A hemodialysis dedicated water treatment PLC system networking monitoring platform and a building method

Abstract

The application provides a hemodialysis water treatment PLC system networking monitoring platform and a building method, relates to the technical field of medical data processing, and comprises a system management layer, a network communication layer and a field measurement and control layer. The system management layer further comprises three functional modules, namely, a pure water demand amount prediction module, a use condition evaluation module and a load balancing scheduling module. The pure water demand amount in a future preset time period can be accurately predicted according to the historical pure water demand amount and the use conditions of each pure water unit, and input into the load balancing scheduling module, so as to schedule the use strategy of each pure water unit. The technical scheme can accurately predict the pure water demand amount in the future preset time period from multiple dimensions, and generate an individual scheduling strategy according to the actual use conditions of each pure water unit, so that the production efficiency of pure water can meet the requirements, and the production energy consumption can be effectively reduced through load balancing scheduling.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of medical data processing, and particularly relates to a hemodialysis special water treatment PLC system networking monitoring platform and a construction method. BACKGROUND

[0002] Hemodialysis is an important medical means for treating diseases such as uremia, and a large amount of medical pure water is needed in the hemodialysis process, so the quality of the medical pure water is directly related to the safety of the patients. In the prior art, a PLC system is usually used to control the production process of the medical pure water, however, the automatic degree of the control process is low, and the yield and quality of the medical pure water cannot be accurately controlled. SUMMARY

[0003] The purpose of the application is to provide a hemodialysis special water treatment PLC system networking monitoring platform and a construction method, so as to solve the technical problem that the automatic degree of the control process is low and the yield and quality of the medical pure water cannot be accurately controlled in the prior art.

[0004] The application provides a hemodialysis special water treatment PLC system networking monitoring platform, which comprises a blockchain network composed of a cloud server node and a plurality of pure water unit nodes, and has the following characteristics.

[0005] A system management layer, comprising a cloud server located in a water machine monitoring system master station, and the cloud server is in communication connection with a field measurement and control layer through a network communication layer; in the cloud server, three functional modules of a pure water demand amount prediction module, a use condition evaluation module and a load balancing scheduling module are included

[0006] A network communication layer, which is used for establishing communication connection between the system management layer and the field measurement and control layer;

[0007] A field measurement and control layer, comprising at least one pure water unit, and the pure water unit is used for preparing medical pure water; each pure water unit comprises a cross-network segment device, a switch, a PLC panel, a slave station device and a PLC, wherein the PLC panel, the slave station device and the PLC are connected with the switch, and information is sent to the system management layer through the cross-network segment device.

[0008] Preferably, the working steps of the pure water demand amount prediction module comprise:

[0009] S11: obtaining first historical hemodialysis data from the cloud server, and obtaining a first pure water demand amount prediction factor according to the first historical hemodialysis data;

[0010] S12: determining a second pure water demand amount prediction factor according to a first regional hemodialysis fluctuation curve and a first unit hemodialysis fluctuation curve;

[0011] S13: input the first hemodialysis frequency and the first average hemodialysis parameter corresponding to the plurality of first natural persons into the pure water demand seasonal correction model respectively to determine a first pure water demand correction factor; wherein the first hemodialysis frequency refers to the average interval time of hemodialysis of each of the first natural persons; the first average hemodialysis parameter refers to the average hemodialysis time, the average pure water consumption and the average effect evaluation result in the historical hemodialysis process for each of the first natural persons; the average pure water consumption refers to the average single pure water consumption of each of the first natural persons in the plurality of hemodialysis processes; and the average effect evaluation result represents the average single condition improvement situation of each of the first natural persons after the plurality of hemodialysis processes;

[0012] S14: determine the pure water demand according to the first pure water demand prediction factor, the second pure water demand prediction factor and the first pure water demand correction factor.

[0013] Preferably, the first pure water demand prediction factor is obtained according to the first historical hemodialysis data, and the method comprises the following steps:

[0014] S111: obtain the first hemodialysis frequency and the first average hemodialysis parameter corresponding to the plurality of first natural persons from the first historical hemodialysis data;

[0015] S112: obtain a first pure water demand estimation according to the first hemodialysis frequency and the first average hemodialysis parameter corresponding to each of the first natural persons;

[0016] S113: add the plurality of first pure water demand estimations corresponding to the plurality of natural persons to obtain the first pure water demand prediction factor.

[0017] Preferably, the first pure water demand estimation is calculated in the following manner:

[0018] determine a first basic pure water demand estimation according to the first hemodialysis frequency and the average pure water consumption;

[0019] correct the first basic pure water demand estimation according to the average effect evaluation result to obtain the first pure water demand estimation.

[0020] Preferably, the working steps of the use condition evaluation module comprise:

[0021] S21: obtain first historical use condition information of each of the pure water machine groups;

[0022] S22: input the first historical use condition information into a pure water machine group use strategy determination model to obtain a first use strategy corresponding to each of the pure water machine groups.

[0023] Preferably, the working steps of the load balancing scheduling module include:

[0024] S31: Obtain the first pure water demand within the first preset time period;

[0025] S32: Determine the first load balancing scheduling model based on the number of pure water units;

[0026] S33: Input the first pure water demand and multiple first usage strategies into the first load balancing scheduling model to output the first scheduling strategy.

[0027] Preferably, after the first scheduling strategy is formed, the method further includes:

[0028] The cloud server performs a first decomposition operation on the first scheduling strategy to obtain a first sub-scheduling strategy corresponding to each of the pure water units.

[0029] This application also proposes a method for building a networked monitoring platform for a PLC system dedicated to hemodialysis water treatment, used to build the aforementioned networked monitoring platform for a PLC system dedicated to hemodialysis water treatment, characterized in that the method includes:

[0030] A system management layer is established, including a cloud server located at the main station of the water turbine monitoring system. The cloud server is connected to the field measurement and control layer through a network communication layer.

[0031] Establish a network communication layer to create a communication connection between the system management layer and the field measurement and control layer;

[0032] A field monitoring and control layer is established, including at least one pure water unit. The pure water unit is used to prepare medical pure water. Each pure water unit includes a cross-network segment device, a switch, a PLC panel, a slave device, and a PLC. The PLC panel, slave device, and PLC are all connected to the switch and send information to the system management layer through the cross-network segment device.

[0033] This application proposes a networked monitoring platform and construction method for a PLC system dedicated to hemodialysis water treatment. The platform includes a system management layer, a network communication layer, and a field measurement and control layer. The system management layer further includes three functional modules: a pure water demand prediction module, a usage assessment module, and a load balancing scheduling module. These modules can accurately predict the pure water demand for a preset future time period based on historical pure water demand and the usage of each pure water unit, and input this prediction into the load balancing scheduling module for scheduling the usage strategies of each pure water unit. This technical solution allows for accurate prediction of pure water demand for a preset future time period from multiple dimensions and generates personalized scheduling strategies based on the actual usage of each pure water unit. This ensures that pure water production efficiency meets requirements, while load balancing scheduling effectively reduces production energy consumption. Attached Figure Description

[0034] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely exemplary, and those skilled in the art can derive other embodiments based on the provided drawings without creative effort.

[0035] Figure 1 This is a system framework diagram of a network monitoring platform for a PLC system for hemodialysis-specific water treatment in this invention.

[0036] Figure 2 This is a structural diagram of the pure water unit in this invention. Detailed Implementation

[0037] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0038] The present invention will now be described in detail with reference to the accompanying drawings and specific embodiments. The illustrative embodiments and descriptions are only used to explain the present invention and are not intended to limit the present invention.

[0039] The following is a detailed description of the network monitoring platform and construction method of a PLC system for hemodialysis-specific water treatment according to the present invention.

[0040] This embodiment proposes a networked monitoring platform for a dedicated hemodialysis water treatment PLC system. (See [link]). Figure 1 The specific system framework is as follows:

[0041] The system management layer includes a cloud server located at the main station of the water turbine monitoring system, which is connected to the field measurement and control layer through a network communication layer.

[0042] The network communication layer establishes a communication connection between the system management layer and the field measurement and control layer through a switch.

[0043] The on-site monitoring and control layer includes at least one pure water unit, which is used to prepare medical-grade pure water. Figure 2 As shown, each pure water unit includes a cross-network segment device, a switch, a PLC panel, a slave device, and a PLC. The PLC panel, slave device, and PLC are all connected to the switch and send information to the system management layer through the cross-network segment device.

[0044] In this invention, the network monitoring platform of the hemodialysis-specific water treatment PLC system and multiple pure water units all serve as multiple blockchain nodes, thereby establishing a blockchain network. The system management layer is used to perform big data analysis based on the seasonal changes in patients' dialysis needs, the usage and maintenance status of each pure water unit, and energy consumption, thereby sending control commands to multiple blockchain nodes composed of pure water units.

[0045] The system management layer includes three functional modules: a pure water demand prediction module, a usage assessment module, and a load balancing scheduling module. The functions of these three modules are described below:

[0046] Pure water demand prediction module. The medical pure water used in hemodialysis has high purity requirements and a short shelf life. Therefore, it is necessary to make a relatively accurate prediction of the pure water demand and prepare pure water according to the prediction.

[0047] The pure water demand prediction module mainly predicts the pure water demand based on three aspects: historical hemodialysis demand, future estimated hemodialysis demand, and seasonal influencing factors.

[0048] The pure water demand prediction module operates through the following steps:

[0049] S11: Obtain the first historical hemodialysis data from the cloud server, and obtain the first pure water demand prediction factor based on the first historical hemodialysis data.

[0050] The first historical hemodialysis data refers to hemodialysis order information within a preset time period recorded in the hospital's hemodialysis record database.

[0051] The preset time period refers to a period of time within a preset time range from the current time, such as within a week or half a month. The hemodialysis order information refers to the number and specific information of hemodialysis orders placed by the first natural person at the hospital within the preset time period. The number of orders refers to the number of times the first natural person undergoes hemodialysis within the preset time period, and the specific information refers to the duration of each hemodialysis session, the amount of purified water consumed, and the effects after hemodialysis.

[0052] The step of obtaining the first pure water demand prediction factor based on the first historical hemodialysis data includes the following steps:

[0053] S111: Obtain the first hemodialysis frequency and the first average hemodialysis parameter corresponding to multiple first natural persons from the first historical hemodialysis data.

[0054] Among them, the multiple first natural persons refer to natural persons who undergo hemodialysis treatment at a certain frequency in the hospital, and the first hemodialysis frequency refers to the average interval between hemodialysis treatments for each first natural person.

[0055] The first average hemodialysis parameter refers to the average hemodialysis duration, average pure water consumption, and average effect evaluation result for each of the first natural persons during historical hemodialysis processes.

[0056] S112: Based on the first hemodialysis frequency and the first average hemodialysis parameter corresponding to each of the first natural persons, obtain the first pure water demand estimate.

[0057] Specifically, for each of the first natural persons, the first estimated demand for pure water is determined using the corresponding first hemodialysis frequency and the first average hemodialysis parameter.

[0058] The first estimated demand for pure water is calculated using the following method:

[0059] The first step is to determine the estimated first basic pure water requirement based on the first hemodialysis frequency and the average pure water consumption.

[0060] The second step is to correct the first basic pure water demand estimate based on the average effect evaluation results to obtain the first pure water demand estimate.

[0061] S113: Summing up the multiple estimated first pure water demand quantities corresponding to the multiple natural persons to obtain the first pure water demand prediction factor.

[0062] S12: Determine the second pure water demand prediction factor based on the hemodialysis fluctuation curve of the first region and the hemodialysis fluctuation curve of the first unit.

[0063] The first regional hemodialysis fluctuation curve refers to the fluctuation curve of hemodialysis demand within a predetermined geographical area within a preset time interval. For example, the fluctuation pattern of hemodialysis demand over time within a province or city.

[0064] The first unit hemodialysis fluctuation curve refers to the fluctuation curve of hemodialysis demand in a medical unit within a preset time interval. For example, the fluctuation pattern of hemodialysis demand over time in a hospital.

[0065] In this step, the second pure water demand prediction factor is determined primarily based on the hemodialysis fluctuation curve of the first region and the hemodialysis fluctuation curve of the first unit corresponding to the geographical location. Specifically, the calculation method can employ curve fitting to determine the average change in the number of hemodialysis patients, and then use this average change in the number of hemodialysis patients, along with the average hemodialysis frequency and average pure water consumption, to obtain the final result.

[0066] S13: Input the first hemodialysis frequency and the first average hemodialysis parameter corresponding to the multiple first natural persons into the seasonal correction model for pure water demand to determine the first pure water demand correction factor.

[0067] Temperatures fluctuate significantly with the changing seasons; for example, the demand for hemodialysis is lower in summer than in winter. Therefore, a correction factor for the demand for pure water can be determined based on the current season, making the prediction of pure water demand more accurate.

[0068] The first pure water demand correction factor is mainly predicted based on the treatment status of existing hemodialysis patients in the hospital and seasonal factors. The seasonal correction model for pure water demand is obtained by training an LSTM convolutional neural network model in the following manner:

[0069] First, historical sample data was obtained. Each historical sample data point uses the hemodialysis data of a single hemodialysis patient as the seasons change.

[0070] Secondly, the LSTM convolutional neural network model is trained by using multiple hemodialysis data from the historical sample data as input data and the pure water demand correction factor determined according to the hemodialysis change pattern as output data.

[0071] The pure water demand correction factor refers to the fluctuation value of seasonal pure water demand compared with the annual average pure water demand.

[0072] S14: Determine the pure water demand based on the first pure water demand prediction factor, the second pure water demand prediction factor, and the first pure water demand correction factor.

[0073] The pure water demand can be obtained by simple addition and subtraction of the first pure water demand prediction factor, the second pure water demand prediction factor, and the first pure water demand correction factor, or it can be obtained by algorithm calculation according to the specified demand.

[0074] Usage Assessment Module. This module primarily evaluates the usage of each water purifier unit to prepare for the load balancing scheduling module's operation, ensuring that each unit operates at its optimal state. The main evaluation factors for this module include the usage frequency, duration, historical maintenance history, and historical repair history of each water purifier unit.

[0075] The usage assessment module performs the assessment operation using the following steps:

[0076] S21: Obtain the first historical usage information for each of the pure water units.

[0077] The first historical usage information includes the usage frequency, usage duration, historical maintenance information, and historical repair information for each water purifier unit. The usage frequency and usage duration refer to the usage frequency and cumulative usage duration of each water purifier unit within a preset time interval, while the historical maintenance information and historical repair information refer to the maintenance frequency and repair frequency information of each water purifier unit within the preset time interval.

[0078] S22: Input the first historical usage information into the pure water unit usage strategy determination model to obtain the first usage strategy corresponding to each pure water unit.

[0079] The pure water unit usage strategy determination model is obtained by training a convolutional neural network. It uses the historical usage data of pure water units as training samples. Each historical sample data includes the historical situation information of a pure water unit and the optimal usage strategy. The historical situation information is used as input data and the optimal usage strategy is used as output data to train and obtain the pure water unit usage strategy determination model.

[0080] The optimal usage strategy includes the usage frequency and cumulative usage time corresponding to the pure water unit.

[0081] A load balancing scheduling module. This module is used to schedule the use of multiple pure water units based on the pure water demand output by the pure water demand prediction module and the first usage strategy output by the usage assessment module.

[0082] The load balancing scheduling module performs scheduling operations using the following steps:

[0083] S31: Obtain the first pure water demand within the first preset time period.

[0084] The first preset time period refers to a future period of time, preferably 24 hours.

[0085] The first pure water demand is calculated and output by the pure water demand prediction module.

[0086] S32: Determine the first load balancing scheduling model based on the number of pure water units.

[0087] The load balancing scheduling model is obtained through training a convolutional neural network model. The training process is as follows:

[0088] First, historical sample data is obtained. This historical sample data is categorized according to the number of pure water units; specifically, pure water production systems with four units are grouped together, and pure water production systems with five units are grouped together. Each group of sample data is used to train one load balancing scheduling model.

[0089] Secondly, the pure water demand and usage strategies of multiple pure water units in each set of historical sample data are used as input data, and the scheduling strategies of multiple pure water units are used as output data to train a convolutional neural network model to obtain the load balancing scheduling model. Multiple load balancing scheduling models are obtained through the above training process for different numbers of pure water units.

[0090] In S32, the corresponding first load balancing scheduling model is determined based on the number of pure water units.

[0091] S33: Input the first pure water demand and multiple first usage strategies into the first load balancing scheduling model to output the first scheduling strategy.

[0092] After the first scheduling policy is formed, the following steps are also included:

[0093] The cloud server performs a first decomposition operation on the first scheduling strategy to obtain a first sub-scheduling strategy corresponding to each of the pure water units.

[0094] The cloud server forwards multiple first sub-scheduling strategies to the corresponding pure water units through the network communication layer.

[0095] This application also proposes a method for building a networked monitoring platform for a PLC system dedicated to hemodialysis water treatment, used to build the aforementioned networked monitoring platform for the PLC system dedicated to hemodialysis water treatment, the method comprising the following steps:

[0096] A system management layer is established, including a cloud server located at the main station of the water turbine monitoring system. The cloud server is connected to the field measurement and control layer through a network communication layer.

[0097] Establish a network communication layer and use a switch to establish a communication connection between the system management layer and the field measurement and control layer.

[0098] A field monitoring and control layer is established, including at least one pure water unit, which is used to prepare medical-grade pure water. Each pure water unit includes a cross-network segment device, a switch, a PLC panel, a slave device, and a PLC. The PLC panel, slave device, and PLC are all connected to the switch and send information to the system management layer through the cross-network segment device.

[0099] This application proposes a networked monitoring platform and construction method for a PLC system dedicated to hemodialysis water treatment. The platform includes a system management layer, a network communication layer, and a field measurement and control layer. The system management layer further includes three functional modules: a pure water demand prediction module, a usage assessment module, and a load balancing scheduling module. These modules can accurately predict the pure water demand for a preset future time period based on historical pure water demand and the usage of each pure water unit, and input this prediction into the load balancing scheduling module for scheduling the usage strategies of each pure water unit. This technical solution allows for accurate prediction of pure water demand for a preset future time period from multiple dimensions and generates personalized scheduling strategies based on the actual usage of each pure water unit. This ensures that pure water production efficiency meets requirements, while load balancing scheduling effectively reduces production energy consumption.

[0100] The above description is only a preferred embodiment of the present invention. Therefore, all equivalent changes or modifications made to the structure, features and principles described in the claims of this patent application are included in the scope of this patent application.

Claims

1. A networked monitoring platform for a PLC system dedicated to hemodialysis water treatment, comprising a blockchain network consisting of cloud server nodes and multiple pure water unit nodes, characterized in that, include: The system management layer includes a cloud server located at the main station of the water turbine monitoring system, which is connected to the field measurement and control layer through a network communication layer; The cloud server includes three functional modules: a pure water demand prediction module, a usage assessment module, and a load balancing scheduling module. The pure water demand prediction module is used to predict the pure water demand based on three aspects: historical hemodialysis demand, future estimated hemodialysis demand, and seasonal influencing factors. The usage evaluation module is used to evaluate the usage of each pure water unit, preparing for the scheduling work of the load balancing scheduling module, so that each pure water unit is in an optimal state. The load balancing scheduling module is used to schedule the use of multiple pure water units based on the pure water demand output by the pure water demand prediction module and the first usage strategy of the usage evaluation module. The network communication layer is used to establish communication connections between the system management layer and the field measurement and control layer. The field monitoring and control layer includes at least one pure water unit, which is used to prepare medical pure water; each pure water unit includes a cross-network segment device, a switch, a PLC panel, a slave device and a PLC, wherein the PLC panel, slave device and PLC are all connected to the switch and send information to the system management layer through the cross-network segment device.

2. The network monitoring platform for the hemodialysis-specific water treatment PLC system according to claim 1, characterized in that, The working steps of the pure water demand prediction module include: S11: Obtain first historical hemodialysis data from the cloud server, and obtain a first pure water demand prediction factor based on the first historical hemodialysis data; S12: Determine the second pure water demand prediction factor based on the first region hemodialysis fluctuation curve and the first unit hemodialysis fluctuation curve; S13: Input the first hemodialysis frequency and the first average hemodialysis parameter corresponding to multiple first natural persons into the seasonal correction model for pure water demand to determine the first pure water demand correction factor; wherein, the first hemodialysis frequency refers to the average interval time for each first natural person to undergo hemodialysis; the first average hemodialysis parameter refers to the average hemodialysis duration, average pure water consumption, and average effect evaluation result for each first natural person in the historical hemodialysis process; the average pure water consumption refers to the average pure water consumption per session for each first natural person in multiple hemodialysis processes; the average effect evaluation result represents the average improvement in condition per session for each first natural person after multiple hemodialysis sessions. S14: Determine the pure water demand based on the first pure water demand prediction factor, the second pure water demand prediction factor, and the first pure water demand correction factor.

3. The network monitoring platform for the hemodialysis-specific water treatment PLC system according to claim 2, characterized in that, The step of obtaining the first pure water demand prediction factor based on the first historical hemodialysis data includes the following steps: S111: Obtain the first hemodialysis frequency and the first average hemodialysis parameter corresponding to multiple first natural persons from the first historical hemodialysis data; S112: Based on the first hemodialysis frequency and the first average hemodialysis parameter corresponding to each of the first natural persons, obtain the first pure water demand estimate; S113: Summing up the multiple estimated first pure water demand quantities corresponding to the multiple natural persons to obtain the first pure water demand prediction factor.

4. The network monitoring platform for the hemodialysis-specific water treatment PLC system according to claim 3, characterized in that, The specific calculation method for the first pure water demand estimate is as follows: Based on the first hemodialysis frequency and the average pure water consumption, determine the first basic pure water demand estimate; Based on the average effect evaluation results, the first basic pure water demand estimate is corrected to obtain the first pure water demand estimate.

5. The network monitoring platform for the hemodialysis-specific water treatment PLC system according to claim 4, characterized in that, The operation steps of the usage assessment module include: S21: Obtain the first historical usage information for each of the pure water units; S22: Input the first historical usage information into the pure water unit usage strategy determination model to obtain the first usage strategy corresponding to each pure water unit.

6. The network monitoring platform for the hemodialysis-specific water treatment PLC system according to claim 5, characterized in that, The working steps of the load balancing scheduling module include: S31: Obtain the first pure water demand within the first preset time period; S32: Determine the first load balancing scheduling model based on the number of pure water units; S33: Input the first pure water demand and multiple first usage strategies into the first load balancing scheduling model to output the first scheduling strategy.

7. The network monitoring platform for the hemodialysis-specific water treatment PLC system according to claim 6, characterized in that, After the first scheduling policy is formed, the following is also included: The cloud server performs a first decomposition operation on the first scheduling strategy to obtain a first sub-scheduling strategy corresponding to each of the pure water units.

8. A method for constructing a networked monitoring platform for a PLC system dedicated to hemodialysis water treatment, used to construct a networked monitoring platform for a PLC system dedicated to hemodialysis water treatment as described in any one of claims 1-7, characterized in that, The method includes: A system management layer is established, including a cloud server located at the main station of the water turbine monitoring system. The cloud server is connected to the field measurement and control layer through a network communication layer. Establish a network communication layer to create a communication connection between the system management layer and the field measurement and control layer; A field monitoring and control layer is established, including at least one pure water unit. The pure water unit is used to prepare medical pure water. Each pure water unit includes a cross-network segment device, a switch, a PLC panel, a slave device, and a PLC. The PLC panel, slave device, and PLC are all connected to the switch and send information to the system management layer through the cross-network segment device.

Images