolet sterilization device; a grouping threshold is calculated based on the comprehensive performance index of all ultraviolet sterilization devices in the ultraviolet sterilization device group; the master control device group and the slave control device group are divided by comparing the comprehensive performance index with the grouping threshold. Based on the time-series feature vector, the performance change trend of each ultraviolet sterilization device is predicted. When the prediction result shows that the performance of the ultraviolet sterilization device in the slave device group is on the rise, the ultraviolet sterilization device is adjusted to the master device group; when the prediction result shows that the performance of the ultraviolet sterilization device in the master device group is on the fall, the ultraviolet sterilization device is adjusted to the slave device group.

3. The method according to claim 1, characterized in that, The sensitive spectrum information corresponding to different microorganisms is extracted from a pre-set ultraviolet spectrum feature database to generate a microbial spectrum sensitivity distribution map of the target area, including: Based on the microbial species and density information, microbial feature vectors are formed in a preset dimensional order; the product of the microbial feature vectors with each dimension of the feature vectors in the preset feature database is calculated, and the product is multiplied by the feature weight of the corresponding dimension and summed to obtain a weighted sum of products; the square root of the product of the sum of squares of the microbial feature vectors and the sum of squares of the feature vectors in the preset feature database is calculated, and the weighted sum of products is divided by the square root to obtain the weighted cosine similarity; The recognition probability of each microorganism in the target area is determined based on the weighted cosine similarity. The recognition probability of each microorganism is multiplied by the corresponding spectral sensitivity feature stored in the preset feature database, and then multiplied by the environmental factor correction coefficient and summed to obtain the spectral sensitivity function of the microorganism in the target area. The microbial spectral sensitivity function is integrated with the microbial density within the target area within a preset wavelength range to generate a microbial spectral sensitivity distribution map characterizing the distribution features of microorganisms in the target area. Calculate the second partial derivative of the microbial spectral sensitivity distribution map in the spatial dimension, multiply the second partial derivative by the diffusion coefficient, and add it to the response function of the microbial density to obtain the rate of change of the microbial spectral sensitivity distribution map in the time dimension; The microbial spectral sensitivity distribution map is updated based on the rate of change to obtain a dynamic distribution map of the microbial distribution characteristics of the target area over time.

4. The method according to claim 1, characterized in that, Based on the microbial spectral sensitivity distribution map, the weighting coefficients of each frequency band are calculated, and combined with the spatial distribution of the master control device group and the slave control device group, a spectral adjustment command for the ultraviolet germicidal lamp is generated, including: The microbial spectral sensitivity distribution map is discretized within a preset wavelength range to obtain sensitivity distributions for multiple frequency bands; spatial importance weight values ​​are set according to the degree of disinfection importance at different locations within the target area, and the weight coefficient of the corresponding frequency band is calculated by combining the sensitivity distribution of the corresponding frequency band. The irradiance intensity distribution of each ultraviolet sterilization device in the master control device group and the slave control device group is obtained respectively. The power coefficient of each ultraviolet sterilization device is calculated according to its rated power. The total irradiance intensity distribution of the target area is obtained by multiplying the irradiance intensity distribution with the power coefficient and superimposing them. Calculate the integral value of the product of the irradiance intensity distributions of adjacent ultraviolet sterilization devices in the target area, and divide the integral value by the square root of the product of the integral values ​​of the squares of the irradiance intensity distributions of the two ultraviolet sterilization devices in the target area to obtain the complementarity coefficient between the devices. The objective function for spectrum optimization is obtained by multiplying the square of the difference between the ratio of the actual irradiance intensity to the total irradiance intensity distribution in each frequency band and the target spectrum ratio, and then summing the results by multiplying the corresponding frequency band weighting coefficients. Under the constraints of total power not exceeding the maximum power limit and frequency band wavelength within a preset range, the gradient descent algorithm is used to optimize the objective function of the spectrum optimization, yielding spectrum adjustment parameters. Spectrum adjustment commands for the ultraviolet germicidal lamps are then generated based on these parameters.

5. The method according to claim 1, characterized in that, Real-time monitoring of the sterilization effect of each ultraviolet sterilization device after executing the spectrum adjustment command, and calculation of the sterilization compliance rate, including: Ultraviolet spectral data of each monitoring point within the target area are collected. The correlation between the ultraviolet spectral data and the target spectral data is calculated to obtain the spectral matching degree. Cell activity data and microbial integrity data of each monitoring point are collected simultaneously to obtain cell activity value and microbial damage value, respectively. The spectrum matching degree is divided by the preset target matching degree to obtain the spectrum matching degree ratio. The cell activity value is divided by the preset standard activity value to obtain the activity ratio. The microbial damage value is divided by the preset allowable damage threshold and the supplementary value is taken to obtain the integrity ratio. The spectrum matching degree ratio, activity ratio and integrity ratio are multiplied together to obtain the local sterilization compliance rate of each monitoring point. The location criticality is set according to the spatial location of each monitoring point in the target area and the disinfection requirements. The location criticality is multiplied by a preset weight adjustment coefficient and the negative value is taken. The negative value is substituted into the exponential function to obtain the exponential term. The spatial importance weight of each monitoring point is obtained according to the exponential term. The spatial importance weight is positively correlated with the location criticality. The local sterilization compliance rate of each monitoring point is multiplied by the spatial importance weight of the corresponding location, and then double-integrated within the spatial coordinate range of the entire target area and integrated over the monitoring time period to obtain a weighted cumulative effect. The spatial importance weight of each monitoring point is triple-integrated within the same spatial and time range to obtain a weight normalization benchmark. The weighted cumulative effect is divided by the weight normalization benchmark to obtain the global sterilization compliance rate, which reflects the sterilization effect of the entire target area.

6. The method according to claim 1, characterized in that, Real-time collection of energy consumption data from each device in the master control device group and the slave control device group, combined with the spatial distribution of the devices, to calculate the total energy consumption of the device group, including: The basic energy consumption, radiation energy consumption, and auxiliary system energy consumption of each ultraviolet sterilization device in the main control device group and the slave control device group are collected separately. The basic energy consumption, radiation energy consumption, and auxiliary system energy consumption are added together to obtain the total energy consumption of each ultraviolet sterilization device. The output power and input power of each ultraviolet sterilization device are collected, and the temperature and humidity data of the device's operating environment are acquired simultaneously. The temperature correction coefficient is calculated based on the temperature data, and the humidity correction coefficient is calculated based on the humidity data. The ratio of output power to input power is multiplied by the temperature correction coefficient and the humidity correction coefficient to obtain the dynamic efficiency of each ultraviolet sterilization device. Obtain the spatial coordinates of each ultraviolet sterilization device within the target area, calculate the distance between each ultraviolet sterilization device and the center point of the target area, multiply the distance by a preset attenuation coefficient and take the negative exponent, and then multiply it by the importance index of the location of each ultraviolet sterilization device to obtain the position weight of each ultraviolet sterilization device. Multiply the total energy consumption of each ultraviolet sterilization device in the main control equipment group by the dynamic efficiency and the first equipment weight, respectively. Multiply the total energy consumption of each ultraviolet sterilization device in the slave control equipment group by the dynamic efficiency and the second equipment weight, respectively. Sum the two products to obtain the total energy consumption of the equipment group. Multiply the mutual coupling coefficient of any two UV sterilization devices by their corresponding location weights and collaborative working coefficients, and sum the results. Multiply the summation by the total energy consumption of the device group to obtain the corrected total energy consumption considering spatial distribution.

7. A collaborative control system for a group of ultraviolet sterilization equipment, used to implement the method as described in any one of claims 1-6, characterized in that, include: The first unit is used to acquire the working status information of multiple ultraviolet sterilization devices, calculate the comprehensive performance index of each ultraviolet sterilization device based on the working status information, and divide the ultraviolet sterilization device group into a master control device group and a slave control device group based on a preset threshold. The second unit is used to collect information on the types and density of microorganisms within the coverage area in real time using photoelectric sensors, extract sensitive spectrum information corresponding to different microorganisms from a preset ultraviolet spectrum feature database, and generate a microorganism spectrum sensitivity distribution map of the target area; calculate the weight coefficient of each frequency band based on the microorganism spectrum sensitivity distribution map, and generate a spectrum adjustment command for the ultraviolet germicidal lamps by combining the spatial distribution of the master control device group and the slave control device group, and send the spectrum adjustment command to the corresponding ultraviolet germicidal device; monitor the sterilization effect of each ultraviolet germicidal device after executing the spectrum adjustment command in real time, and calculate the sterilization compliance rate; The third unit is used to collect energy consumption data of each device in the master control device group and the slave control device group in real time, and calculate the total energy consumption of the device group in combination with the spatial distribution of the devices; calculate and generate an energy efficiency score based on the sterilization compliance rate and the total energy consumption, compare the energy efficiency score with the preset target energy efficiency range; and generate energy-saving control instructions for the device group based on the comparison results. The fourth unit is used to combine the spectrum adjustment command and the energy-saving control command to generate a coordinated control command for the ultraviolet sterilization equipment group.

8. An electronic device, characterized in that, include: processor; Memory used to store processor-executable instructions; The processor is configured to invoke instructions stored in the memory to execute the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having computer program instructions stored thereon, characterized in that, When the computer program instructions are executed by the processor, they implement the method described in any one of claims 1 to 6.

Images