Automatic detection method and system based on ATP fluorescence detection

Abstract

The invention provides an automatic detection method and system based on ATP fluorescence detection. The method comprises the following steps: obtaining a to-be-detected sample, and fully and uniformly mixing to generate a mixed solution; detecting the intensity of a fluorescence signal, synchronously collecting and recording a background fluorescence value, eliminating environmental interference noise, improving the signal-to-noise ratio of the signal, and obtaining the optimized change rate of the intensity of the fluorescence signal; performing prediction processing on the fluorescence signal intensity change rate to generate an initial concentration prediction value of ATP in the to-be-detected sample, effectively correcting detection deviation caused by reagent batch difference at the same time, and generating a corrected initial concentration prediction value; a dynamic range expansion algorithm is implemented, fluorescence detection parameters are automatically adjusted, and a final optimized detection result is obtained; and after the detection is completed, protecting a final optimized detection result, sending the result to a cloud server, and generating a comprehensive biological safety monitoring report. According to the technical scheme provided by the invention, the overall performance and reliability of ATP fluorescence detection are improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of biological detection technology, and in particular to an automated detection method and system based on ATP fluorescence detection. Background Art

[0002] In the fields of food safety, environmental monitoring, and medical diagnosis, it is crucial to quickly and accurately detect the level of microbial contamination. Adenosine triphosphate (ATP) is the energy carrier of all living cells, and its concentration can indirectly reflect the activity of microorganisms in the sample.

[0003] There are many handheld or laboratory-level detection devices on the market that are designed based on the ATP fluorescence principle. These devices usually use disposable swabs or test tubes to collect samples, and generate fluorescent signals through the pre-installed enzymatic reaction reagents and ATP in the sample, and then use photoelectric sensors to measure the fluorescence intensity to deduce the ATP content. Some advanced models also integrate functions such as automated sampling and data processing software to simplify the operation process and improve analysis efficiency.

[0004] Although existing solutions have met basic testing needs to a certain extent, they still face some challenges: Especially under low ATP concentration conditions, traditional methods are difficult to ensure sufficient detection accuracy. External factors such as light and temperature changes may interfere with test results, resulting in poor repeatability. Differences in reagents between different batches may cause deviations in test results, requiring frequent manual corrections. When encountering extremely high or low concentration samples, existing testing equipment often cannot provide accurate results. Lack of support from advanced data analysis tools makes it difficult to achieve automated trend analysis and abnormal warning functions.

[0005] In summary, this application proposes a new generation of ATP fluorescence detection solution based on microfluidics technology and machine learning algorithm optimization, aiming to overcome current technical limitations and provide faster, more accurate and stable services. Summary of the invention

[0006] The embodiments of the present application provide an automated detection method and system based on ATP fluorescence detection, which are used to solve the problems of low overall performance and reliability of ATP fluorescence detection in the prior art.

[0007] In a first aspect, the present application provides an automated detection method based on ATP fluorescence detection, comprising:

[0008] Obtaining a sample to be tested, controlling the flow speed and direction of the liquid on the microfluidic chip, and fully and evenly mixing the sample to be tested with the premixed fluorescently labeled ATP detection reagent to generate a mixed solution;

[0009] Based on the mixed solution, a high-sensitivity photomultiplier tube is used to detect the fluorescence signal intensity at a specific wavelength, and the background fluorescence value is synchronously collected and recorded. The environmental interference noise is eliminated by applying digital signal processing technology to the collected signal to improve the signal-to-noise ratio, and the optimized fluorescence signal intensity change rate is obtained;

[0010] The optimized fluorescence signal intensity change rate is analyzed by using an adaptive threshold algorithm, and the fluorescence signal intensity change rate is predicted and processed in combination with a machine learning model trained based on a large amount of historical detection data, so as to generate a preliminary concentration prediction value of ATP in the sample to be tested, and at the same time, the detection deviation caused by the difference in reagent batches is effectively corrected to generate a corrected preliminary concentration prediction value;

[0011] According to the corrected preliminary concentration prediction value, a dynamic range expansion algorithm is implemented to automatically adjust the fluorescence detection parameters to adapt to the ATP detection requirements within different concentration ranges, re-detect and optimize the fluorescence signal, and obtain the final optimized detection result to ensure that the detection accuracy is not limited by the change in sample concentration;

[0012] After the test is completed, the final optimized test results are protected and the encrypted data is sent to the cloud server through a secure wireless communication protocol to achieve real-time monitoring, trend prediction and abnormal alarm functions, and generate a comprehensive biosafety monitoring report.

[0013] Optionally, the optimized fluorescence signal intensity change rate is analyzed by using an adaptive threshold algorithm, and a machine learning model trained based on a large amount of historical detection data is combined to predict the fluorescence signal intensity change rate, generate a preliminary concentration prediction value of ATP in the sample to be tested, and effectively correct the detection deviation caused by the difference in reagent batches to generate a corrected preliminary concentration prediction value, including:

[0014] Using the optimized fluorescence signal, performing time series analysis on the optimized fluorescence signal, extracting the trend characteristics of the fluorescence signal changing over time, and obtaining time series data of the fluorescence signal intensity change rate;

[0015] Based on the time series data of the fluorescence signal intensity change rate, an adaptive threshold algorithm is applied to dynamically set the threshold to distinguish the effective change part from the noise part in the signal, and obtain the fluorescence signal intensity change rate of the effective change part;

[0016] Combined with a machine learning model trained based on a large amount of historical detection data, the fluorescence signal intensity change rate of the effective change part is predicted and processed to generate a preliminary concentration prediction value of ATP in the sample to be tested;

[0017] In the machine learning model, based on the differences in fluorescence response characteristics between different reagent batches in historical data, the preliminary concentration prediction value of ATP in the sample to be tested is corrected to generate a corrected preliminary concentration prediction value, so as to reduce the impact of reagent batch differences on the test results and improve the accuracy and consistency of the test results.

[0018] Optionally, the method of applying an adaptive threshold algorithm based on the time series data of the fluorescence signal intensity change rate to dynamically set a threshold to distinguish between an effective change part and a noise part in the signal to obtain the fluorescence signal intensity change rate of the effective change part includes:

[0019] Using the time series data of the fluorescence signal intensity change rate, calculating the statistical characteristics of the time series data of the fluorescence signal intensity change rate, including the mean and the standard deviation, to obtain basic parameters;

[0020] According to the basic parameters, an adaptive threshold algorithm is applied to dynamically calculate the threshold of each time point to obtain a dynamic threshold, wherein the threshold of each time point can be adjusted with the fluctuation of the time series data to adaptively identify the effective change part and the noise part in the signal;

[0021] Based on the dynamically calculated threshold value at each time point, the time series data of the fluorescence signal intensity change rate is screened and processed, and data points below the threshold value are removed, and the data points below the threshold value are considered to belong to the noise part, so as to obtain the fluorescence signal intensity change rate after preliminary screening;

[0022] Data points higher than or equal to the dynamic threshold are retained, and it is considered that the data points retained higher than or equal to the dynamic threshold represent the effective change part in the signal, and the fluorescence signal intensity change rate of the effective change part is generated from the fluorescence signal intensity change rate after the preliminary screening.

[0023] Optionally, the method of applying an adaptive threshold algorithm based on the time series data of the fluorescence signal intensity change rate to dynamically set a threshold to distinguish between an effective change part and a noise part in the signal to obtain the fluorescence signal intensity change rate of the effective change part includes:

[0024] Using the time series data of the fluorescence signal intensity change rate, calculate the local statistical characteristics of the time series data of the fluorescence signal intensity change rate in the time window [t-Δt, t+Δt], including the local mean μ loc (t) and the local standard deviation σ loc (t), get the local basic parameters;

[0025] According to the local basic parameter μ loc (t) and σ loc(t), combined with the global statistical characteristics μ and σ, and considering the different importance of different time points in time series data, an adaptive threshold algorithm is applied, and the time weight factor w(t) and the nonlinear adjustment factor f(x) are introduced to dynamically calculate the threshold T(t) of each time point t. The threshold of each time point is calculated by the following formula:

[0026] T(t)=f(μ+w(t)·k·(σ loc (t)) α )

[0027] Where T(t) represents the threshold at each time point t, μ represents the global mean, which represents the average value of the fluorescence signal intensity change rate in the entire time series; σ represents the global standard deviation, which represents the degree of fluctuation of the fluorescence signal intensity change rate in the entire time series; k is an adjustable coefficient used to control the sensitivity of the threshold, and α is an adjustable index used to adjust the influence of the local standard deviation on the threshold. is the time weight factor, which is used to reflect the importance of data at different time points. β represents the parameter that controls the rate of change of the weight over time and is adjusted according to actual application requirements. t0 represents the reference time point, which is usually the center point or starting point of the time series. f(x) = x + γ (x-μ) 2 It is a nonlinear function used to increase the nonlinear adjustment ability of the threshold. γ is an adjustable coefficient used to control the degree of nonlinear adjustment. It is adjusted according to the actual application requirements. T(t) can be adjusted with the fluctuation of time series data to adaptively identify the effective change part and the noise part in the signal.

[0028] Based on the dynamically calculated threshold value T(t) at each time point t, the time series data of the fluorescence signal intensity change rate is screened and processed, and data points below the threshold value T(t) are removed, and the data points below the threshold value T(t) are considered to belong to the noise part, thereby obtaining the fluorescence signal intensity change rate after preliminary screening;

[0029] The data points higher than or equal to the dynamic threshold T(t) are retained, and it is considered that the data points retained higher than or equal to the dynamic threshold T(t) represent the effective change part in the signal, and the fluorescence signal intensity change rate of the effective change part is generated from the fluorescence signal intensity change rate after the preliminary screening.

[0030] Optionally, the method implements a dynamic range expansion algorithm based on the corrected preliminary concentration prediction value, automatically adjusts the fluorescence detection parameters to adapt to the ATP detection requirements within different concentration ranges, re-detects and optimizes the fluorescence signal, and obtains the final optimized detection result to ensure that the detection accuracy is not limited by the change in sample concentration, including:

[0031] Using the preliminary concentration prediction value of ATP in the sample to be tested, evaluating the preliminary concentration prediction value to obtain an approximate concentration range of ATP in the sample to be tested;

[0032] Based on the approximate concentration range of ATP in the sample to be tested, a corresponding dynamic range expansion algorithm is selected, and fluorescence detection parameters are selected and adjusted to determine the exposure time and gain setting working parameters suitable for the current concentration range;

[0033] According to the working parameters, the working state of the high-sensitivity photomultiplier tube is automatically adjusted, and the fluorescence signal intensity of the mixed solution is re-detected to obtain the fluorescence signal under the optimized detection conditions;

[0034] Using the fluorescence signal under the optimized detection conditions, digital signal processing technology is performed again to eliminate environmental interference noise, improve the signal-to-noise ratio of the signal, and generate a further optimized fluorescence signal;

[0035] Based on the further optimized fluorescence signal, the adaptive threshold algorithm and machine learning model are applied again to predict the fluorescence signal intensity change rate to generate the final optimized detection result, ensuring that the detection accuracy is not limited by changes in sample concentration.

[0036] Optionally, based on the approximate concentration range of ATP in the sample to be tested, a corresponding dynamic range expansion algorithm is selected, fluorescence detection parameters are selected and adjusted, and working parameters of exposure time and gain setting suitable for the current concentration range are determined, including:

[0037] Using the approximate concentration range of ATP in the sample to be tested, searching the dynamic range extension algorithm library to find the dynamic range extension algorithm that best suits the current concentration range, and generating a selected dynamic range extension algorithm;

[0038] Based on the selected dynamic range extension algorithm, the fluorescence detection parameters are simulated and analyzed to determine the exposure time and gain settings that can provide the best detection performance within the current ATP concentration range, and generate working parameters.

[0039] Optionally, based on the approximate concentration range of ATP in the sample to be tested, a corresponding dynamic range expansion algorithm is selected, fluorescence detection parameters are selected and adjusted, and working parameters of exposure time and gain setting suitable for the current concentration range are determined, including:

[0040] Using the approximate concentration range of ATP in the sample to be tested, C range , ,Search the dynamic range extension algorithm library to find the most suitable dynamic range extension algorithm for the current concentration range, and generate the selected dynamic range extension algorithm;

[0041] Based on the selected dynamic range extension algorithm, the fluorescence detection parameters are simulated and analyzed to determine the exposure time and gain settings that can provide the best detection performance within the current ATP concentration range, and generate working parameters, specifically including:

[0042] Using the approximate concentration range of ATP in the sample to be tested, C range , select the most appropriate algorithm A(C range ), generating a selected dynamic range extension algorithm;

[0043] Based on the selected dynamic range extension algorithm A(C range ), simulate and analyze the fluorescence detection parameters, and calculate the performance index P(E, G) of each parameter combination, where E represents the exposure time and G represents the gain setting;

[0044] The performance index P(E, G) is calculated by the following formula:

[0045]

[0046] Wherein, S(E, G) represents the signal intensity, which is obtained through simulation and reflects the intensity of the fluorescence signal under a given exposure time and gain setting; D(E, G) represents the signal-to-noise ratio, which is obtained through simulation and reflects the signal-to-noise ratio of the fluorescence signal under a given exposure time and gain setting; N(E, G) represents the noise level, which is obtained through simulation and reflects the noise level of the fluorescence signal under a given exposure time and gain setting; T(E, G) represents the detection time, which is obtained through simulation and reflects the time required to complete a detection under a given exposure time and gain setting; w1(C range )、w2(C range )、w3(C range ) and w4(C range ) is a dynamic weight factor used to adjust the ATP concentration range C range Dynamically adjust the impact of different performance indicators according to actual application needs; α(C range ), β(C range ),γ(C range ) and δ(C range ) is an adjustable index used to adjust the ATP concentration range C range Dynamically adjust the nonlinear effects of various performance indicators according to actual application needs;

[0047] The optimization algorithm is used to find the exposure time and gain setting that maximizes the performance index P(E, G) and generate the best working parameters (E opt , G opt );

[0048] Based on the optimal working parameters (E opt , G opt ) to generate the final working parameters, which are used to automatically adjust the working state of the high-sensitivity photomultiplier tube to ensure the best detection performance within the current ATP concentration range.

[0049] Optionally, based on the further optimized fluorescence signal, the adaptive threshold algorithm and the machine learning model are applied again to predict the fluorescence signal intensity change rate to generate a final optimized detection result to ensure that the detection accuracy is not limited by the change in sample concentration, including:

[0050] Using the further optimized fluorescence signal, performing time series analysis and processing, extracting the characteristics of the fluorescence signal changing over time, and obtaining optimized fluorescence signal characteristic data;

[0051] Based on the optimized fluorescence signal characteristic data, an adaptive threshold algorithm is applied again to dynamically set a threshold to distinguish between an effective change part and a noise part in the signal, and obtain a fluorescence signal intensity change rate of the effective change part;

[0052] The fluorescence signal intensity change rate of the effective change part is used as an input feature, and a machine learning model trained based on a large amount of historical detection data is combined to perform prediction processing on the fluorescence signal intensity change rate to generate a predicted value of the final concentration of ATP in the sample to be tested;

[0053] In the machine learning model, based on the differences in fluorescence response characteristics between different reagent batches in historical data, the final concentration prediction value is corrected to generate a corrected final concentration prediction value, so as to reduce the impact of reagent batch differences on the test results and improve the accuracy and consistency of the test results;

[0054] Based on the corrected final concentration prediction value, a final optimized detection result is generated to ensure that the detection result can maintain high accuracy and reliability regardless of how the concentration of ATP in the sample changes.

[0055] Optionally, based on the mixed solution, the fluorescence signal intensity is detected at a specific wavelength using a high-sensitivity photomultiplier tube, the background fluorescence value is synchronously collected and recorded, and the environmental interference noise is eliminated by applying digital signal processing technology to the collected signal to improve the signal-to-noise ratio of the signal to obtain an optimized fluorescence signal intensity change rate, including:

[0056] Using the mixed solution, controlling a high-sensitivity photomultiplier tube to work at a specific wavelength, detecting the fluorescence signal intensity of the mixed solution, and synchronously collecting and recording the background fluorescence value to obtain original fluorescence signal data;

[0057] Based on the raw fluorescence signal data, signal processing is performed to remove environmental interference noise, improve signal clarity, and generate a preliminarily processed fluorescence signal;

[0058] Using the fluorescence signal after the preliminary processing and the background fluorescence value, background fluorescence correction processing is performed to eliminate the influence of the background fluorescence on the signal, thereby obtaining a corrected fluorescence signal;

[0059] Based on the corrected fluorescent signal, the signal quality is further optimized to ensure that the signal-to-noise ratio of the fluorescent signal is optimal, thereby generating an optimized fluorescent signal.

[0060] In a second aspect, the present application provides an automated detection system based on ATP fluorescence detection, comprising:

[0061] An acquisition control module is used to acquire a sample to be tested, control the flow speed and direction of the liquid on the microfluidic chip, and fully and evenly mix the sample to be tested with the premixed fluorescently labeled ATP detection reagent to generate a mixed solution;

[0062] A detection and acquisition module is used to detect the intensity of the fluorescence signal at a specific wavelength based on the mixed solution using a high-sensitivity photomultiplier tube, synchronously collect and record the background fluorescence value, and eliminate environmental interference noise by applying digital signal processing technology to the collected signal to improve the signal-to-noise ratio of the signal, thereby obtaining an optimized fluorescence signal intensity change rate;

[0063] An analysis and prediction module is used to analyze the optimized fluorescence signal intensity change rate using an adaptive threshold algorithm, and to predict the fluorescence signal intensity change rate in combination with a machine learning model trained based on a large amount of historical detection data, thereby generating a preliminary concentration prediction value of ATP in the sample to be tested, and at the same time effectively correcting the detection deviation caused by the difference in reagent batches, thereby generating a corrected preliminary concentration prediction value;

[0064] An adjustment detection module is used to implement a dynamic range expansion algorithm according to the corrected preliminary concentration prediction value, automatically adjust fluorescence detection parameters to adapt to ATP detection requirements within different concentration ranges, re-detect and optimize the fluorescence signal, and obtain a final optimized detection result to ensure that the detection accuracy is not limited by changes in sample concentration;

[0065] The protection generation module is used to protect the final optimized detection results after the detection is completed, and send the encrypted data to the cloud server through a secure wireless communication protocol to achieve real-time monitoring, trend prediction and abnormal alarm functions, and generate a comprehensive biosafety monitoring report.

[0066] In an embodiment of the present application, a sample to be tested is obtained, the flow speed and direction of the liquid on the microfluidic chip are controlled, the sample to be tested and the premixed fluorescent-labeled ATP detection reagent are fully and evenly mixed to generate a mixed solution; based on the mixed solution, a high-sensitivity photomultiplier tube is used to detect the fluorescence signal intensity at a specific wavelength, and the background fluorescence value is synchronously collected and recorded, and the environmental interference noise is eliminated by applying digital signal processing technology to the collected signal to improve the signal-to-noise ratio of the signal, thereby obtaining an optimized fluorescence signal intensity change rate; an adaptive threshold algorithm is used to analyze the optimized fluorescence signal intensity change rate, and the fluorescence signal intensity change rate is predicted in combination with a machine learning model obtained by training based on a large amount of historical detection data. Processing is performed to generate a preliminary concentration prediction value of ATP in the sample to be tested, and at the same time, the detection deviation caused by the difference in reagent batches is effectively corrected to generate a corrected preliminary concentration prediction value; according to the corrected preliminary concentration prediction value, a dynamic range extension algorithm is implemented to automatically adjust the fluorescence detection parameters to adapt to the ATP detection requirements within different concentration ranges, and the fluorescence signal is re-tested and optimized to obtain the final optimized detection result to ensure that the detection accuracy is not limited by the change in sample concentration; after completing the detection, the final optimized detection result is protected, and the encrypted data is sent to the cloud server through a secure wireless communication protocol to realize real-time monitoring, trend prediction and abnormal alarm functions, and generate a comprehensive biosafety monitoring report.

[0067] The technical solution of this application has the following beneficial effects:

[0068] The present application provides an automated method based on ATP fluorescence detection, which significantly improves the sensitivity, accuracy and dynamic range of ATP detection through the combination of microfluidics, high-sensitivity photoelectric detection, digital signal processing and machine learning algorithms. The method can effectively eliminate environmental interference noise, improve the signal-to-noise ratio, and correct the deviation caused by reagent batch differences through adaptive threshold algorithms and machine learning models, ensuring the consistency and accuracy of the test results. In addition, the detection parameters are automatically adjusted through the dynamic range extension algorithm, so that the system can adapt to sample detection within different concentration ranges, thereby ensuring that accurate results can be obtained within a wide range of concentrations. Finally, the encrypted data is sent to the cloud through a secure data transmission protocol, realizing real-time monitoring, trend prediction and abnormal alarm functions, and enhancing the ability of biosafety monitoring.

[0069] Furthermore, the present application further refines the process of analyzing the rate of change of fluorescence signal intensity using an adaptive threshold algorithm and a machine learning model. By performing time series analysis on the optimized fluorescence signal, extracting trend characteristics that change over time, and applying an adaptive threshold algorithm to distinguish between the effective change part and the noise part, the real fluorescence signal change can be more accurately identified. Subsequently, the effective change part is predicted and processed using a machine learning model trained based on a large amount of historical data, which not only generates a preliminary concentration prediction value, but also reduces the impact of the response characteristic differences between different reagent batches through correction processing, greatly improving the accuracy and consistency of the test results. This method enhances the robustness of the system and ensures that a high level of detection accuracy can be maintained even when using different batches of reagents.

[0070] Furthermore, the present application describes the specific steps of implementing dynamic range expansion based on the corrected preliminary concentration prediction value. By evaluating the approximate concentration range of ATP in the sample to be tested, selecting a suitable dynamic range expansion algorithm and adjusting the fluorescence detection parameters, the system can make the best detection configuration for the current concentration range. This dynamic adjustment mechanism allows the device to maintain good detection performance when facing extremely low or extremely high concentration samples, avoiding the problem of decreased detection accuracy caused by traditional fixed parameter settings. After further signal processing and analysis, a more optimized test result is finally obtained, ensuring that no matter how the sample concentration changes, a reliable and accurate ATP concentration measurement value can be obtained. This not only improves the quality of a single test, but also provides a solid foundation for subsequent data analysis.

[0071] These and other aspects of the present application will become more clearly understood in the description of the following embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0073] Figure 1 A flowchart of an automated detection method based on ATP fluorescence detection provided in an embodiment of the present application;

[0074] Figure 2 A schematic diagram of the structure of an automated detection system based on ATP fluorescence detection provided in an embodiment of the present application;

[0075] Figure 3 A schematic diagram of the structure of a computing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0076] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0077] In some of the processes described in the specification and claims of this application and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish between different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.

[0078] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0079] Figure 1 A flowchart of an automated detection method based on ATP fluorescence detection is provided for the present application embodiment, such as Figure 1 As shown, the method includes:

[0080] 101. Obtain a sample to be tested, control the flow speed and direction of the liquid on the microfluidic chip, and fully and evenly mix the sample to be tested with the premixed fluorescently labeled ATP detection reagent to generate a mixed solution;

[0081] In this step, the sample to be tested refers to a liquid sample, such as a water sample, that needs to be tested for ATP fluorescence. Microfluidic chip is a technology platform that can accurately control the flow of trace amounts of liquid. It achieves fine manipulation of liquids through components such as tiny channels, valves, and pumps. Fluorescently labeled ATP detection reagents contain chemical substances that can specifically bind to ATP and emit fluorescent signals.

[0082] First, collect the water sample that needs to be tested for ATP concentration as the sample to be tested. Then, introduce the sample into the microfluidic chip and add the pre-mixed fluorescent-labeled ATP detection reagent. Finally, by adjusting the flow rate and flow direction on the microfluidic chip, ensure that the sample and the reagent are fully and evenly mixed to form a mixed solution, ready for subsequent fluorescence signal detection.

[0083] In this application example, it is assumed that at a water quality monitoring station, staff members take samples from a river or lake and use a specially designed microfluidic chip system. This system automatically completes the sample pretreatment, including mixing with a fluorescently labeled ATP detection reagent, to quickly and accurately assess the level of microbial activity in the water.

[0084] 102. Based on the mixed solution, a high-sensitivity photomultiplier tube is used to detect the fluorescence signal intensity at a specific wavelength, and the background fluorescence value is synchronously collected and recorded. The environmental interference noise is eliminated by applying digital signal processing technology to the collected signal to improve the signal-to-noise ratio of the signal, and the optimized fluorescence signal intensity change rate is obtained;

[0085] In this step, the photomultiplier tube is an extremely sensitive photodetector that can convert the received light signal into an electrical signal and amplify the output. The specific wavelength refers to the specific wavelength of light used to excite the fluorescent marker to emit light. The background fluorescence value is the fluorescence signal caused by environmental factors in the absence of the sample to be tested.

[0086] First, after the mixed liquid enters the detection area, the fluorescent marker in it will emit fluorescence under the specific wavelength of light. Secondly, the high-sensitivity photomultiplier tube is responsible for capturing these fluorescent signals and converting them into quantifiable electrical signals. At the same time, the system will also record the background fluorescence value so that the environmental noise can be removed through digital signal processing technology, the signal-to-noise ratio can be improved, and a clearer fluorescence signal intensity change rate can be obtained.

[0087] In the present application example, after the water sample is initially processed and mixed with the fluorescently labeled ATP detection reagent, it is sent to a closed detection chamber. Here, a specific light source is used to stimulate the fluorescence reaction, and the photomultiplier tube captures the generated fluorescence signal. This process helps the monitoring station to grasp the microbial contamination status of the water in real time, which is particularly important in the water source protection area.

[0088] Optionally, the method in step 102 is based on the mixed solution, using a high-sensitivity photomultiplier tube to detect the fluorescence signal intensity at a specific wavelength, synchronously collecting and recording the background fluorescence value, and applying digital signal processing technology to the collected signal to eliminate environmental interference noise, improve the signal-to-noise ratio of the signal, and obtain an optimized fluorescence signal intensity change rate, including: using the mixed solution, controlling the high-sensitivity photomultiplier tube to work at a specific wavelength, performing fluorescence signal intensity detection on the mixed solution, and synchronously collecting and recording the background fluorescence value to obtain original fluorescence signal data; based on the original fluorescence signal data, performing signal processing to remove environmental interference noise, improve signal clarity, and generate a fluorescent signal after preliminary processing; using the fluorescent signal after preliminary processing and the background fluorescence value, performing background fluorescence correction processing to eliminate the influence of background fluorescence on the signal, and obtain a corrected fluorescent signal; based on the corrected fluorescent signal, further optimizing the signal quality to ensure that the signal-to-noise ratio of the fluorescent signal is optimal, and generating an optimized fluorescent signal.

[0089] In this step, the high-sensitivity photomultiplier tube is a highly sensitive photodetector capable of detecting weak light signals, and is commonly used for fluorescence detection. Specific wavelength refers to the specific wavelength of light used to excite fluorescent markers to emit light. The background fluorescence value is the fluorescence signal caused by environmental factors or the system itself in the absence of the sample to be tested. Digital signal processing technology is a series of technologies used to process and analyze digital signals, such as filtering, noise reduction, etc., to improve signal quality. The signal-to-noise ratio is the ratio of signal intensity to noise intensity. The higher the signal-to-noise ratio, the clearer and more reliable the signal.

[0090] Firstly, the mixed liquid is used to control the high-sensitivity photomultiplier tube to work at a specific wavelength, and the fluorescence signal intensity of the mixed liquid is detected. At the same time, the background fluorescence value is synchronously collected and recorded to obtain the original fluorescence signal data.

[0091] Secondly, based on the original fluorescence signal data, digital signal processing technology is applied to remove environmental interference noise, improve signal clarity, and generate a preliminary processed fluorescence signal.

[0092] Next, the background fluorescence correction process is performed using the fluorescence signal after preliminary processing and the background fluorescence value to eliminate the influence of the background fluorescence on the signal and obtain a corrected fluorescence signal.

[0093] Finally, based on the corrected fluorescence signal, the signal quality is further optimized to ensure that the signal-to-noise ratio of the fluorescence signal reaches the optimal state, generate an optimized fluorescence signal, and provide a high-quality data basis for subsequent analysis.

[0094] In the present application embodiment, it is assumed that in the field of water quality monitoring, such as drinking water safety detection, water samples are collected from the water supply system as samples to be tested. First, the water sample is mixed with a fluorescently labeled ATP detection reagent to form a mixed solution. A high-sensitivity photomultiplier tube is used to detect the fluorescence signal intensity in the mixed solution at a specific wavelength (such as 485nm excitation light), and the background fluorescence value is recorded simultaneously. By digital signal processing technology, such as wavelet transform or Kalman filtering, environmental interference noise is removed to improve the clarity of the signal. Then, the background fluorescence value is used to correct the fluorescence signal to eliminate the influence of background fluorescence on the measurement result. Finally, by further optimizing signal processing, such as using adaptive filtering technology, it is ensured that the signal-to-noise ratio of the fluorescence signal reaches the optimum, thereby obtaining high-quality fluorescence signal data. These data can be used to accurately assess the activity level of microorganisms in the water sample, and then judge the safety of water quality.

[0095] 103. Analyze the optimized fluorescence signal intensity change rate using an adaptive threshold algorithm, and combine it with a machine learning model trained based on a large amount of historical detection data to predict the fluorescence signal intensity change rate, generate a preliminary concentration prediction value of ATP in the sample to be tested, and effectively correct the detection deviation caused by the difference in reagent batches to generate a corrected preliminary concentration prediction value;

[0096] In this step, the adaptive threshold algorithm is a method to dynamically adjust the threshold according to the actual situation to distinguish valid signals from noise. The machine learning model is a predictive model trained based on historical data that can recognize patterns and make predictions.

[0097] First, the adaptive threshold algorithm is used to analyze the optimized fluorescence signal intensity change rate to separate the real signal part. Then, the signal intensity change rate is predicted and processed in combination with the pre-trained machine learning model to generate a preliminary ATP concentration estimate. In addition, considering the possible differences between different batches of reagents, the prediction results are further corrected through the correction mechanism to obtain a more accurate and reliable preliminary concentration prediction value.

[0098] In this application example, it is assumed that during the water quality detection process, the system uses an adaptive threshold algorithm to eliminate non-target signal interference, ensuring the accuracy of ATP concentration measurement. At the same time, with the help of machine learning technology, the system can continuously optimize its prediction ability based on a large amount of past experimental data, and maintain consistent detection accuracy even in the face of different batches of reagents, which is crucial for long-term monitoring of water quality changes.

[0099] Optionally, the step 103 uses an adaptive threshold algorithm to analyze the optimized fluorescence signal intensity change rate, combines with a machine learning model trained based on a large amount of historical detection data, predicts the fluorescence signal intensity change rate, generates a preliminary concentration prediction value of ATP in the sample to be tested, and effectively corrects the detection deviation caused by the difference in reagent batches to generate a corrected preliminary concentration prediction value, including: using the optimized fluorescence signal, performing a time series analysis on the optimized fluorescence signal, extracting the trend characteristics of the fluorescence signal changing over time, and obtaining time series data of the fluorescence signal intensity change rate; based on the time series data of the fluorescence signal intensity change rate, applying an adaptive threshold algorithm to the optimized fluorescence signal intensity change rate. An adaptive threshold algorithm dynamically sets a threshold to distinguish between the effective change part and the noise part in the signal, and obtains the fluorescence signal intensity change rate of the effective change part; combined with a machine learning model trained based on a large amount of historical detection data, the fluorescence signal intensity change rate of the effective change part is predicted and processed to generate a preliminary concentration prediction value of ATP in the sample to be tested; in the machine learning model, based on the differences in fluorescence response characteristics between different reagent batches in the historical data, the preliminary concentration prediction value of ATP in the sample to be tested is corrected and processed to generate a corrected preliminary concentration prediction value, so as to reduce the impact of reagent batch differences on the test results and improve the accuracy and consistency of the test results.

[0100] Optionally, in step 103, the time series data based on the fluorescence signal intensity change rate is subjected to an adaptive threshold algorithm, and a threshold is dynamically set to distinguish between an effective change part and a noise part in the signal, so as to obtain the fluorescence signal intensity change rate of the effective change part, including: using the time series data of the fluorescence signal intensity change rate, calculating the statistical characteristics of the time series data of the fluorescence signal intensity change rate, including a mean and a standard deviation, to obtain basic parameters; applying an adaptive threshold algorithm according to the basic parameters, dynamically calculating the threshold of each time point to obtain a dynamic threshold, wherein the threshold of each time point can be adjusted with the fluctuation of the time series data to adaptively identify the effective change part and the noise part in the signal; based on the dynamically calculated threshold of each time point, the time series data of the fluorescence signal intensity change rate is screened and processed, and data points below the threshold are removed, and the data points below the threshold are considered to belong to the noise part, so as to obtain the fluorescence signal intensity change rate after preliminary screening; retaining data points higher than or equal to the dynamic threshold, and the retained data points higher than or equal to the dynamic threshold are considered to represent the effective change part in the signal, and the fluorescence signal intensity change rate of the effective change part is generated from the fluorescence signal intensity change rate after preliminary screening.

[0101] In this step, the adaptive threshold algorithm is an algorithm that dynamically adjusts the threshold according to the characteristics of the data, and is used to distinguish the effective change part from the noise part in the signal. Time series analysis is the analysis of data that changes over time to extract its trend characteristics. The time series data of the fluorescence signal intensity change rate is a data sequence that records the change of the fluorescence signal intensity over time. The machine learning model is a model trained based on a large amount of historical detection data, which can predict the relationship between the fluorescence signal intensity change rate and the ATP concentration. Reagent batch differences are changes in the fluorescence response characteristics of different batches of reagents due to subtle differences in production conditions, ingredients, etc.

[0102] Firstly, the optimized fluorescence signal is used to perform time series analysis on the fluorescence signal, extract the trend characteristics of the fluorescence signal changing over time, and generate time series data of the fluorescence signal intensity change rate.

[0103] Secondly, based on the time series data of the fluorescence signal intensity change rate, an adaptive threshold algorithm is applied to dynamically set the threshold for each time point by calculating statistical characteristics such as the mean and standard deviation to distinguish the effective change part from the noise part in the signal, and obtain the fluorescence signal intensity change rate of the effective change part.

[0104] Next, combined with the machine learning model trained based on a large amount of historical detection data, the change rate of the fluorescence signal intensity of the effective change part is predicted and processed to generate a preliminary concentration prediction value of ATP in the sample to be tested.

[0105] Finally, in the machine learning model, based on the differences in fluorescence response characteristics between different reagent batches in historical data, the preliminary concentration prediction value of ATP in the sample to be tested is corrected to generate a corrected preliminary concentration prediction value, thereby reducing the impact of reagent batch differences on the test results and improving the accuracy and consistency of the test results.

[0106] In the present application embodiment, it is assumed that in the field of water quality monitoring, such as drinking water safety detection, water samples are collected from the water supply system as samples to be tested. First, a high-sensitivity photomultiplier tube is used to detect the fluorescence signal intensity in the mixed solution at a specific wavelength, and after being optimized by digital signal processing technology, an optimized fluorescence signal is obtained. Then, the optimized fluorescence signal is subjected to time series analysis, and the trend characteristics of the fluorescence signal changing over time are extracted to form the time series data of the fluorescence signal intensity change rate. Using these data, an adaptive threshold algorithm is applied, and the threshold value of each time point is dynamically set by calculating statistical characteristics such as mean and standard deviation, and the fluorescence signal intensity change rate of the effective change part is screened out. Then, combined with a pre-trained machine learning model, the fluorescence signal intensity change rate of the effective change part is predicted, and the preliminary concentration prediction value of ATP in the water sample is generated. Finally, considering the possible differences in fluorescence response characteristics of different batches of reagents, a correction mechanism is introduced in the machine learning model, and the preliminary concentration prediction value of ATP in the sample to be tested is corrected to generate the corrected preliminary concentration prediction value. This ensures that even if different batches of reagents are used, consistent and accurate test results can be obtained, thereby better evaluating the safety of water quality.

[0107] The present application considers that in the automated detection method based on ATP fluorescence detection, in order to distinguish the effective change part from the noise part from the time series data of the fluorescence signal intensity change rate, an adaptive threshold algorithm is used. The algorithm achieves this goal by dynamically calculating the threshold value at each time point. This method can dynamically adjust the threshold value according to the local characteristics and global characteristics of the time series data, thereby more accurately identifying the effective components in the signal.

[0108] Optionally, the step 103, based on the time series data of the fluorescence signal intensity change rate, applies an adaptive threshold algorithm, dynamically sets a threshold to distinguish between an effective change part and a noise part in the signal, and obtains the fluorescence signal intensity change rate of the effective change part, including:

[0109] Using the time series data of the fluorescence signal intensity change rate, calculate the local statistical characteristics of the time series data of the fluorescence signal intensity change rate in the time window [t-Δt, t+Δt], including the local mean μ loc (t) and the local standard deviation σ loc (t), get the local basic parameters;

[0110] According to the local basic parameter μ loc (t) and σ loc(t), combined with the global statistical characteristics μ and σ, and considering the different importance of different time points in time series data, an adaptive threshold algorithm is applied, and the time weight factor w(t) and the nonlinear adjustment factor f(x) are introduced to dynamically calculate the threshold T(t) of each time point t. The threshold of each time point is calculated by the following formula:

[0111] T(t)=f(μ+w(t)·k·(σ loc (t)) α )

[0112] Where T(t) represents the threshold at each time point t, μ represents the global mean, which represents the average value of the fluorescence signal intensity change rate in the entire time series; σ represents the global standard deviation, which represents the degree of fluctuation of the fluorescence signal intensity change rate in the entire time series; k is an adjustable coefficient used to control the sensitivity of the threshold, and α is an adjustable index used to adjust the influence of the local standard deviation on the threshold. is the time weight factor, which is used to reflect the importance of data at different time points. β represents the parameter that controls the rate of change of the weight over time and is adjusted according to actual application requirements. t0 represents the reference time point, which is usually the center point or starting point of the time series. f(x) = x + γ (x-μ) 2 It is a nonlinear function used to increase the nonlinear adjustment ability of the threshold. γ is an adjustable coefficient used to control the degree of nonlinear adjustment. It is adjusted according to the actual application requirements. T(t) can be adjusted with the fluctuation of time series data to adaptively identify the effective change part and the noise part in the signal.

[0113] Based on the dynamically calculated threshold value T(t) at each time point t, the time series data of the fluorescence signal intensity change rate is screened and processed, and data points below the threshold value T(t) are removed, and the data points below the threshold value T(t) are considered to belong to the noise part, thereby obtaining the fluorescence signal intensity change rate after preliminary screening;

[0114] The data points higher than or equal to the dynamic threshold T(t) are retained, and it is considered that the data points retained higher than or equal to the dynamic threshold T(t) represent the effective change part in the signal, and the fluorescence signal intensity change rate of the effective change part is generated from the fluorescence signal intensity change rate after the preliminary screening.

[0115] By calculating the local mean and local standard deviation within the time window, the local characteristics of the data can be better captured. Taking the global mean and standard deviation into consideration ensures that the threshold setting depends not only on local information but also on the overall characteristics of the entire time series. The time weight factor w(t) is introduced to reflect the importance of different time points, so that recent data points have a greater impact on the threshold. The nonlinear function f(x) is used to increase the nonlinear adjustment ability of the threshold, making the threshold more adaptable to the changing trend of the signal.

[0116] The following is a brief introduction to the design reasons of each sub-item of the formula:

[0117] In the threshold formula T(t) at each time point, w(t)·k·(σ loc (t)) α This sub-item dynamically adjusts the threshold to adapt to the importance of the signal at different time points and the local fluctuation characteristics by combining the time weight, adjustable coefficient and the power of the local standard deviation.

[0118] The following is a brief introduction to how to obtain the parameters of the formula:

[0119] Among them, the local mean μ loc (t) and the local standard deviation σ loc (t) is calculated by calculating the data in the time window [t-Δt, t+Δt]. The global mean μ and the global standard deviation σ are calculated by calculating the entire time series data. The adjustable coefficient k and the exponent α are determined based on experiments or historical data analysis. The parameters β and t0 in the time weight factor, β can be set according to actual application requirements, and t0 usually selects the center point or starting point of the time series. The parameter γ in the nonlinear function is determined based on experiments or historical data analysis.

[0120] Suppose there is a set of time series data of the change rate of fluorescence signal intensity, with a length of 100 time points, a time window width Δt=10, a global mean μ=5.0, a global standard deviation σ=2.0, an adjustable coefficient k=2.0, an exponent α=1.5, a parameter β in the time weight factor=0.1, a reference time point t0=50, and a parameter γ in the nonlinear function=0.5.

[0121] Compute the local mean and local standard deviation:

[0122] For each time point t, calculate the local mean μ in the time window [t-10, t+10] loc (t) and the local standard deviation σ loc (t).

[0123] Calculate the time weight factor w(t):

[0124] w(t)=e -0.1|t-50|;

[0125] Calculate the threshold T(t) at each time point:

[0126] T(t)=f(5.0+w(t)·2.0·(σ loc (t)) 1.5 );

[0127] Where f(x) = x + 0.5 (x - 5.0) 2

[0128] Screening Process:

[0129] Data points below the threshold T(t) are removed, and data points above or equal to the threshold T(t) are retained.

[0130] Assume that at time t = 50, the local mean μ loc (50) = 5.5, local standard deviation σ loc (50) = 2.5;

[0131] Assume that at time t = 50, the local mean μ loc (50) = 5.5, local standard deviation σ loc (50) = 2.5;

[0132] Time weight factor w(50) = e -0.1|50-50| =e 0 =1.0

[0133] Threshold T(50) = f(5.0 + 1.0 · 2.0 · (2.5) 1.5 )

[0134] T(50) = f(5.0 + 2.0 2.5 1.5 )

[0135] T(50)=f(5.0+2.0·3.9528)=f(5.0+7.9056)=f(12.9056)

[0136] T(50)=12.9056+0.5·(12.9056-5.0) 2

[0137] T(50)=12.9056+0.5·7.9056 2

[0138] T(50)=12.9056+0.5·62.496

[0139] T(50)=12.9056+31.248

[0140] T(50)=44.1536

[0141] At time point t=50, the calculated threshold value T(50)=44.1536.

[0142] If the change rate of the fluorescence signal intensity at this time point is lower than 44.1536, this part of the data is considered to be noise; if it is higher than or equal to 44.1536, it is considered to be a valid change part.

[0143] By setting such a threshold, noise can be effectively removed and useful signals can be retained, thereby improving the accuracy of subsequent analysis.

[0144] In the field of water quality testing, this threshold setting method can help more accurately identify changes in microbial activity in water samples, thereby assessing the safety and degree of contamination of water quality. For example, in drinking water safety monitoring, this method can more reliably detect microbial contamination in water and ensure the safety of the water supply system.

[0145] 104. According to the corrected preliminary concentration prediction value, a dynamic range expansion algorithm is implemented to automatically adjust the fluorescence detection parameters to adapt to the ATP detection requirements within different concentration ranges, and the fluorescence signal is re-detected and optimized to obtain the final optimized detection result to ensure that the detection accuracy is not limited by the change of sample concentration;

[0146] In this step, the dynamic range extension algorithm is a technology that can automatically adjust the detection parameters to expand the effective measurement range of the detection equipment. Exposure time and gain setting are key parameters that affect the sensitivity of fluorescence signal detection.

[0147] First, based on the preliminary concentration prediction obtained in the previous step, the system determines the approximate concentration range of the current sample. Then, it selects the appropriate dynamic range extension algorithm and adjusts key detection parameters such as exposure time and gain to ensure optimal detection performance. Next, it re-executes the fluorescence signal detection to obtain better data quality and finally obtains accurate ATP concentration measurement results.

[0148] In the example of this application, for water quality detection, the dynamic range extension algorithm allows the system to flexibly respond to water samples with different pollution levels. For example, when dealing with clear water sources with low pollution levels, the system may increase the exposure time to capture weak fluorescence signals; while when dealing with turbid water sources with high pollution levels, the exposure time is appropriately reduced to avoid signal overload. In this way, no matter how the water quality changes, the reliability and accuracy of the test results can be guaranteed.

[0149] Optionally, the method in step 104 implements a dynamic range expansion algorithm based on the corrected preliminary concentration prediction value, automatically adjusts the fluorescence detection parameters to adapt to the ATP detection requirements within different concentration ranges, re-detects and optimizes the fluorescence signal, and obtains the final optimized detection result to ensure that the detection accuracy is not limited by the change in sample concentration, including: using the preliminary concentration prediction value of ATP in the sample to be tested, evaluating the preliminary concentration prediction value to obtain an approximate concentration range of ATP in the sample to be tested; based on the approximate concentration range of ATP in the sample to be tested, selecting a corresponding dynamic range expansion algorithm, selecting and adjusting the fluorescence detection parameters, and determining a suitable concentration range for the sample to be tested. The method comprises the following steps: adjusting the exposure time and gain setting of the previous concentration range; automatically adjusting the working state of the high-sensitivity photomultiplier tube according to the working parameters, re-detecting the fluorescence signal intensity of the mixed solution, and obtaining the fluorescence signal under the optimized detection conditions; using the fluorescence signal under the optimized detection conditions, performing digital signal processing technology again to eliminate environmental interference noise, improve the signal-to-noise ratio of the signal, and generate a further optimized fluorescence signal; based on the further optimized fluorescence signal, applying the adaptive threshold algorithm and the machine learning model again to predict the fluorescence signal intensity change rate, generate the final optimized detection result, and ensure that the detection accuracy is not limited by the change of the sample concentration.

[0150] Optionally, the step 104 selects a corresponding dynamic range extension algorithm based on the approximate concentration range of ATP in the sample to be tested, selects and adjusts the fluorescence detection parameters, and determines the exposure time and gain setting working parameters suitable for the current concentration range, including: using the approximate concentration range of ATP in the sample to be tested, searching the dynamic range extension algorithm library to find the dynamic range extension algorithm that best suits the current concentration range, and generating a selected dynamic range extension algorithm; based on the selected dynamic range extension algorithm, simulating and analyzing the fluorescence detection parameters to determine the exposure time and gain setting that can provide the best detection performance within the current ATP concentration range, and generating the working parameters.

[0151] Optionally, based on the further optimized fluorescence signal in step 104, the adaptive threshold algorithm and the machine learning model are applied again to predict the fluorescence signal intensity change rate to generate a final optimized detection result to ensure that the detection accuracy is not limited by the change in sample concentration, including: using the further optimized fluorescence signal to perform time series analysis and processing to extract the characteristics of the fluorescence signal changing over time to obtain optimized fluorescence signal characteristic data; based on the optimized fluorescence signal characteristic data, the adaptive threshold algorithm is applied again to dynamically set the threshold to distinguish the effective change part from the noise part in the signal to obtain the fluorescence signal intensity change rate of the effective change part; using the effective change part The fluorescence signal intensity change rate is used as an input feature, and combined with a machine learning model trained based on a large amount of historical detection data, the fluorescence signal intensity change rate is predicted and processed to generate a final concentration prediction value of ATP in the sample to be tested; in the machine learning model, based on the differences in fluorescence response characteristics between different reagent batches in the historical data, the final concentration prediction value is corrected to generate a corrected final concentration prediction value, so as to reduce the impact of reagent batch differences on the test results and improve the accuracy and consistency of the test results; based on the corrected final concentration prediction value, the final optimized test result is generated to ensure that no matter how the concentration of ATP in the sample changes, the test result can maintain high accuracy and reliability.

[0152] In this step, the dynamic range extension algorithm is an algorithm that automatically adjusts the detection parameters according to the sample concentration range to ensure that high-quality fluorescence signals can be obtained in different concentration ranges. The exposure time is the length of time the photomultiplier tube collects the fluorescence signal, which affects the signal intensity and signal-to-noise ratio. The gain setting is the multiple of the photomultiplier tube amplifying the signal, which affects the sensitivity and noise level of the signal. The operating parameters refer to the specific parameters used to control the operation of the photomultiplier tube, including exposure time and gain setting.

[0153] First, the preliminary concentration prediction value of ATP in the sample to be tested is used to evaluate the preliminary concentration prediction value to obtain the approximate concentration range of ATP in the sample to be tested.

[0154] Secondly, based on the approximate concentration range of ATP in the sample to be tested, the dynamic range extension algorithm that best suits the current concentration range is searched and selected from the dynamic range extension algorithm library.

[0155] Next, the fluorescence detection parameters are simulated and analyzed through the selected dynamic range expansion algorithm to determine the exposure time and gain settings that can provide the best detection performance and generate working parameters suitable for the current concentration range.

[0156] Furthermore, according to the generated working parameters, the working state of the high-sensitivity photomultiplier tube is automatically adjusted, and the fluorescence signal intensity of the mixed solution is re-detected to obtain the fluorescence signal under the optimized detection conditions.

[0157] Furthermore, by utilizing the fluorescence signal under optimized detection conditions, digital signal processing technology is again applied to eliminate environmental interference noise, improve the signal-to-noise ratio of the signal, and generate a further optimized fluorescence signal.

[0158] Finally, based on the further optimized fluorescence signal, the adaptive threshold algorithm and machine learning model are applied again to predict the rate of change of fluorescence signal intensity and generate the final optimized detection result to ensure that the detection accuracy is not limited by changes in sample concentration.

[0159] In the embodiment of the present application, it is assumed that in the field of water quality monitoring, such as drinking water safety testing, water samples are collected from the water supply system as samples to be tested. First, the approximate concentration range of ATP in the sample to be tested is evaluated using the corrected preliminary concentration prediction value generated in step 103. Based on this approximate concentration range, an algorithm that best suits the current concentration range is selected from the dynamic range extension algorithm library, such as using a high gain and low exposure time setting for a low concentration range, and a low gain and high exposure time setting for a high concentration range.

[0160] Secondly, the fluorescence detection parameters are simulated and analyzed through the selected dynamic range extension algorithm to determine the optimal exposure time and gain settings and generate working parameters. For example, for the low concentration range, a longer exposure time and a higher gain may be selected; while for the high concentration range, a shorter exposure time and a lower gain may be selected.

[0161] Furthermore, these working parameters are used to automatically adjust the working state of the high-sensitivity photomultiplier tube, re-detect the fluorescence signal in the mixed solution, and obtain the fluorescence signal under the optimized detection conditions. Then, digital signal processing technology is used to further remove environmental interference noise, improve the signal-to-noise ratio of the signal, and generate a further optimized fluorescence signal.

[0162] Finally, based on the further optimized fluorescence signal, the adaptive threshold algorithm and the pre-trained machine learning model are applied again to predict the fluorescence signal intensity change rate and generate the final optimized detection result. This ensures that no matter how the ATP concentration in the water sample changes, accurate and reliable detection results can be obtained, thereby better evaluating the safety of water quality.

[0163] The present application takes into account that in the automated detection method based on ATP fluorescence detection, in order to adapt to the ATP detection requirements in different concentration ranges, it is necessary to dynamically adjust the fluorescence detection parameters. By selecting a suitable dynamic range extension algorithm and combining simulation analysis to determine the optimal working parameters, it is possible to ensure that the best detection performance is obtained in different concentration ranges. The performance index P (E, G) is used to comprehensively evaluate the effects of different parameter combinations.

[0164] Optionally, the steps in step 104, based on the approximate concentration range of ATP in the sample to be tested, selecting a corresponding dynamic range extension algorithm, selecting and adjusting fluorescence detection parameters, and determining exposure time and gain setting working parameters suitable for the current concentration range, include:

[0165] Using the approximate concentration range of ATP in the sample to be tested, C range， , searching and processing the dynamic range extension algorithm library, finding the most suitable dynamic range extension algorithm for the current concentration range, and generating the selected dynamic range extension algorithm;

[0166] Based on the selected dynamic range extension algorithm, the fluorescence detection parameters are simulated and analyzed to determine the exposure time and gain settings that can provide the best detection performance within the current ATP concentration range, and generate working parameters, specifically including:

[0167] Using the approximate concentration range of ATP in the sample to be tested, C range , select the most appropriate algorithm A(C range ), generating a selected dynamic range extension algorithm;

[0168] Based on the selected dynamic range extension algorithm A(C range ), simulate and analyze the fluorescence detection parameters, and calculate the performance index P(E, G) of each parameter combination, where E represents the exposure time and G represents the gain setting;

[0169] The performance index P(E, G) is calculated by the following formula:

[0170]

[0171] Wherein, S(E, G) represents the signal intensity, which is obtained through simulation and reflects the intensity of the fluorescence signal under a given exposure time and gain setting; D(E, G) represents the signal-to-noise ratio, which is obtained through simulation and reflects the signal-to-noise ratio of the fluorescence signal under a given exposure time and gain setting; N(E, G) represents the noise level, which is obtained through simulation and reflects the noise level of the fluorescence signal under a given exposure time and gain setting; T(E, G) represents the detection time, which is obtained through simulation and reflects the time required to complete a detection under a given exposure time and gain setting; w1(C range )、w2(C range )、w3(C range ) and w4(C range ) is a dynamic weight factor used to adjust the ATP concentration range C range Dynamically adjust the impact of different performance indicators according to actual application needs; α(C range ), β(C range ),γ(C range ) and δ(C range ) is an adjustable index used to adjust the ATP concentration range C range Dynamically adjust the nonlinear effects of various performance indicators according to actual application needs;

[0172] The optimization algorithm is used to find the exposure time and gain setting that maximizes the performance index P(E, G) and generate the best working parameters (E opt , G opt );

[0173] Based on the optimal working parameters (E opt , G opt ) to generate the final working parameters, which are used to automatically adjust the working state of the high-sensitivity photomultiplier tube to ensure the best detection performance within the current ATP concentration range.

[0174] The performance index P(E, G) comprehensively considers multiple factors such as signal strength, signal-to-noise ratio, noise level and detection time to achieve multi-objective optimization. The dynamic weight factor w1(C range )、w2(C range )、w3(C range ) and w4(C range ), allowing the importance of different performance indicators to be adjusted over a range of ATP concentrations. Using an adjustable exponent α(C range ), β(C range ),γ(C range ) and δ(C range ), so that the performance indicators can better reflect the nonlinear changes of various performance indicators under different concentration ranges.

[0175] The following is a brief introduction to the design reasons of each sub-item of the formula:

[0176] In the performance indicator formula P(E, G), The signal strength S(E, G) in this sub-item is the key indicator of detection sensitivity. High signal strength means that the optical signal can be detected more clearly. By introducing the dynamic weight factor w1(C range ) and an adjustable exponent α(C range ), you can adjust the impact of signal strength on the overall performance indicators; The signal-to-noise ratio D(E, G) in this sub-item reflects the ratio of signal to noise. A high signal-to-noise ratio means a clearer signal, which helps improve detection accuracy. range ) and an adjustable exponent β(C range ), the effect of the signal-to-noise ratio on the overall performance index can be adjusted; The noise level N(E, G) in this sub-item reflects the background noise at a given exposure time and gain setting. A lower noise level helps improve detection accuracy. range ) and an adjustable exponent γ(C range ), the effect of noise level on overall performance indicators can be adjusted; The detection time T(E, G) in this sub-item reflects the time required to complete a detection. Short detection time can improve detection efficiency, especially in application scenarios that require fast response. range ) and an adjustable exponent δ(C range ), the impact of detection time on the overall performance index can be adjusted;

[0177] The following is a brief introduction to how to obtain the parameters of the formula:

[0178] Among them, the signal strength S(E, G), signal-to-noise ratio D(E, G), noise level N(E, G) and detection time T(E, G) are obtained through simulation or experimental data; the dynamic weight factor w1(C range )、w2(C range )、w3(C range ) and w4(C range ): Determined according to actual application requirements and historical data analysis; adjustable index α (C range ), β(C range ),γ(C range ) and δ(C range ): Also determined based on actual application requirements and historical data analysis;

[0179] Assume that there is a group of water samples with a rough ATP concentration range of C range =10 -6 M to 10 -5 M, and has selected a dynamic range extension algorithm A (C range ). The optimal exposure time and gain settings will be calculated by the following steps:

[0180] Dynamic weighting factor:

[0181] w1(C range )=0.5;w2(C range )=0.3;w3(C range )=0.1;w4(C range )=0.1;

[0182] Adjustable index:

[0183] α(C range )=1.5;β(C range )=1.0;γ(C range )=1.2;δ(C range )=1.0;

[0184] The data obtained from the simulation:

[0185] E=100ms, G=1000; S(100,1000)=1000; D(100,1000)=50; N(100,1000)=10; T(100,1000)=0.1s;

[0186] Calculate the performance index P(E, G):

[0187] P(100,1000)=0.5·1000 1.5 +0.3 50 1.0 -0.1 10 1.2 -0.1 0.1 1.0

[0188] P(100,1000)=0.5·1000000+0.3·50-0.1·15.849-0.1·0.1

[0189] P(100,1000)=500000+15-1.5849-0.01

[0190] P(100,1000)=500013.4151

[0191] The optimization algorithm seeks to maximize P(E, G):

[0192] By traversing different exposure time and gain setting combinations, find the E and G values ​​that maximize P(E, G). Assume that after searching with the optimization algorithm, it is found that P(E, G) reaches the maximum value when E=120ms and G=1200.

[0193] Generate optimal operating parameters:

[0194] The best working parameter is E opt =120ms and G opt =1200.

[0195] In the ATP concentration range C range =10 -6 M to 10 -5 M, through the dynamic range expansion algorithm A(C range ) and optimization of performance indicators P(E, G) determined that the optimal exposure time was 120ms and the gain was set to 1200.

[0196] These parameters provide optimal detection performance, including high signal intensity, good signal-to-noise ratio, low noise level, and reasonable detection time.

[0197] By automatically adjusting the working state of the high-sensitivity photomultiplier tube, the best detection performance is ensured within the current ATP concentration range, thereby improving the accuracy and reliability of water quality detection.

[0198] 105. After the test is completed, the final optimized test results are protected, and the encrypted data is sent to the cloud server through a secure wireless communication protocol to achieve real-time monitoring, trend prediction and abnormal alarm functions, and generate a comprehensive biosafety monitoring report.

[0199] In this step, the wireless communication protocol is a standard protocol for data transmission, ensuring the security and reliability of data transmission. The cloud server is a remote server used to store and process data, supporting real-time monitoring, trend prediction and abnormal alarm functions.

[0200] After the test is completed, the final optimized test results are protected and the encrypted data is sent to the cloud server through a secure wireless communication protocol. The cloud server realizes real-time monitoring, trend prediction and abnormal alarm functions, and generates a comprehensive biosafety monitoring report.

[0201] In this application example, in water quality monitoring, after completing the ATP concentration test, the encrypted data is sent to the cloud server through a secure wireless communication protocol. The cloud server can display the test results in real time, perform trend analysis, and issue an alarm when an abnormal situation is found, helping the management department to take timely measures to ensure water quality safety.

[0202] Figure 2A schematic diagram of the structure of an automated detection system based on ATP fluorescence detection is provided for the present application embodiment. Figure 2 As shown, the system includes:

[0203] The acquisition control module 21 is used to acquire the sample to be tested, control the flow speed and direction of the liquid on the microfluidic chip, and fully and evenly mix the sample to be tested with the premixed fluorescently labeled ATP detection reagent to generate a mixed solution;

[0204] The detection and acquisition module 22 is used to detect the fluorescence signal intensity at a specific wavelength based on the mixed solution using a high-sensitivity photomultiplier tube, synchronously collect and record the background fluorescence value, and eliminate environmental interference noise by applying digital signal processing technology to the collected signal to improve the signal-to-noise ratio of the signal, thereby obtaining an optimized fluorescence signal intensity change rate;

[0205] The analysis and prediction module 23 is used to analyze the optimized fluorescence signal intensity change rate by using an adaptive threshold algorithm, and to predict the fluorescence signal intensity change rate in combination with a machine learning model trained based on a large amount of historical detection data, to generate a preliminary concentration prediction value of ATP in the sample to be tested, and to effectively correct the detection deviation caused by the difference in reagent batches, to generate a corrected preliminary concentration prediction value;

[0206] The detection adjustment module 24 is used to implement a dynamic range expansion algorithm according to the corrected preliminary concentration prediction value, automatically adjust the fluorescence detection parameters to meet the ATP detection requirements within different concentration ranges, re-detect and optimize the fluorescence signal, and obtain the final optimized detection result to ensure that the detection accuracy is not limited by the change of sample concentration;

[0207] The protection generation module 25 is used to protect the final optimized detection result after the detection is completed, and send the encrypted data to the cloud server through a secure wireless communication protocol to achieve real-time monitoring, trend prediction and abnormal alarm functions, and generate a comprehensive biosafety monitoring report.

[0208] Figure 2 The automated detection system based on ATP fluorescence detection can perform Figure 1 The implementation principle and technical effect of the automated detection method based on ATP fluorescence detection described in the illustrated embodiment will not be described in detail. The specific manner in which each module and unit performs operations in the automated detection system based on ATP fluorescence detection in the above embodiment has been described in detail in the embodiment of the method, and will not be described in detail here.

[0209] In one possible design, Figure 2 The automated detection system based on ATP fluorescence detection of the embodiment shown can be implemented as a computing device, such as Figure 3As shown, the computing device may include a storage component 31 and a processing component 32;

[0210] The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 32 .

[0211] The processing component 32 is used to: obtain a sample to be tested, control the flow speed and direction of the liquid on the microfluidic chip, and fully and evenly mix the sample to be tested with the premixed fluorescent-labeled ATP detection reagent to generate a mixed solution; based on the mixed solution, use a high-sensitivity photomultiplier tube to detect the intensity of the fluorescence signal at a specific wavelength, synchronously collect and record the background fluorescence value, and eliminate environmental interference noise by applying digital signal processing technology to the collected signal to improve the signal-to-noise ratio of the signal to obtain an optimized fluorescence signal intensity change rate; use an adaptive threshold algorithm to analyze the optimized fluorescence signal intensity change rate, and combine it with a machine learning model trained based on a large amount of historical detection data to perform an optimization on the fluorescence signal intensity change rate. Prediction processing generates a preliminary concentration prediction value of ATP in the sample to be tested, and at the same time effectively corrects the detection deviation caused by the difference in reagent batches to generate a corrected preliminary concentration prediction value; according to the corrected preliminary concentration prediction value, a dynamic range expansion algorithm is implemented to automatically adjust the fluorescence detection parameters to adapt to the ATP detection requirements within different concentration ranges, re-test and optimize the fluorescence signal, and obtain the final optimized detection result to ensure that the detection accuracy is not limited by the change in sample concentration; after the detection is completed, the final optimized detection result is protected, and the encrypted data is sent to the cloud server through a secure wireless communication protocol to realize real-time monitoring, trend prediction and abnormal alarm functions, and generate a comprehensive biosafety monitoring report.

[0212] The processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the above method.

[0213] The storage component 31 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0214] Of course, the computing device may also include other components, such as input / output interfaces, display components, communication components, etc.

[0215] The input / output interface provides an interface between the processing component and the peripheral interface module, which may be an output device, an input device, etc.

[0216] The communication component is configured to facilitate, among other things, wired or wireless communications between the computing device and other devices.

[0217] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. In this case, the computing device can refer to a cloud server, and the above-mentioned processing components, storage components, etc. can be basic server resources rented or purchased from the cloud computing platform.

[0218] The present application also provides a computer storage medium storing a computer program, wherein the computer program can achieve the above-mentioned Figure 1 The illustrated embodiment is an automated detection method based on ATP fluorescence detection.

[0219] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0220] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0221] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0222] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. An automated detection method based on ATP fluorescence detection, characterized in that: include: Obtaining a sample to be tested, controlling the flow speed and direction of the liquid on the microfluidic chip, and fully and evenly mixing the sample to be tested with the premixed fluorescently labeled ATP detection reagent to generate a mixed solution; Based on the mixed solution, a high-sensitivity photomultiplier tube is used to detect the fluorescence signal intensity at a specific wavelength, and the background fluorescence value is synchronously collected and recorded. The environmental interference noise is eliminated by applying digital signal processing technology to the collected signal to improve the signal-to-noise ratio, and the optimized fluorescence signal intensity change rate is obtained; The optimized fluorescence signal intensity change rate is analyzed by using an adaptive threshold algorithm, and the fluorescence signal intensity change rate is predicted and processed in combination with a machine learning model trained based on a large amount of historical detection data, so as to generate a preliminary concentration prediction value of ATP in the sample to be tested, and at the same time, the detection deviation caused by the difference in reagent batches is effectively corrected to generate a corrected preliminary concentration prediction value; According to the corrected preliminary concentration prediction value, a dynamic range expansion algorithm is implemented to automatically adjust the fluorescence detection parameters to adapt to the ATP detection requirements within different concentration ranges, re-detect and optimize the fluorescence signal, and obtain the final optimized detection result to ensure that the detection accuracy is not limited by the change in sample concentration; After the test is completed, the final optimized test results are protected and the encrypted data is sent to the cloud server through a secure wireless communication protocol to achieve real-time monitoring, trend prediction and abnormal alarm functions, and generate a comprehensive biosafety monitoring report.

2. The automated detection method based on ATP fluorescence detection according to claim 1, characterized in that: The method of analyzing the optimized fluorescence signal intensity change rate by using an adaptive threshold algorithm and combining it with a machine learning model trained based on a large amount of historical detection data to predict the fluorescence signal intensity change rate, generate a preliminary concentration prediction value of ATP in the sample to be tested, and effectively correct the detection deviation caused by the difference in reagent batches to generate a corrected preliminary concentration prediction value, including: Using the optimized fluorescence signal, performing time series analysis on the optimized fluorescence signal, extracting the trend characteristics of the fluorescence signal changing over time, and obtaining time series data of the fluorescence signal intensity change rate; Based on the time series data of the fluorescence signal intensity change rate, an adaptive threshold algorithm is applied to dynamically set the threshold to distinguish the effective change part from the noise part in the signal, and obtain the fluorescence signal intensity change rate of the effective change part; Combined with a machine learning model trained based on a large amount of historical detection data, the fluorescence signal intensity change rate of the effective change part is predicted and processed to generate a preliminary concentration prediction value of ATP in the sample to be tested; In the machine learning model, based on the differences in fluorescence response characteristics between different reagent batches in historical data, the preliminary concentration prediction value of ATP in the sample to be tested is corrected to generate a corrected preliminary concentration prediction value, so as to reduce the impact of reagent batch differences on the test results and improve the accuracy and consistency of the test results.

3. The automated detection method based on ATP fluorescence detection according to claim 2, characterized in that: The method of applying an adaptive threshold algorithm based on the time series data of the fluorescence signal intensity change rate to dynamically set a threshold to distinguish the effective change part from the noise part in the signal to obtain the fluorescence signal intensity change rate of the effective change part includes: Using the time series data of the fluorescence signal intensity change rate, calculating the statistical characteristics of the time series data of the fluorescence signal intensity change rate, including the mean and the standard deviation, to obtain basic parameters; According to the basic parameters, an adaptive threshold algorithm is applied to dynamically calculate the threshold of each time point to obtain a dynamic threshold, wherein the threshold of each time point can be adjusted with the fluctuation of the time series data to adaptively identify the effective change part and the noise part in the signal; Based on the dynamically calculated threshold value at each time point, the time series data of the fluorescence signal intensity change rate is screened and processed, and data points below the threshold value are removed, and the data points below the threshold value are considered to belong to the noise part, so as to obtain the fluorescence signal intensity change rate after preliminary screening; Data points higher than or equal to the dynamic threshold are retained, and it is considered that the data points retained higher than or equal to the dynamic threshold represent the effective change part in the signal, and the fluorescence signal intensity change rate of the effective change part is generated from the fluorescence signal intensity change rate after the preliminary screening.

4. The automated detection method based on ATP fluorescence detection according to claim 3, characterized in that: The method of applying an adaptive threshold algorithm based on the time series data of the fluorescence signal intensity change rate to dynamically set a threshold to distinguish the effective change part from the noise part in the signal to obtain the fluorescence signal intensity change rate of the effective change part includes: Using the time series data of the fluorescence signal intensity change rate, calculate the local statistical characteristics of the time series data of the fluorescence signal intensity change rate in the time window [t-Δt, t+Δt], including the local mean μ loc (t) and the local standard deviation σ loc (t), get the local basic parameters; According to the local basic parameter μ loc (t) and σ loc (t), combined with the global statistical characteristics μ and σ, and considering the different importance of different time points in time series data, an adaptive threshold algorithm is applied, and the time weight factor w(t) and the nonlinear adjustment factor f(x) are introduced to dynamically calculate the threshold T(t) of each time point t. The threshold of each time point is calculated by the following formula: T(t)=f(μ+w(t)·k·(σ loc (t)) α ) Where T(t) represents the threshold at each time point t, μ represents the global mean, which represents the average value of the fluorescence signal intensity change rate in the entire time series; σ represents the global standard deviation, which represents the degree of fluctuation of the fluorescence signal intensity change rate in the entire time series; k is an adjustable coefficient used to control the sensitivity of the threshold, and α is an adjustable index used to adjust the influence of the local standard deviation on the threshold. is the time weight factor, which is used to reflect the importance of data at different time points. β represents the parameter that controls the rate of change of the weight over time and is adjusted according to actual application requirements. t0 represents the reference time point, which is usually the center point or starting point of the time series. f(x) = x + γ (x-μ) 2 It is a nonlinear function used to increase the nonlinear adjustment ability of the threshold. γ is an adjustable coefficient used to control the degree of nonlinear adjustment. It is adjusted according to the actual application requirements. T(t) can be adjusted with the fluctuation of time series data to adaptively identify the effective change part and the noise part in the signal. Based on the dynamically calculated threshold value T(t) at each time point t, the time series data of the fluorescence signal intensity change rate is screened and processed, and data points below the threshold value T(t) are removed, and the data points below the threshold value T(t) are considered to belong to the noise part, thereby obtaining the fluorescence signal intensity change rate after preliminary screening; The data points higher than or equal to the dynamic threshold T(t) are retained, and it is considered that the data points retained higher than or equal to the dynamic threshold T(t) represent the effective change part in the signal, and the fluorescence signal intensity change rate of the effective change part is generated from the fluorescence signal intensity change rate after the preliminary screening.

5. The automated detection method based on ATP fluorescence detection according to claim 1, characterized in that: According to the corrected preliminary concentration prediction value, a dynamic range expansion algorithm is implemented to automatically adjust the fluorescence detection parameters to adapt to the ATP detection requirements within different concentration ranges, re-detect and optimize the fluorescence signal, and obtain the final optimized detection result to ensure that the detection accuracy is not limited by the change of sample concentration, including: Using the preliminary concentration prediction value of ATP in the sample to be tested, evaluating the preliminary concentration prediction value to obtain an approximate concentration range of ATP in the sample to be tested; Based on the approximate concentration range of ATP in the sample to be tested, a corresponding dynamic range expansion algorithm is selected, and fluorescence detection parameters are selected and adjusted to determine the exposure time and gain setting working parameters suitable for the current concentration range; According to the working parameters, the working state of the high-sensitivity photomultiplier tube is automatically adjusted, and the fluorescence signal intensity of the mixed solution is re-detected to obtain the fluorescence signal under the optimized detection conditions; Using the fluorescence signal under the optimized detection conditions, digital signal processing technology is performed again to eliminate environmental interference noise, improve the signal-to-noise ratio of the signal, and generate a further optimized fluorescence signal; Based on the further optimized fluorescence signal, the adaptive threshold algorithm and machine learning model are applied again to predict the fluorescence signal intensity change rate to generate the final optimized detection result, ensuring that the detection accuracy is not limited by changes in sample concentration.

6. The automated detection method based on ATP fluorescence detection according to claim 5, characterized in that: The method of selecting a corresponding dynamic range expansion algorithm based on the approximate concentration range of ATP in the sample to be tested, selecting and adjusting the fluorescence detection parameters, and determining the exposure time and gain setting working parameters suitable for the current concentration range includes: Using the approximate concentration range of ATP in the sample to be tested, searching the dynamic range extension algorithm library to find the most suitable dynamic range extension algorithm for the current concentration range, and generating a selected dynamic range extension algorithm; Based on the selected dynamic range extension algorithm, the fluorescence detection parameters are simulated and analyzed to determine the exposure time and gain settings that can provide the best detection performance within the current ATP concentration range, and generate working parameters.

7. The automated detection method based on ATP fluorescence detection according to claim 5, characterized in that: The method of selecting a corresponding dynamic range expansion algorithm based on the approximate concentration range of ATP in the sample to be tested, selecting and adjusting the fluorescence detection parameters, and determining the exposure time and gain setting working parameters suitable for the current concentration range includes: Using the approximate concentration range of ATP in the sample to be tested, C range , searching and processing the dynamic range extension algorithm library, finding the most suitable dynamic range extension algorithm for the current concentration range, and generating the selected dynamic range extension algorithm; Based on the selected dynamic range extension algorithm, the fluorescence detection parameters are simulated and analyzed to determine the exposure time and gain setting that can provide the best detection performance within the current ATP concentration range, and generate working parameters, including: Using the approximate concentration range of ATP in the sample to be tested, C range , select the most appropriate algorithm A(C range ), generating a selected dynamic range extension algorithm; Based on the selected dynamic range extension algorithm A(C range ), simulate and analyze the fluorescence detection parameters, and calculate the performance index P(E, G) of each parameter combination, where E represents the exposure time and G represents the gain setting; The performance index P(E, G) is calculated by the following formula: Wherein, S(E, G) represents the signal intensity, which is obtained through simulation and reflects the intensity of the fluorescence signal under a given exposure time and gain setting; D(E, G) represents the signal-to-noise ratio, which is obtained through simulation and reflects the signal-to-noise ratio of the fluorescence signal under a given exposure time and gain setting; N(E, G) represents the noise level, which is obtained through simulation and reflects the noise level of the fluorescence signal under a given exposure time and gain setting; T(E, G) represents the detection time, which is obtained through simulation and reflects the time required to complete a detection under a given exposure time and gain setting; w1(C range )、w2(C range )、w3(C range ) and w4(C range ) is a dynamic weight factor used to adjust the ATP concentration range C range Dynamically adjust the impact of different performance indicators according to actual application needs; α(C range ), β(C range ),γ(C range ) and δ(C range ) is an adjustable index used to adjust the ATP concentration range C range Dynamically adjust the nonlinear effects of various performance indicators according to actual application needs; The optimization algorithm is used to find the exposure time and gain setting that maximizes the performance index P(E, G) and generate the best working parameters (E opt , G opt ); Based on the optimal working parameters (E opt , G opt ) to generate the final working parameters, which are used to automatically adjust the working state of the high-sensitivity photomultiplier tube to ensure the best detection performance within the current ATP concentration range.

8. The automated detection method based on ATP fluorescence detection according to claim 5, characterized in that: Based on the further optimized fluorescence signal, the adaptive threshold algorithm and the machine learning model are applied again to predict the fluorescence signal intensity change rate to generate the final optimized detection result, ensuring that the detection accuracy is not limited by the change of sample concentration, including: Using the further optimized fluorescence signal, performing time series analysis and processing, extracting the characteristics of the fluorescence signal changing over time, and obtaining optimized fluorescence signal characteristic data; Based on the optimized fluorescence signal characteristic data, an adaptive threshold algorithm is applied again to dynamically set a threshold to distinguish between an effective change part and a noise part in the signal, and obtain a fluorescence signal intensity change rate of the effective change part; The fluorescence signal intensity change rate of the effective change part is used as an input feature, combined with a machine learning model trained based on a large amount of historical detection data, to predict the fluorescence signal intensity change rate and generate a predicted value of the final concentration of ATP in the sample to be tested; In the machine learning model, based on the differences in fluorescence response characteristics between different reagent batches in historical data, the final concentration prediction value is corrected to generate a corrected final concentration prediction value, so as to reduce the impact of reagent batch differences on the test results and improve the accuracy and consistency of the test results; Based on the corrected final concentration prediction value, a final optimized detection result is generated to ensure that the detection result can maintain high accuracy and reliability regardless of how the concentration of ATP in the sample changes.

9. The automated detection method based on ATP fluorescence detection according to claim 1, characterized in that: Based on the mixed solution, the fluorescence signal intensity is detected at a specific wavelength using a high-sensitivity photomultiplier tube, the background fluorescence value is synchronously collected and recorded, and the environmental interference noise is eliminated by applying digital signal processing technology to the collected signal to improve the signal-to-noise ratio of the signal, thereby obtaining an optimized fluorescence signal intensity change rate, including: Using the mixed solution, controlling a high-sensitivity photomultiplier tube to work at a specific wavelength, detecting the fluorescence signal intensity of the mixed solution, and synchronously collecting and recording the background fluorescence value to obtain original fluorescence signal data; Based on the raw fluorescence signal data, signal processing is performed to remove environmental interference noise, improve signal clarity, and generate a preliminarily processed fluorescence signal; Using the fluorescence signal after the preliminary processing and the background fluorescence value, a background fluorescence correction process is performed to eliminate the influence of the background fluorescence on the signal, thereby obtaining a corrected fluorescence signal; Based on the corrected fluorescent signal, the signal quality is further optimized to ensure that the signal-to-noise ratio of the fluorescent signal is optimal, thereby generating an optimized fluorescent signal.

10. An automated detection system based on ATP fluorescence detection, characterized in that: include: An acquisition control module is used to acquire a sample to be tested, control the flow speed and direction of the liquid on the microfluidic chip, and fully and evenly mix the sample to be tested with the premixed fluorescently labeled ATP detection reagent to generate a mixed solution; A detection and acquisition module is used to detect the intensity of the fluorescence signal at a specific wavelength based on the mixed solution using a high-sensitivity photomultiplier tube, synchronously collect and record the background fluorescence value, and eliminate environmental interference noise by applying digital signal processing technology to the collected signal to improve the signal-to-noise ratio of the signal, thereby obtaining an optimized fluorescence signal intensity change rate; An analysis and prediction module is used to analyze the optimized fluorescence signal intensity change rate using an adaptive threshold algorithm, and to predict the fluorescence signal intensity change rate in combination with a machine learning model trained based on a large amount of historical detection data, thereby generating a preliminary concentration prediction value of ATP in the sample to be tested, and at the same time effectively correcting the detection deviation caused by the difference in reagent batches, thereby generating a corrected preliminary concentration prediction value; An adjustment detection module is used to implement a dynamic range expansion algorithm according to the corrected preliminary concentration prediction value, automatically adjust fluorescence detection parameters to adapt to ATP detection requirements within different concentration ranges, re-detect and optimize the fluorescence signal, and obtain a final optimized detection result to ensure that the detection accuracy is not limited by changes in sample concentration; The protection generation module is used to protect the final optimized detection results after the detection is completed, and send the encrypted data to the cloud server through a secure wireless communication protocol to achieve real-time monitoring, trend prediction and abnormal alarm functions, and generate a comprehensive biosafety monitoring report.

Images