An intelligent control system and control method for hospital radioactive wastewater decay pool

Abstract

The present invention relates to the technical field of wastewater treatment, and specifically discloses an intelligent control system and control method for a hospital radioactive wastewater decay pool. The control system collects wastewater flow and radioactive substance concentration data in the decay pool in real time, identifies the decay state of the wastewater, and determines whether it has entered a severe decay or mild decay state. In the severe decay state, an early warning signal is generated by calculating the concentration difference between different areas in the decay pool. In the mild decay state, the control system predicts future decay trends through historical data analysis and real-time monitoring, and adjusts control parameters in the decay pool, such as temperature and flow, based on the prediction results, to optimize the decay process of radioactive substances in the wastewater. The present invention also includes the training and application of a machine learning model. By using a comprehensive feature vector of a wastewater flow barrier index and a radioactive substance concentration anomaly index, a support vector machine model is used to judge the future decay state of the decay pool, so as to provide early warning and emergency response.

Description

Technical Field

[0001] The present invention relates to the technical field of wastewater treatment, and in particular to an intelligent control system and a control method for a hospital radioactive wastewater decay pool. Background Art

[0002] With the development of the medical industry, the discharge of radioactive wastewater from hospitals has gradually attracted widespread public attention. Radioactive wastewater, typically derived from wastewater used in medical activities such as radiotherapy and diagnosis, contains various types of radioactive substances. If improperly handled, this wastewater not only pollutes the environment but also poses a serious threat to public health. Therefore, efficient and stable management of hospital radioactive wastewater treatment is crucial. Traditional radioactive wastewater treatment typically relies on manual operation and experience, making it difficult to achieve accurate real-time monitoring and adjustment. This can lead to instability and inefficiency in the treatment process, failing to ensure environmental safety and efficient wastewater treatment.

[0003] The existing technology has the following deficiencies:

[0004] Existing technologies have limitations in real-time monitoring and control of wastewater flow and radioactive material concentrations, making it difficult to achieve a dynamic and precise wastewater treatment process. For example, fluctuations in wastewater flow and changes in radioactive material concentrations are not effectively monitored and analyzed in real time, resulting in an inability to optimize the treatment effect within the decay pool. Furthermore, traditional systems also have errors in predicting wastewater decay trends, failing to promptly detect potential abnormal conditions in the decay pool, leading to inadequate wastewater treatment and increased risk of environmental pollution. Therefore, existing technologies urgently need to innovate in intelligent monitoring, data prediction, and automated control to improve the safety and efficiency of hospital radioactive wastewater treatment. Summary of the Invention

[0005] The purpose of the present invention is to provide an intelligent control system and control method for a hospital radioactive wastewater decay pool to solve the above-mentioned problems.

[0006] The purpose of the present invention can be achieved through the following technical solutions:

[0007] An intelligent control method for a hospital radioactive wastewater decay pool comprises the following steps:

[0008] S1: Real-time collection of wastewater flow and radioactive material concentration data in the hospital's radioactive wastewater decay pool, including the radioactivity intensity of beta rays, gamma rays, and alpha rays;

[0009] S2: Analyze the collected wastewater flow data and radioactive material concentration data, calculate the attenuation degree of radioactive materials in the wastewater, identify the decay state of the wastewater, and determine whether it has entered a severe attenuation state or a mild attenuation state;

[0010] S3: If the wastewater decay state is severe, the concentration difference of each area in the decay pool is calculated by comparing the concentration of radioactive substances in different areas of the decay pool, and an early warning signal is generated based on the difference;

[0011] S4: If the wastewater decay state is slight decay, then through historical data analysis and real-time monitoring of wastewater flow and radioactive material concentration in the decay pool, the wastewater decay degree in the future period is predicted to obtain the future decay trend;

[0012] S5: Based on the predicted decay trend, the control parameters in the decay pool, including temperature and flow, are automatically adjusted to optimize the decay process of radioactive substances in the wastewater.

[0013] As a further solution of the present invention: the identification of the decay state of wastewater specifically includes:

[0014] Obtain wastewater flow data within the monitoring period, and calculate the wastewater flow barrier index based on the degree of wastewater flow fluctuation, which is used to evaluate the impact of wastewater flow on the treatment efficiency of the wastewater decay tank;

[0015] Obtain radioactive material concentration data within the monitoring period, calculate the degree of change in radioactive material concentration in the decay pool, and calculate the radioactive material concentration anomaly index to evaluate the impact of radioactive material concentration on the wastewater decay pool treatment efficiency;

[0016] The wastewater flow barrier index and the radioactive substance concentration anomaly index are normalized and calculated to obtain the wastewater attenuation index, which is used to identify the decay state of the wastewater.

[0017] As a further solution of the present invention: the process of obtaining the wastewater flow barrier index is:

[0018] Obtain wastewater flow time series data from the monitoring period, and perform multi-level decomposition on the wastewater flow time series data to decompose it into low-frequency components and high-frequency components of different scales;

[0019] For each level of high-frequency component decomposed, the fluctuation energy of each level is calculated, and the calculation expression is: ;in, Indicates the Grade quantity, Indicates the coefficients, Indicates the The fluctuation energy of the magnitude component, Indicates the The first high frequency component coefficients, Indicates the total number of data points in the monitoring period;

[0020] Normalize the fluctuation energy at each level to obtain the normalized value of the fluctuation energy at each level. Calculate the ratio of the normalized energy of the highest level high-frequency component to the normalized energy of the lowest level high-frequency component to obtain the wastewater flow barrier index.

[0021] As a further solution of the present invention: the process of obtaining the abnormal index of radioactive substance concentration is as follows:

[0022] Acquire radioactive material concentration data within the monitoring period, divide the data into a three-dimensional data structure based on time points and spatial coordinates, and represent it as a tensor; perform low-rank tensor decomposition on the concentration data tensor, decomposing it into a low-rank tensor and a sparse tensor, where the low-rank tensor represents the normal pattern of the concentration data; the sparse tensor represents the abnormal component of the concentration data, capturing the abnormal part of the concentration change;

[0023] The abnormal concentration contribution at each time point is extracted from the sparse tensor, and the absolute sum of the abnormal values of all spatial coordinates in the tensor is summed to obtain the abnormal concentration contribution at the time point. The abnormal concentration contribution of

[0024] By calculating the mean of the abnormal contributions at all time points, the average concentration change degree within the monitoring period is calculated, and the concentration change degree is ratioed with the overall mean of the concentration data to obtain the radioactive material concentration anomaly index.

[0025] As a further solution of the present invention: the determination of whether the system enters a severe attenuation state or a mild attenuation state specifically includes:

[0026] Determine whether the attenuation index of the wastewater is greater than or equal to a preset threshold. If so, it is recorded as a severe attenuation state; if not, it is recorded as a slight attenuation state.

[0027] As a further solution of the present invention: generating the warning signal specifically includes:

[0028] Obtain radioactive material concentration data for multiple areas of the same area within the decay pool during the monitoring period; calculate the dynamic time warping distance between the concentration series of any two areas;

[0029] The concentration difference coefficient of the decay pool is obtained by calculating the ratio of the mean to the variance of the dynamic time warping distance in different areas of the decay pool;

[0030] Based on the comparison between the calculated concentration difference coefficient and the preset threshold, if the concentration difference coefficient is greater than or equal to the preset threshold, an early warning signal is triggered.

[0031] As a further solution of the present invention, the method of predicting the wastewater attenuation degree within a future period of time to obtain the future decay trend specifically includes:

[0032] The wastewater flow barrier index and radioactive substance concentration anomaly index of the wastewater in the decay pool are obtained, and the wastewater flow barrier index and the radioactive substance concentration anomaly index are constructed into a comprehensive feature vector as the input of the machine learning model. The model is trained with historical data, and the attenuation index is output according to the trained model to judge the degree of attenuation in the future monitoring period. The machine learning model is a support vector machine.

[0033] As a further solution of the present invention: the process of constructing the machine learning model is:

[0034] The wastewater flow barrier index and the radioactive material concentration anomaly index are combined to form a comprehensive feature vector. The support vector machine model is trained using historical data. The input feature is the comprehensive feature vector of each monitoring period, corresponding to the decay state of the decay pool during the monitoring period. The label value is 0 or 1, where 0 indicates a slight decay state and 1 indicates a severe decay state. The training process is as follows:

[0035] Extract the wastewater flow barrier index and radioactive material concentration anomaly index of each period from historical data to construct a training set. Each sample in the training set consists of a comprehensive feature vector and a label.

[0036] Use historical data to train a support vector machine model to classify the state of the decay pool by maximizing the interval between categories. The support vector machine model will automatically adjust the hyperparameters during training to minimize the classification error. The standard loss function of the support vector machine is used for training, the model is cross-validated, and the prediction accuracy is improved by adjusting the hyperparameters.

[0037] As a further solution of the present invention: the control parameters in the decay pool, including temperature and flow rate, are automatically adjusted according to the predicted decay trend to optimize the decay process of radioactive substances in wastewater, specifically including:

[0038] Temperature control: If the decay pool is predicted to be in a mild decay state, the system increases the temperature inside the decay pool to accelerate the decay reaction of the radioactive material; if it is in a severe decay state, the reaction speed is controlled by lowering the temperature;

[0039] Flow control: According to the fluctuation of wastewater flow and the current treatment status of the decay pool, the flow is adjusted to ensure that the wastewater stays in the pool for a longer time so that the radioactive substances can be fully decayed. For flow fluctuations, the flow stability is increased to ensure decay efficiency.

[0040] An intelligent control system for a hospital radioactive wastewater decay pool, comprising:

[0041] A data acquisition module, which collects real-time data on wastewater flow and radioactive material concentration in the hospital's radioactive wastewater decay pool, including the radioactive intensity of beta rays, gamma rays, and alpha rays;

[0042] a decay state identification module, which analyzes the collected wastewater flow data and radioactive substance concentration data, calculates the decay degree of the radioactive substances in the wastewater, identifies the decay state of the wastewater, and determines whether it has entered a severe decay state or a mild decay state;

[0043] An early warning module, which, if the wastewater decay state is severe, compares the radioactive material concentrations in different areas of the decay pool, calculates the concentration differences between the areas within the decay pool, and generates an early warning signal based on the differences;

[0044] A decay prediction module, which predicts the degree of wastewater decay over a period of time in the future and determines the future decay trend if the wastewater decay state is slight decay through historical data analysis and real-time monitoring of wastewater flow and radioactive material concentration in the decay pool;

[0045] The decay control adjustment module automatically adjusts the control parameters in the decay pool, including temperature and flow rate, according to the predicted decay trend, to optimize the decay process of radioactive substances in the wastewater.

[0046] Beneficial effects of the present invention:

[0047] (1) The present invention realizes accurate evaluation and dynamic monitoring of the wastewater decay process in the decay pool by collecting wastewater flow and radioactive substance concentration data in real time and combining it with advanced data analysis technologies such as low-rank tensor decomposition and dynamic time warping algorithm. Specifically, low-rank tensor decomposition technology can efficiently extract normal and abnormal patterns from high-dimensional concentration data, thereby identifying abnormal fluctuations in radioactive substance concentration and timely reflecting the degree of decay of wastewater. The dynamic time warping algorithm captures subtle time series differences by comparing concentration changes in different areas of the decay pool, ensuring high-precision diagnosis of the wastewater decay process. In addition, the present invention adopts a data-driven intelligent control method to automatically adjust the control parameters of the decay pool, such as temperature and flow, based on real-time monitoring data and prediction results, to optimize the decay process of radioactive substances in wastewater. Through this innovative intelligent regulation, the stability and efficiency of the wastewater decay treatment process can be significantly improved, the safety, environmental protection and efficiency of hospital radioactive wastewater treatment can be guaranteed, and the risk of treatment failure or environmental pollution can be avoided.

[0048] (2) The present invention realizes accurate monitoring and optimized management of the hospital's radioactive wastewater decay pool by real-time collection and analysis of wastewater flow and radioactive material concentration data, combined with advanced prediction algorithms and intelligent control systems. The system can dynamically adjust key control parameters in the decay pool, such as temperature and flow, to ensure that the decay process of radioactive materials in the wastewater achieves the best effect. When the operating state of the decay pool is close to severe decay, the system can quickly issue an early warning signal and automatically activate the emergency response mechanism when potential risks arise through early prediction and continuous monitoring. This not only avoids the spread of radioactive contamination that may be caused by the failure of decay pool treatment, but also effectively protects the environment and public safety. Combined with the innovative solution of the present invention, the system's intelligent control capability and automated emergency response greatly improve the safety, reliability and operational efficiency of wastewater treatment, ensuring the stability and controllability of the hospital's radioactive wastewater treatment process in complex environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The present invention will be further described below with reference to the accompanying drawings.

[0050] Figure 1 This is a flowchart of the specific steps of an intelligent control method for a hospital radioactive wastewater decay pool according to the present invention;

[0051] Figure 2 This is a flow chart of an intelligent control system for a hospital radioactive wastewater decay pool in the present invention. DETAILED DESCRIPTION

[0052] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present invention.

[0053] See also Figure 1 As shown, the present invention is an intelligent control method for a hospital radioactive wastewater decay pool, comprising the following steps:

[0054] S1: Real-time collection of wastewater flow and radioactive material concentration data in the hospital's radioactive wastewater decay pool, including the radioactivity intensity of beta rays, gamma rays, and alpha rays;

[0055] S2: Analyze the collected wastewater flow data and radioactive material concentration data, calculate the attenuation degree of radioactive materials in the wastewater, identify the decay state of the wastewater, and determine whether it has entered a severe attenuation state or a mild attenuation state;

[0056] S3: If the wastewater decay state is severe, the concentration difference of each area in the decay pool is calculated by comparing the concentration of radioactive substances in different areas of the decay pool, and an early warning signal is generated based on the difference;

[0057] S4: If the wastewater decay state is slight decay, then through historical data analysis and real-time monitoring of wastewater flow and radioactive material concentration in the decay pool, the wastewater decay degree in the future period is predicted to obtain the future decay trend;

[0058] S5: Based on the predicted decay trend, the control parameters in the decay pool, including temperature and flow, are automatically adjusted to optimize the decay process of radioactive substances in the wastewater.

[0059] In S1, real-time data on wastewater flow and radioactive material concentration in the hospital's radioactive wastewater decay pool is collected, including the radioactivity intensity of beta rays, gamma rays, and alpha rays. Specifically, the following are available:

[0060] Real-time data collection of wastewater flow from the hospital's radioactive wastewater decay pool is performed using a high-precision flow meter. The flow meter uses sensors to monitor changes in wastewater flow in real time, accurately recording the volume of wastewater flowing through the decay pool per unit time. This flow data provides essential information for subsequent evaluation of the decay pool's treatment effectiveness and adjustments to control strategies.

[0061] Real-time data on radioactive material concentrations within the decay pool is collected, specifically measuring the intensities of beta, gamma, and alpha rays using highly sensitive radiation detectors. Beta and alpha ray intensities are typically acquired using scintillation detectors, while gamma ray intensity is precisely measured using a gamma spectrometer. These detectors provide real-time feedback on the intensities of various radiation types within the decay pool, providing critical data for subsequent analysis and dynamic control of the decay pool.

[0062] In S2, the collected wastewater flow data and radioactive material concentration data are analyzed to calculate the attenuation degree of radioactive materials in the wastewater, identify the decay state of the wastewater, and determine whether it has entered a severe attenuation state or a mild attenuation state. Specifically, the following are performed:

[0063] Obtain wastewater flow data within the monitoring period, and calculate the wastewater flow barrier index based on the degree of wastewater flow fluctuation, which is used to evaluate the impact of wastewater flow on the treatment efficiency of the wastewater decay tank;

[0064] Obtain radioactive material concentration data within the monitoring period, calculate the degree of change in radioactive material concentration in the decay pool, and calculate the radioactive material concentration anomaly index to evaluate the impact of radioactive material concentration on the wastewater decay pool treatment efficiency;

[0065] The wastewater flow barrier index and the radioactive substance concentration abnormality index are normalized and calculated to obtain the wastewater attenuation index, which is used to identify the decay state of the wastewater;

[0066] Determine whether the attenuation index of the wastewater is greater than or equal to a preset threshold. If so, it is recorded as a severe attenuation state; if not, it is recorded as a slight attenuation state;

[0067] The process of obtaining the wastewater flow barrier index is as follows:

[0068] Obtain wastewater flow time series data from the monitoring period, perform multi-level decomposition on the data, and decompose it into low-frequency components and high-frequency components of different scales. The high-frequency components obtained from the decomposition are used to characterize the fluctuation characteristics of wastewater flow;

[0069] For the high-frequency components decomposed at each level, the fluctuation energy of each level is calculated to quantify the intensity of wastewater flow fluctuation. The calculation expression is: ;in, Indicates the Grade quantity, Indicates the coefficients, Indicates the The fluctuation energy of the magnitude component, Indicates the The first high frequency component coefficients, Indicates the total number of data points in the monitoring period;

[0070] Normalize the fluctuation energy at each level to obtain the relative contribution rate of fluctuations at each level. The calculation expression is: ;in, Indicates the The normalized value of the level component fluctuation energy, It represents the total number of layers of Haar wavelet decomposition. The wastewater flow barrier index is calculated based on the ratio of the normalized energy of the highest-level high-frequency component to the normalized energy of the lowest-level high-frequency component.

[0071] The process of obtaining the radioactive substance concentration abnormality index is as follows:

[0072] Acquire radioactive material concentration data within a monitoring period, divide the data into a three-dimensional data structure according to time points and spatial coordinates, and represent it as a tensor; perform low-rank tensor decomposition on the concentration data tensor to decompose it into a low-rank tensor and a sparse tensor, wherein the low-rank tensor represents the normal pattern of the concentration data; the sparse tensor represents the abnormal component of the concentration data and captures the abnormal part in the concentration change. The decomposition is based on sparse regularization to constrain the abnormal component and minimize its deviation from the concentration data;

[0073] The abnormal concentration contribution at each time point is extracted from the sparse tensor, and the absolute sum of the abnormal values of all spatial coordinates in the tensor is summed to obtain the abnormal concentration contribution at the time point. The abnormal concentration contribution of is calculated as follows: ;in, Indicates a time point and location The outliers on represents the spatial coordinates, It represents the number of decay pools divided horizontally. It represents the number of decay pools divided along the longitudinal direction. Indicates a time point The abnormal concentration contribution of

[0074] By calculating the abnormal contribution of all time points The average concentration change degree during the monitoring period is calculated, and the concentration change degree is compared with the overall mean of the concentration data to obtain the radioactive substance concentration anomaly index.

[0075] The calculation expression of the attenuation index is: Where, represents the wastewater flow barrier index, Indicates the abnormal concentration index of radioactive substances, and represents the preset scale factor, and and are greater than 0, represents the decay index;

[0076] It should be noted that: since excessive or insufficient wastewater flow may lead to insufficient decay pool treatment or excessive retention time, the wastewater flow barrier index affects the wastewater decay pool treatment efficiency, and the larger the value of the wastewater flow barrier index, the greater the impact of the wastewater flow on the decay pool treatment efficiency, and the larger the value of the radioactive substance concentration anomaly index, the greater the impact of the corresponding radioactive substance concentration on the decay pool treatment efficiency.

[0077] In S3, if the wastewater decay state is severe decay, the concentration difference of each area in the decay pool is calculated by comparing the concentration of radioactive substances in different areas of the decay pool, and an early warning signal is generated according to the difference;

[0078] The radioactive material concentration data for multiple identical areas within the decay pool during the monitoring period are obtained. For any two areas, the dynamic time warping distance (DTW) between their concentration series is calculated. The dynamic time warping metric effectively identifies concentration differences caused by fluctuations occurring at different time points by comparing the patterns of change in the time series. The dynamic time warping algorithm recursively calculates the shortest distance between time series, ensuring that all possible alignments are considered, thereby capturing differences in concentration changes.

[0079] The concentration difference coefficient of the decay pool is obtained by calculating the ratio of the mean to the variance of the dynamic time warping distance in different areas of the decay pool;

[0080] Based on the comparison between the calculated concentration difference coefficient and the preset threshold, if the concentration difference coefficient is greater than or equal to the preset threshold, an early warning signal is triggered.

[0081] In S4, if the wastewater decay state is slight decay, the wastewater decay degree in the future period is predicted through historical data analysis and real-time monitoring of the wastewater flow rate and radioactive material concentration in the decay pool, and the future decay trend is obtained, including:

[0082] Obtain the wastewater flow barrier index and radioactive substance concentration anomaly index of the wastewater in the decay pool, construct the wastewater flow barrier index and radioactive substance concentration anomaly index into a comprehensive feature vector, and use it as the input of the machine learning model. The model is trained with historical data, and based on the trained model, the attenuation index is output to determine the degree of attenuation in the future monitoring period. The machine learning model is a support vector machine, which specifically includes:

[0083] The wastewater flow barrier index and the radioactive material concentration anomaly index are combined to form a comprehensive feature vector. The support vector machine model is trained using historical data. The input feature is the comprehensive feature vector of each monitoring period, corresponding to the decay state of the decay pool during the monitoring period. The label value is 0 or 1, where 0 indicates a slight decay state and 1 indicates a severe decay state. The training process is as follows:

[0084] The wastewater flow barrier index and radioactive material concentration anomaly index for each cycle are extracted from historical data to construct a training set. Each sample in the training set consists of a comprehensive feature vector and a label.

[0085] Use historical data to train a support vector machine model to classify the state of the decay pool by maximizing the interval between categories. The support vector machine model will automatically adjust its hyperparameters during training to minimize the classification error. Use the standard loss function of the support vector machine for training to optimize the model's classification ability. Cross-validate the model to ensure its generalization ability on new data, and improve prediction accuracy by adjusting hyperparameters (such as the penalty parameter C and kernel function parameters).

[0086] After the training is completed, the trained support vector machine model is used to predict the attenuation state in the future monitoring period.

[0087] In S5, based on the predicted decay trend, the control parameters in the decay pool, including temperature and flow, are automatically adjusted to optimize the decay process of radioactive substances in the wastewater. Specifically, the following are included:

[0088] Based on the predicted decay index, the system determines whether the decay pool is in a severe or mild decay state, and automatically adjusts key control parameters (such as temperature and flow) in the decay pool to optimize the decay process of radioactive substances in the wastewater. Specifically, it includes:

[0089] Temperature control: If the decay pool is predicted to be in a mild decay state, the system can moderately increase the temperature inside the decay pool to accelerate the decay reaction of the radioactive material; if it is in a severe decay state, the reaction speed is controlled by lowering the temperature to avoid excessive decay;

[0090] Flow control: Based on the fluctuation of wastewater flow and the current treatment status of the decay pool, the flow rate is adjusted to ensure that the wastewater stays in the pool long enough to fully decay the radioactive substances. In the case of large flow fluctuations, the flow stability is increased to ensure decay efficiency;

[0091] By using sensors to monitor various indicators within the decay pool in real time, including temperature, flow rate, and radioactive material concentration, the system dynamically adjusts its control strategy and optimizes the pool's operating efficiency through closed-loop feedback. Each adjustment is calibrated based on real-time data to ensure optimal attenuation of radioactive materials in the wastewater.

[0092] During the decay state prediction process of the decay pool, if the prediction results indicate that the decay pool is about to reach a critical state of severe decay, the system will automatically issue an early warning signal and trigger an emergency response mechanism based on the early warning to quickly restore the stability of the decay pool by increasing the temperature or flow rate, thereby avoiding potential contamination spread or treatment failure.

[0093] See also Figure 2 As shown, an intelligent control system for a hospital radioactive wastewater decay pool includes:

[0094] A data acquisition module, which collects real-time data on wastewater flow and radioactive material concentration in the hospital's radioactive wastewater decay pool, including the radioactive intensity of beta rays, gamma rays, and alpha rays;

[0095] a decay state identification module, which analyzes the collected wastewater flow data and radioactive substance concentration data, calculates the decay degree of the radioactive substances in the wastewater, identifies the decay state of the wastewater, and determines whether it has entered a severe decay state or a mild decay state;

[0096] An early warning module, which, if the wastewater decay state is severe, compares the radioactive material concentrations in different areas of the decay pool, calculates the concentration differences between the areas within the decay pool, and generates an early warning signal based on the differences;

[0097] A decay prediction module, which predicts the degree of wastewater decay over a period of time in the future and determines the future decay trend if the wastewater decay state is slight decay through historical data analysis and real-time monitoring of wastewater flow and radioactive material concentration in the decay pool;

[0098] The decay control adjustment module automatically adjusts the control parameters in the decay pool, including temperature and flow rate, according to the predicted decay trend, to optimize the decay process of radioactive substances in the wastewater.

[0099] The present invention operates by accurately monitoring and regulating the wastewater decay process through real-time collection of wastewater flow and radioactive material concentration data, combined with advanced data analysis and machine learning techniques. In its implementation, high-precision flow meters and radiation detectors first collect real-time data on wastewater flow and radioactive material concentration in the decay pool, including the intensities of beta, gamma, and alpha rays. Subsequently, methods such as multi-level decomposition and low-rank tensor decomposition are used to calculate the wastewater flow barrier index and radioactive material concentration anomaly index. These two indices are used to assess the impact of wastewater flow and concentration on the decay pool's treatment efficiency. Based on these indices, a decay index is calculated to determine whether the decay pool is in a severe or mild decay state. In the severe decay state, a dynamic time warping algorithm is used to calculate the concentration difference coefficient between different areas within the pool, and a warning signal is generated based on the degree of difference. In the mild decay state, a support vector machine approach is used to predict future decay trends based on historical data and real-time monitoring data. The control parameters of the decay pool, including temperature and flow rate, are then adjusted to optimize the decay process of radioactive materials in the wastewater. Temperature control can be adjusted to accelerate or slow the decay reaction, depending on the decay state. Flow control ensures that the wastewater remains in the decay pool for a sufficient period of time to ensure efficient decay. Furthermore, the system is capable of automatically issuing warnings and triggering emergency response mechanisms based on predicted decay states to quickly restore stability within the pool and prevent potential contamination spread or treatment failure. Through a closed-loop feedback mechanism, the system can adjust control strategies in real time to ensure optimal treatment of radioactive wastewater.

[0100] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0101] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via wired or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0102] It should be understood that the term "and / or" as used herein simply describes a relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A alone, A and B together, or B alone. A and B can be singular or plural. Furthermore, the character " / " as used herein generally indicates an "or" relationship between the associated objects, but it may also indicate an "and / or" relationship. For specific understanding, please refer to the context.

[0103] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0104] The above is a detailed description of an embodiment of the present invention. However, the content described is only a preferred embodiment of the present invention and should not be considered to limit the scope of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. An intelligent control method for a hospital radioactive wastewater decay pool, characterized in that: The following steps are involved: S1: Real-time collection of wastewater flow and radioactive material concentration data in the hospital's radioactive wastewater decay pool, including the radioactivity intensity of beta rays, gamma rays, and alpha rays; S2: Analyze the collected wastewater flow data and radioactive material concentration data, calculate the attenuation degree of radioactive materials in the wastewater, identify the decay state of the wastewater, and determine whether it has entered a severe attenuation state or a mild attenuation state. Specifically, it includes: Obtain wastewater flow data within the monitoring period, and calculate the wastewater flow barrier index based on the degree of wastewater flow fluctuation, which is used to evaluate the impact of wastewater flow on the treatment efficiency of the wastewater decay tank; Obtain radioactive material concentration data within the monitoring period, calculate the degree of change in radioactive material concentration in the decay pool, and calculate the radioactive material concentration anomaly index to evaluate the impact of radioactive material concentration on the wastewater decay pool treatment efficiency; The wastewater flow barrier index and the radioactive substance concentration abnormality index are normalized and calculated to obtain the wastewater attenuation index, which is used to identify the decay state of the wastewater; The process of obtaining the wastewater flow barrier index is as follows: Obtain wastewater flow time series data from the monitoring period, and perform multi-level decomposition on the wastewater flow time series data to decompose it into low-frequency components and high-frequency components of different scales; For each level of high-frequency component decomposed, the fluctuation energy of each level is calculated, and the calculation expression is: ;in, Indicates the Grade quantity, Indicates the coefficients, Indicates the The fluctuation energy of the magnitude component, Indicates the The first high frequency component coefficients, Indicates the total number of data points in the monitoring period; Normalize the fluctuation energy at each level to obtain the normalized value of the fluctuation energy at each level, and calculate the ratio of the normalized energy of the highest level high-frequency component to the normalized energy of the lowest level high-frequency component to obtain the wastewater flow barrier index; S3: If the wastewater decay state is severe, the concentration difference of each area in the decay pool is calculated by comparing the concentration of radioactive substances in different areas of the decay pool, and an early warning signal is generated based on the difference; S4: If the wastewater decay state is slight decay, then through historical data analysis and real-time monitoring of wastewater flow and radioactive material concentration in the decay pool, the wastewater decay degree in the future period is predicted to obtain the future decay trend; S5: Based on the predicted decay trend, the control parameters in the decay pool, including temperature and flow, are automatically adjusted to optimize the decay process of radioactive substances in the wastewater.

2. The intelligent control method for a hospital radioactive wastewater decay pool according to claim 1, characterized in that: The process of obtaining the radioactive substance concentration abnormality index is as follows: Acquire radioactive material concentration data within the monitoring period, divide the data into a three-dimensional data structure based on time points and spatial coordinates, and represent it as a tensor; perform low-rank tensor decomposition on the concentration data tensor, decomposing it into a low-rank tensor and a sparse tensor, where the low-rank tensor represents the normal pattern of the concentration data; the sparse tensor represents the abnormal component of the concentration data, capturing the abnormal part of the concentration change; The abnormal concentration contribution at each time point is extracted from the sparse tensor, and the absolute sum of the abnormal values of all spatial coordinates in the tensor is summed to obtain the abnormal concentration contribution at the time point. The abnormal concentration contribution of By calculating the mean of the abnormal contributions at all time points, the average concentration change degree within the monitoring period is calculated, and the concentration change degree is ratioed with the overall mean of the concentration data to obtain the radioactive material concentration anomaly index.

3. The intelligent control method for a hospital radioactive wastewater decay pool according to claim 1, characterized in that: The determination of whether the state has entered a severe attenuation state or a mild attenuation state specifically includes: Determine whether the attenuation index of the wastewater is greater than or equal to a preset threshold. If so, it is recorded as a severe attenuation state; if not, it is recorded as a slight attenuation state.

4. The intelligent control method for a hospital radioactive wastewater decay pool according to claim 1, characterized in that: The generating of the early warning signal specifically includes: Obtain radioactive material concentration data for multiple areas of the same area within the decay pool during the monitoring period; calculate the dynamic time warping distance between the concentration series of any two areas; The concentration difference coefficient of the decay pool is obtained by calculating the ratio of the mean to the variance of the dynamic time warping distance in different areas of the decay pool; Based on the comparison between the calculated concentration difference coefficient and the preset threshold, if the concentration difference coefficient is greater than or equal to the preset threshold, an early warning signal is triggered.

5. The intelligent control method for a hospital radioactive wastewater decay pool according to claim 1, characterized in that: The prediction of wastewater attenuation within a certain period of time in the future and the acquisition of future attenuation trends specifically include: The wastewater flow barrier index and radioactive substance concentration anomaly index of the wastewater in the decay pool are obtained, and the wastewater flow barrier index and the radioactive substance concentration anomaly index are constructed into a comprehensive feature vector as the input of the machine learning model. The model is trained with historical data, and the attenuation index is output according to the trained model to judge the degree of attenuation in the future monitoring period. The machine learning model is a support vector machine.

6. The intelligent control method for a hospital radioactive wastewater decay pool according to claim 5, characterized in that: The process of building the machine learning model is as follows: The wastewater flow barrier index and the radioactive material concentration anomaly index are combined to form a comprehensive feature vector. The support vector machine model is trained using historical data. The input feature is the comprehensive feature vector of each monitoring period, corresponding to the decay state of the decay pool during the monitoring period. The label value is 0 or 1, where 0 indicates a slight decay state and 1 indicates a severe decay state. The training process is as follows: Extract the wastewater flow barrier index and radioactive material concentration anomaly index of each period from historical data to construct a training set. Each sample in the training set consists of a comprehensive feature vector and a label. Use historical data to train a support vector machine model to classify the state of the decay pool by maximizing the interval between categories. The support vector machine model will automatically adjust the hyperparameters during training to minimize the classification error. The standard loss function of the support vector machine is used for training, the model is cross-validated, and the prediction accuracy is improved by adjusting the hyperparameters.

7. The intelligent control method for a hospital radioactive wastewater decay pool according to claim 1, characterized in that: The control parameters in the decay pool, including temperature and flow rate, are automatically adjusted according to the predicted decay trend to optimize the decay process of radioactive substances in the wastewater, specifically including: Temperature control: If the decay pool is predicted to be in a mild decay state, the system increases the temperature inside the decay pool to accelerate the decay reaction of the radioactive material; if it is in a severe decay state, the reaction speed is controlled by lowering the temperature; Flow control: According to the fluctuation of wastewater flow and the current treatment status of the decay pool, the flow is adjusted to ensure that the wastewater stays in the pool for a longer time so that the radioactive substances can be fully decayed. For flow fluctuations, the flow stability is increased to ensure decay efficiency.

8. An intelligent control system for a hospital radioactive wastewater decay pool, characterized in that: A method for intelligently controlling a hospital radioactive wastewater decay pool as claimed in any one of claims 1 to 7, comprising: A data acquisition module, which collects real-time data on wastewater flow and radioactive material concentration in the hospital's radioactive wastewater decay pool, including the radioactive intensity of beta rays, gamma rays, and alpha rays; a decay state identification module, which analyzes the collected wastewater flow data and radioactive substance concentration data, calculates the decay degree of the radioactive substances in the wastewater, identifies the decay state of the wastewater, and determines whether it has entered a severe decay state or a mild decay state; An early warning module, which, if the wastewater decay state is severe, compares the radioactive material concentrations in different areas of the decay pool, calculates the concentration differences between the areas within the decay pool, and generates an early warning signal based on the differences; A decay prediction module, which predicts the degree of wastewater decay over a period of time in the future and determines the future decay trend if the wastewater decay state is slight decay through historical data analysis and real-time monitoring of wastewater flow and radioactive material concentration in the decay pool; The decay control adjustment module automatically adjusts the control parameters in the decay pool, including temperature and flow rate, according to the predicted decay trend, to optimize the decay process of radioactive substances in the wastewater.

Images