Sewage disinfection online monitoring system applied to shelter hospital
Through genetically engineered bacteriophages and multi-parameter sensing technology, combined with deep learning models, the problem of rapid and precise disinfection control in sewage treatment in temporary hospitals has been solved, real-time monitoring and dynamic control have been achieved, ensuring a pathogen inactivation rate of ≥99.99%, and improving data security and emergency response capabilities.
Patent Information
- Application Number
- CN202510880762.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-06-27
- Publication Date
- 2025-10-10
AI Technical Summary
Existing technologies are unable to meet the needs of rapid and accurate disinfection control in sewage treatment in temporary hospitals. Traditional monitoring methods have long detection cycles, complex operations, lack of emergency response mechanisms, insufficient data transmission security and reliability, and cannot meet the strict medical sewage supervision requirements.
By using genetically engineered bacteriophages and multi-parameter sensing technology, combined with deep learning models, real-time monitoring and precise control of the sewage disinfection process can be achieved. Through wireless ad hoc network deployment and safety and compliance interaction modules, the disinfectant dosage is dynamically optimized to ensure a pathogen inactivation rate of ≥99.99%, and stable operation is achieved in complex network environments.
It realizes real-time monitoring and dynamic control of the sewage disinfection process, reduces the use of disinfectants, improves the system's emergency response capabilities and data security, and meets the safety and compliance requirements of the temporary hospital.
Smart Images
Figure CN120761599A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of medical sewage treatment, and particularly relates to a sewage disinfection online monitoring system applied to a shelter hospital. BACKGROUND
[0002] In the field of medical sewage treatment, traditional sewage disinfection monitoring methods mainly rely on chemical analysis and manual sampling detection. For example, residual chlorine concentration detection often uses colorimetric method or electrochemical analysis method, and pathogen detection is through culture method or polymerase chain reaction technology. These methods have problems such as long detection period, complex operation, and inability to reflect the disinfection effect in real time. For temporary medical places such as shelter hospitals, the sewage discharge fluctuates greatly, and the types of pathogens are complex. Traditional monitoring methods are difficult to meet the rapid and accurate disinfection control needs.
[0003] In terms of disinfection control, the common method is to add disinfectants based on fixed dosage or simple flow ratio. This method cannot dynamically adjust the disinfectant dosage according to the sewage quality and pathogen inactivation, which easily leads to waste of disinfectants or incomplete disinfection. Moreover, the traditional system lacks effective emergency handling mechanism. When equipment failure or water quality mutation occurs, it is difficult to take timely measures, which has great safety hazards.
[0004] In terms of data transmission and management, some existing systems use wired network connection, which is complex and inconvenient to move and expand. Although wireless transmission method is applied, the data security and reliability are low, which is easy to be interfered or attacked. At the same time, the traditional system lacks unified data encryption and remote monitoring mechanism, which cannot meet the strict requirements of medical sewage supervision.
[0005] Therefore, how to provide a sewage disinfection online monitoring system applied to a shelter hospital is a problem to be solved by those skilled in the art. SUMMARY
[0006] One object of the present application is to provide a sewage disinfection online monitoring system applied to a shelter hospital. The present application can realize real-time monitoring and precise control of the sewage disinfection process through the cooperative work of multiple modules. The present application can use genetic engineering bacteriophage and multi-parameter sensing technology to obtain the pathogen inactivation rate and various sewage parameters in real time, and dynamically optimize the disinfectant dosage through a deep learning model, thereby ensuring that the pathogen inactivation rate is ≥99.99% while reducing the operating cost.
[0007] According to an embodiment of the present invention, an online monitoring system for sewage disinfection applied to a temporary cabin hospital includes a pathogen inactivation verification module, a multi-parameter perception module, a dynamic decision-making control module, a wireless ad hoc network deployment module, and a safety and compliance interaction module. The pathogen inactivation verification module uses the optical signal generated by the combination of genetically engineered bacteriophages and live pathogens to output a real-time pathogen inactivation rate. The multi-parameter perception module can synchronously collect residual chlorine concentration, sewage flow, pH value, water temperature, and disinfection by-product spectral data. The dynamic decision-making control module can receive the output data of the inactivation verification module and the perception module, and generate disinfectant addition instructions through a deep learning model. The wireless ad hoc network deployment module can provide power and data intercommunication services for each module and support hot-swappable networking. The safety and compliance interaction module can implement data encryption and remote monitoring. The output ends of the pathogen inactivation verification module and the multi-parameter perception module are connected to the input end of the dynamic decision-making control module. The output end of the dynamic decision-making control module is connected to a disinfection execution unit, and all modules are interconnected through the wireless ad hoc network deployment module.
[0008] Furthermore, the pathogen inactivation verification module includes a gene editing unit and an optical conversion unit. The gene editing unit can connect the phage lytic enzyme gene to the fluorescent reporter gene, and the optical conversion unit can convert the fluorescence intensity triggered by the pathogen into an inactivation rate value, and the conversion formula is:
[0009] Inactivation rate = 1-(St / S0)
[0010] Where St is the real-time fluorescence intensity, and S0 is the baseline fluorescence intensity in the absence of disinfectant.
[0011] Furthermore, the multi-parameter sensing module includes a residual chlorine detection unit, a spectral analysis unit and a data fusion unit. The residual chlorine detection unit uses a membrane electrode method to measure the residual chlorine concentration. The spectral analysis unit identifies the characteristic peaks of disinfection by-products through surface-enhanced Raman scattering. The data fusion unit can package the data of each sensor into a time-synchronized structured data packet.
[0012] Furthermore, the dynamic decision-making control module includes an LSTM prediction unit, a reinforcement learning optimization unit and an instruction output unit. The LSTM prediction unit predicts the pathogen inactivation rate in the next 5 minutes based on current sensor data. The reinforcement learning optimization unit can minimize the amount of disinfectant added as the goal and solve the optimal solution that satisfies the inactivation rate ≥ 99.99%. The instruction output unit can convert the optimization result into a 4-20mA control signal and output it to the disinfection execution unit.
[0013] Furthermore, the input data dimensions of the LSTM prediction unit include inactivation rate time series data, residual chlorine concentration change rate, SERS characteristic peak intensity and flow mutation flag.
[0014] Furthermore, the wireless ad hoc network deployment module can automatically assign a network address when a new module is connected, switch to local decision-making mode when the network is disconnected, and use the data cache of the last hour to run the model. Secondly, it can automatically synchronize encrypted data to the cloud after the network is restored.
[0015] Furthermore, the security and compliance interaction module uses the national secret SM4 algorithm to encrypt local stored data during execution, and when the real-time inactivation rate is less than 99.9% or the disinfection by-products exceed the standard, a three-level alarm is triggered. The three-level alarms are local sound and light, text messages, and supervision platform push.
[0016] Furthermore, when the LSTM prediction unit outputs a confidence level less than 90%, the following emergency mechanism is activated:
[0017] Switch to proportional control mode: dosage = reference coefficient × real-time flow rate;
[0018] Activate the standby residual chlorine closed-loop control submodule.
[0019] Furthermore, the security and compliance interaction module can provide a MODBUS-TCP protocol interface for connecting to a third-party PLC system, and the RESTful API supports cloud data subscription, and secondly provides a mini-program alarm information push channel.
[0020] An online monitoring system for sewage disinfection applied to a square cabin hospital comprises the following steps:
[0021] S1, multi-parameter sensing module continuously collects sewage parameters;
[0022] S2, pathogen inactivation verification module outputs the inactivation rate every 5 minutes;
[0023] S3, the dynamic decision control module integrates the data of steps 1-2 to generate a dosing instruction;
[0024] S4, the disinfection execution unit executes the instruction and feedbacks the status;
[0025] S5. The security and compliance interaction module encrypts and transmits data throughout the entire process.
[0026] The beneficial effects of the present invention are:
[0027] 1. The present invention uses genetically engineered bacteriophages and multi-parameter sensing technology to accurately obtain pathogen inactivation rates and various sewage parameters in real time. Combined with a deep learning model, it achieves dynamic optimization control of disinfectant dosage. While ensuring a pathogen inactivation rate of ≥99.99%, it effectively reduces disinfectant usage and saves operating costs.
[0028] 2. The present invention supports hot-swappable networking and local decision-making for network disconnection through the wireless ad hoc network deployment module, ensuring the system's continuous and stable operation in a complex network environment, and further improves the system's ability to cope with emergencies through the emergency mechanism of the dynamic decision-making control module.
[0029] 3. The present invention adopts the national secret algorithm to encrypt data through the security and compliance interaction module, and cooperates with the multi-level alarm mechanism and multiple data interaction interfaces, which not only ensures data security, but also facilitates the integration of the system with other equipment and the remote monitoring and management of users, meeting the safety and compliance requirements of sewage disinfection in the temporary hospital. BRIEF DESCRIPTION OF THE DRAWINGS
[0030] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:
[0031] Figure 1 This is a schematic diagram of the framework structure of an online monitoring system for sewage disinfection applied to a temporary cabin hospital, as proposed by the present invention;
[0032] Figure 2 This is an operation flow chart of an online monitoring system for sewage disinfection applied to a square cabin hospital proposed by the present invention. DETAILED DESCRIPTION
[0033] This invention provides an online monitoring system for wastewater disinfection in temporary hospitals. It addresses the technical challenges of existing wastewater monitoring systems, including delayed pathogen inactivation verification, insufficient multi-parameter coordinated control, weak data security, and insufficient emergency response capabilities. By leveraging multiple modules, the system enables real-time monitoring, dynamic control, and safety and compliance management of the wastewater disinfection process, ensuring that wastewater discharge from temporary hospitals meets discharge standards.
[0034] Example: Provided is an online monitoring system for sewage disinfection applied to a temporary cabin hospital, comprising a pathogen inactivation verification module, a multi-parameter perception module, a dynamic decision-making control module, a wireless ad hoc network deployment module, and a security and compliance interaction module. Each module realizes power supply and data intercommunication through the wireless ad hoc network deployment module, and the output end of the dynamic decision-making control module is connected to the disinfection execution unit.
[0035] In an embodiment of the present application, the pathogen inactivation verification module includes a gene editing unit and an optical conversion unit. The gene editing unit adopts genetic engineering technology. Specifically, the phage lytic enzyme gene and the fluorescent reporter gene are connected by restriction endonucleases and DNA ligases. For example, a specific restriction endonuclease is selected to cut the phage lytic enzyme gene and the fluorescent reporter gene respectively to produce complementary sticky ends, and then the two are connected using DNA ligase to construct a recombinant plasmid. The recombinant plasmid is introduced into the host cell so that the host cell can express the phage lytic enzyme with the fluorescent reporter gene.
[0036] The optical conversion unit uses a highly sensitive fluorescence detection sensor to collect, in real time, the fluorescence intensity generated by the binding of pathogens to genetically engineered bacteriophages. When disinfectants act on pathogens in sewage, the genetically engineered bacteriophages bind to the live pathogens, triggering the expression of the fluorescent reporter gene and generating a fluorescent signal. In the absence of disinfectant, the baseline fluorescence intensity S0 is obtained by testing in a sewage sample without disinfectant. The real-time fluorescence intensity St is the current detected fluorescence signal intensity. According to the formula inactivation rate = 1-(St / S0), the optical conversion unit converts the fluorescence intensity into a real-time pathogen inactivation rate value and outputs it to the dynamic decision control module.
[0037] In an embodiment of the present application, the multi-parameter sensing module includes a residual chlorine detection unit, a spectral analysis unit, and a data fusion unit.
[0038] The residual chlorine detection unit uses the membrane electrode method to measure residual chlorine concentration. Its core component is the membrane electrode, which consists of a cathode, an anode, and an electrolyte, and is covered with a breathable membrane. During measurement, residual chlorine molecules in the wastewater diffuse through the breathable membrane to the cathode surface, where a reduction reaction occurs, generating a current signal proportional to the residual chlorine concentration. The residual chlorine concentration is then determined by measuring this current signal.
[0039] The spectral analysis unit utilizes surface-enhanced Raman scattering (SERS) technology. By fabricating a nanostructured metal substrate on the sensor surface, the Raman scattering signal from DBP molecules is enhanced. As wastewater flows through the spectral analysis unit, DBP molecules adsorb onto the metal substrate, generating Raman scattered light upon exposure to an excitation light source. The spectrometer collects this scattered light and analyzes its characteristic peaks, thereby identifying the type and concentration of the DBPs.
[0040] The data fusion unit synchronizes sensor data such as residual chlorine concentration, wastewater flow, pH value, water temperature, and disinfection by-product spectral data. Specifically, it adds a precise timestamp to each sensor data point to ensure that each parameter corresponds to the time. This data is then packaged into structured data packets for subsequent analysis and processing.
[0041] In an embodiment of the present application, the dynamic decision control module consists of an LSTM prediction unit, a reinforcement learning optimization unit, and an instruction output unit.
[0042] The LSTM prediction unit uses inactivation rate time series data, residual chlorine concentration change rate, SERS peak intensity, and flow rate mutation flag as input data, and uses a long short-term memory network model to predict the pathogen inactivation rate for the next five minutes. The LSTM network has the ability to process time series data and capture long-term dependencies in the data, improving prediction accuracy.
[0043] The reinforcement learning optimization unit establishes an optimization model with the goal of minimizing disinfectant dosage. This model, which considers the constraint that the inactivation rate must meet ≥99.99%, uses a reinforcement learning algorithm to solve and find the optimal disinfectant dosage strategy. The command output unit converts the optimized dosage strategy into a standard 4-20mA industrial control signal, which is output to the disinfection execution unit to control the disinfectant dosage.
[0044] In an embodiment of the present application, a wireless ad hoc network deployment module, when a new module is connected to the system, is automatically assigned a unique network address through the dynamic host configuration protocol or the self-organizing network protocol by the wireless ad hoc network deployment module, thereby realizing plug and play. In the case of a network disconnection, the module switches to the local decision-making mode, and uses the data cache of the last hour to run the deep learning model in the dynamic decision control module to ensure that the system can still perform reasonable disinfectant dosing control based on historical data when the network is interrupted. When the network is restored, the module automatically synchronizes the encrypted data stored locally during the network disconnection to the cloud server to ensure the integrity and continuity of the data. The module uses low-power wide area network technology or wireless local area network technology to achieve wireless communication between modules, supports hot-swappable networking, and facilitates system expansion and maintenance.
[0045] In the embodiment of the present application, the security and compliance interaction module uses the national secret SM4 algorithm to encrypt locally stored data during data storage and transmission to ensure data security and privacy. When the real-time inactivation rate is less than 99.9% or the disinfection by-products exceed the standard, a three-level alarm mechanism is triggered. The first-level alarm is a local sound and light alarm, which emits sound and light signals locally in the monitoring system to alert on-site staff; the second-level alarm sends an alarm text message to the relevant person in charge through the SMS platform to keep them informed of system abnormalities in a timely manner; the third-level alarm pushes the alarm information to the supervision platform to achieve remote supervision of the system operation status.
[0046] The module also provides a MODBUS-TCP protocol interface for connecting to third-party PLC systems, enabling compatibility and data exchange with other industrial control systems. It also supports RESTful API cloud data subscriptions, allowing users to access real-time system data through the cloud platform. It also provides a mini-program alarm information push channel, allowing users to receive alarm information via the mobile app, enabling anytime, anywhere system monitoring.
[0047] In the embodiment of the present application, the specific operating steps of the system are:
[0048] S1: The multi-parameter sensing module continuously collects wastewater parameters. Each sensor in the multi-parameter sensing module monitors wastewater in real time. The residual chlorine detection unit collects residual chlorine concentration data every second. The flow sensor monitors wastewater flow in real time. The pH and temperature sensors collect pH and water temperature data every minute. The spectral analysis unit collects spectral data of disinfection byproducts every two minutes. All sensor data is transmitted to the data fusion unit for time synchronization and packaging to form a structured data package.
[0049] S2: The pathogen inactivation verification module outputs the inactivation rate every 5 minutes. The genetically engineered bacteriophage expressed by the gene editing unit combines with the live pathogens in the sewage to generate a fluorescent signal. The optical conversion unit collects fluorescence intensity data every 5 minutes, calculates the real-time pathogen inactivation rate according to the inactivation rate calculation formula, and outputs the data to the dynamic decision control module.
[0050] S3: The dynamic decision-making control module integrates data to generate dosing instructions. The LSTM prediction unit receives the inactivation rate time series data output by the pathogen inactivation verification module, the residual chlorine concentration change rate, the SERS characteristic peak intensity, and the flow rate mutation flag from the multi-parameter sensing module, and predicts the pathogen inactivation rate for the next five minutes. Based on the prediction results and the current system state, the reinforcement learning optimization unit seeks the optimal solution that achieves an inactivation rate ≥ 99.99%, aiming to minimize the disinfectant dosage. If the confidence level of the LSTM prediction unit's output is less than 90%, the emergency mechanism is activated, switching to proportional control mode (dosage = baseline coefficient × real-time flow rate) and activating the backup residual chlorine closed-loop control submodule to ensure disinfection effectiveness. The command output unit converts the optimized dosing strategy into a 4-20mA control signal, which is output to the disinfection execution unit.
[0051] S4: The disinfection execution unit executes the instruction and feeds back the status. After receiving the control signal, the disinfection execution unit adds the corresponding amount of disinfectant according to the instruction and feeds back the execution status to the dynamic decision control module to form a closed-loop control.
[0052] S5: The Security and Compliance Interaction Module encrypts and transmits full-process data. Using the national SM4 algorithm, the Security and Compliance Interaction Module encrypts data collected by the Multi-Parameter Perception Module, the inactivation rate calculated by the Pathogen Inactivation Verification Module, instructions generated by the Dynamic Decision Control Module, and status feedback from the Disinfection Execution Unit. This data is then transmitted to a cloud server or supervisory platform via the wireless ad hoc network deployment module. Simultaneously, the system's operational status is monitored in real time. When an anomaly occurs, an alarm signal is issued according to the three-level alarm mechanism. Data interaction and alarm information push are implemented through various methods, including the MODBUS-TCP protocol interface, RESTful API, and mini-programs.
[0053] The above description is only a preferred specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any technician familiar with the technical field, within the technical scope disclosed by the present invention, who makes equivalent replacements or changes based on the technical solution and inventive concept of the present invention, should be covered by the scope of protection of the present invention.
Claims
1. An online monitoring system for sewage disinfection used in a square cabin hospital, characterized in that: It includes a pathogen inactivation verification module, a multi-parameter perception module, a dynamic decision-making control module, a wireless ad hoc network deployment module and a safety and compliance interaction module. The pathogen inactivation verification module uses the optical signal generated by the combination of genetically engineered bacteriophages and live pathogens to output a real-time pathogen inactivation rate. The multi-parameter perception module can synchronously collect residual chlorine concentration, sewage flow, pH value, water temperature and disinfection by-product spectral data. The dynamic decision-making control module can receive the output data of the inactivation verification module and the perception module, and generate disinfectant addition instructions through a deep learning model. The wireless ad hoc network deployment module can provide power and data intercommunication services for each module and support hot-swappable networking. The safety and compliance interaction module can realize data encryption and remote monitoring. The output ends of the pathogen inactivation verification module and the multi-parameter perception module are connected to the input end of the dynamic decision-making control module. The output end of the dynamic decision-making control module is connected to a disinfection execution unit, and all modules are interconnected through the wireless ad hoc network deployment module.
2. The sewage disinfection online monitoring system for square cabin hospitals according to claim 1 is characterized in that: The pathogen inactivation verification module includes a gene editing unit and an optical conversion unit. The gene editing unit can connect the phage lytic enzyme gene to the fluorescent reporter gene. The optical conversion unit can convert the fluorescence intensity triggered by the pathogen into an inactivation rate value, and the conversion formula is: Inactivation rate = 1-(St / S0) Where St is the real-time fluorescence intensity, and S0 is the baseline fluorescence intensity in the absence of disinfectant.
3. The sewage disinfection online monitoring system for square cabin hospitals according to claim 1 is characterized in that: The multi-parameter sensing module includes a residual chlorine detection unit, a spectral analysis unit and a data fusion unit. The residual chlorine detection unit uses a membrane electrode method to measure the residual chlorine concentration. The spectral analysis unit identifies the characteristic peaks of disinfection by-products through surface-enhanced Raman scattering. The data fusion unit can package the data of each sensor into a time-synchronized structured data packet.
4. The sewage disinfection online monitoring system for square cabin hospitals according to claim 1 is characterized in that: The dynamic decision-making control module includes an LSTM prediction unit, a reinforcement learning optimization unit, and an instruction output unit. The LSTM prediction unit predicts the pathogen inactivation rate in the next 5 minutes based on current sensor data. The reinforcement learning optimization unit can minimize the amount of disinfectant added as the goal and solve the optimal solution that satisfies the inactivation rate ≥ 99.99%. The instruction output unit can convert the optimization result into a 4-20mA control signal and output it to the disinfection execution unit.
5. The sewage disinfection online monitoring system for square cabin hospitals according to claim 4 is characterized in that: The input data dimensions of the LSTM prediction unit include inactivation rate time series data, residual chlorine concentration change rate, SERS characteristic peak intensity and flow mutation flag.
6. The sewage disinfection online monitoring system for square cabin hospitals according to claim 1 is characterized in that: The wireless ad hoc network deployment module can automatically assign a network address when a new module is connected, switch to local decision-making mode when the network is disconnected, and use the data cache of the last hour to run the model. Secondly, it can automatically synchronize encrypted data to the cloud after the network is restored.
7. The sewage disinfection online monitoring system for square cabin hospitals according to claim 1 is characterized in that: When the security and compliance interaction module is executed, the national secret SM4 algorithm is used to encrypt local stored data, and when the real-time inactivation rate is less than 99.9% or the disinfection by-products exceed the standard, a three-level alarm is triggered. The three-level alarms are local sound and light, SMS, and supervision platform push.
8. The sewage disinfection online monitoring system for square cabin hospitals according to claim 4 is characterized in that: When the LSTM prediction unit outputs a confidence level less than 90%, the following emergency mechanism is activated: Switch to proportional control mode: dosage = reference coefficient × real-time flow rate; Activate the standby residual chlorine closed-loop control submodule.
9. The sewage disinfection online monitoring system for square cabin hospitals according to claim 1 is characterized in that: The security and compliance interaction module can provide a MODBUS-TCP protocol interface for connecting to a third-party PLC system, and the RESTful API supports cloud data subscription, and secondly provides a mini-program alarm information push channel.
10. The sewage disinfection online monitoring system for square cabin hospitals according to claim 1 is characterized in that: The following steps are involved: S1, multi-parameter sensing module continuously collects sewage parameters; S2, pathogen inactivation verification module outputs the inactivation rate every 5 minutes; S3, the dynamic decision control module integrates the data of steps 1-2 to generate a dosing instruction; S4, the disinfection execution unit executes the instruction and feedbacks the status; S5. The security and compliance interaction module encrypts and transmits data throughout the entire process.