Hospital building water system antifouling energy-saving control method and system

Abstract

The present application relates to the technical field of water supply and drainage and new generation information technology, and discloses a hospital building water system anti-fouling energy-saving control system, which comprises a plurality of subsystems, and each subsystem comprises: a sampling device, which is used for acquiring and transmitting trace element content data in sewage; a subsystem processor, which is used for receiving the trace element content data transmitted by the sampling device; the subsystem processor constructs a neural network model of trace element content change, performs function fitting on the content change of the trace elements in each sewage treatment tank in sequence with time, obtains a fitting formula of the trace element content change, calculates the time when the trace element content in the sewage meets the standard, and transmits the time when the trace element content meets the standard; and a valve controller, which is used for controlling the opening and closing of the valve of the sewage treatment tank according to the received time when the trace element content meets the standard. The present application also discloses a hospital building water system anti-fouling energy-saving control method, which can improve the sewage treatment speed and avoid energy waste.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of water supply and drainage and new generation information technology, and particularly relates to a hospital building water system anti-fouling energy-saving control method and system. BACKGROUND

[0002] With the increasing industrialization of human beings, environmental protection will become an important issue in the future human society. For building water supply and drainage systems, environmental protection is not simply treating sewage to meet the standard, but involves every detail in the design. The water system of a hospital is different from that of a common public building. Reasonably designing the water system of a hospital building can effectively guarantee the supply of various water, achieve separate water supply, safety and energy saving, separate discharge from the source, separate treatment, and better protection of the ecological environment.

[0003] Chinese patent application No. CN103319056 discloses a hospital sewage treatment system. A dechlorination agent is prepared in a dosing box and sent to a dechlorination agent dosing box through a pipeline. The dechlorination agent dosing box provides the dechlorination agent to a dechlorination tank. The addition amount and interval time of the dechlorination agent can be controlled through the dechlorination agent dosing box, which is convenient for automatic management and reduces the labor intensity. A ball valve and an electromagnetic valve control the opening and closing of the pipeline. A flocculant dosing box is also provided. The flocculant dosing box is connected to a dosing tank through a pipeline. An electromagnetic valve is arranged on the pipeline connecting the flocculant dosing box and the dosing tank. The flocculant dosing box adds flocculant to the dosing tank, which is convenient for management and automatic control. The electromagnetic valve controls the opening and closing of the pipeline. A collection device can be arranged at the sewage discharge outlets of a dental department, a washing room and a laboratory to pretreat the wastewater, so that the heavy metal ions in the wastewater meet the standard. The treated water is discharged into a septic tank. A decay tank is arranged at the sewage discharge outlet of a radiology department to ensure that the radioactivity of the wastewater meets the standard. A pre-disinfection device is arranged at the outlet of an infectious disease department. The infectious disease wastewater is treated by disinfection and then discharged into a septic tank. However, the present application inventors found at least the following technical problems in the process of implementing the technical scheme in the present application: the prior art cannot detect the relationship between the sewage treatment efficiency, effect and time, cannot improve the sewage treatment speed while meeting the standard, and energy is wasted in the sewage treatment process. SUMMARY

[0004] The present application provides a hospital building water system anti-fouling energy-saving control system and method to solve the problems that the prior art cannot detect the relationship between the sewage treatment efficiency, effect and time, cannot improve the sewage treatment speed while meeting the standard, and energy is wasted in the sewage treatment process.

[0005] The application provides a hospital building water system antifouling energy-saving control system and method, and specifically comprises the following technical solutions.

[0006] In a first aspect, an antifouling energy-saving control system for a hospital building water system is provided. The control system comprises a plurality of subsystems, including: a sampling device arranged in a sewage treatment tank, configured to collect a sewage sample in the sewage treatment tank, detect the treated sewage, obtain and transmit microelement content data in the sewage; a subsystem processor in data connection with the sampling device, configured to receive the microelement content data transmitted by the sampling device; the subsystem processor constructs a microelement content change neural network model, performs function fitting on the content change of microelements in each sewage treatment tank in sequence of time, obtains a microelement content change fitting formula, calculates the time when the microelement content in the sewage meets the standard, and transmits the time when the microelement content meets the standard; and a valve controller in data connection with the subsystem processor, configured to control the opening and closing of the valve of the sewage treatment tank according to the received time when the microelement content meets the standard.

[0007] In combination with the first aspect, in a first possible implementation manner of the first aspect, the subsystem processor comprises: a data acquisition module configured to receive and transmit the microelement content data from the sampling device; a neural network model construction module in data connection with the data acquisition module, configured to construct a microelement content change neural network model, perform function fitting on the content change of microelements in each sewage treatment tank in sequence of time, and obtain a microelement content change fitting formula; a calculation module in data connection with the neural network model construction module, configured to receive the microelement content change fitting formula, calculate and transmit the time when the microelement content in the sewage meets the standard; and an antifouling energy-saving control module in data connection with the calculation module, configured to obtain the time when the microelement content in the sewage meets the standard and issue a control instruction to the valve controller.

[0008] In combination with the first possible implementation manner of the first aspect, in a second possible implementation manner of the first aspect, the subsystem processor further comprises an antifouling audit module in data connection with the data acquisition module, and the antifouling audit module is configured to obtain the microelement content data in the treated sewage and judge whether the treated sewage is qualified.

[0009] In combination with the second possible implementation manner of the first aspect, in a third possible implementation manner of the first aspect, the antifouling audit module can calculate an organic coefficient in the treated sewage, and if the organic coefficient is less than a preset threshold value, the sewage treatment is qualified, otherwise the sewage enters a strengthened tank for strengthened treatment.

[0010] In a second aspect, a hospital building water system antifouling energy-saving control method is provided, including: step A: according to the properties and characteristics of sewage, the hospital sewage is divided into several partitions, the sewage of a plurality of sewage treatment tanks in series in different partitions is collected and detected respectively, and the content of trace elements in the sewage is obtained; step B: the content change value of the trace elements in each sewage treatment tank over time is obtained, a trace element content change neural network is constructed, the content change of the trace elements in each sewage treatment tank in sequence with time is functionally fitted, a trace element content change fitting formula is obtained, the time when the content of the trace elements in the sewage meets the standard is calculated, and the sewage treatment time is controlled.

[0011] In combination with the second aspect, in a first possible implementation manner of the second aspect, the control method further includes step C: when all the sewage treatment processes are completed, the content of each trace element in the sewage is obtained, the organic coefficient in the treated sewage is calculated, and if the organic coefficient δ is less than a preset threshold value, the sewage treatment is qualified; otherwise, the sewage needs to be treated in a strengthened tank.

[0012] In combination with the second aspect or the first possible implementation manner of the second aspect, in a second possible implementation manner of the second aspect, the trace element content change neural network includes an input layer, a verification layer, an activation layer, a fitting layer and an output layer.

[0013] In combination with the second possible implementation manner of the second aspect, in a third possible implementation manner of the second aspect, the verification layer of the trace element content change neural network performs mixed verification by using a covariance function of the trace element content data, a mixed verification rule of the trace element content detection is that the difference value of the trace element content obtained by different sampling points in the same detection is less than a preset threshold value, which indicates that the trace elements in the sewage are sufficiently mixed, and the sampling data of the sufficient mixing can more accurately represent the content of the trace elements in the sewage; the verification layer is provided with a verification instruction interface, if the result does not conform to the verification rule, the sampling data of the batch is abandoned, the verification instruction interface sends a verification instruction of the next batch of sampling data to the input layer, if the result conforms to the verification rule, the verification layer sends the data to the activation layer, the fitting layer analyzes the time sequence of the trace element content by using an autocorrelation function and a partial correlation function of the time sequence, and fits the fitting formula by using a likelihood function.

[0014] Compared with the prior art, the multiple technical solutions provided by the embodiments of the present application have at least the following technical effects:

[0015] 1. According to the different functions of different departments and wards of the hospital, the hospital sewage is classified and discharged and treated, the secondary pollution is effectively prevented, the antifouling control is fundamentally performed, the workload of subsequent sewage treatment is reduced, and the cost is saved.

[0016] 2. The microelement content change neural network is constructed, the content change of the microelement in each sewage treatment tank is sequentially fitted with time as a function, the sewage treatment time is controlled, the sewage treatment efficiency is improved, unnecessary energy waste in the sewage treatment process is reduced, the purpose of preventing pollution and saving energy is achieved.

[0017] 3. The technical scheme of the application can effectively solve the problem that the relationship between the sewage treatment efficiency, effect and time cannot be detected when sewage is treated, the sewage treatment speed cannot be improved while the sewage treatment meets the standard, and energy is wasted in the sewage treatment process, and the above system or method has been verified in a series of tests, and finally the effect of preventing pollution and saving energy of the hospital building water system can be achieved. BRIEF DESCRIPTION OF DRAWINGS

[0018] Figure 1 is a structural diagram of the hospital building water system pollution prevention and energy saving control system of the application;

[0019] Figure 2 is a flowchart of the hospital building water system pollution prevention and energy saving control method of the application. DETAILED DESCRIPTION

[0020] The principles and characteristics of the application are described below in combination with the drawings, and the examples are only used to explain the application and not to limit the scope of the application.

[0021] According to the different functions of different departments and wards of the hospital, the hospital sewage is classified and discharged and treated, secondary pollution is effectively prevented, pollution control is fundamentally performed, the workload of subsequent sewage treatment is reduced, and costs are saved; a microelement content change neural network is constructed, the content change of the microelement in each sewage treatment tank is sequentially fitted with time as a function, the sewage treatment time is controlled, the sewage treatment efficiency is improved, unnecessary energy waste in the sewage treatment process is reduced, and the purpose of preventing pollution and saving energy is achieved.

[0022] In order to better understand the above technical scheme, the above technical scheme will be described in detail below in combination with the drawings of the specification and the specific embodiments.

[0023] Referring to Figure 1 The control system comprises a plurality of subsystems.

[0024] The above-mentioned subsystems comprise a sampling device 10 arranged in the sewage treatment tank, the sampling device 10 is data-connected with a subsystem processor 30, and the subsystem processor 30 is data-connected with a valve controller 20.

[0025] In some embodiments, the sampling device 10 is used to collect sewage samples in the sewage treatment tank, detect the treated sewage, obtain the content of trace elements in the sewage, and send the collected data to the subsystem processor 30 through wireless transmission. The content of trace elements in each sewage treatment tank changes over time. The subsystem processor 30 is used to receive the trace element content data sent by the sampling device on the one hand; on the other hand, it is used to construct a trace element content change neural network model, to functionally fit the content change of trace elements in each sewage treatment tank in sequence with time, to obtain a trace element content change fitting formula, to calculate the time when the content of trace elements in the sewage meets the standard, and to send the time when the content of trace elements meets the standard to the valve controller 20. The valve controller 20 is used to control the opening and closing of the valve of the sewage treatment tank.

[0026] In some embodiments, the above-mentioned several subsystems can be three subsystems, including: pollution area anti-pollution energy-saving control subsystem, sick area anti-pollution energy-saving control subsystem and general area anti-pollution energy-saving control subsystem.

[0027] As shown in Figure 1 In some embodiments, the subsystem processor 30 includes a data acquisition module 301, a neural network model construction module 302, a calculation module 303, and an anti-pollution energy-saving control module 304.

[0028] The data acquisition module 301 is used to receive the content of trace elements in the sewage, and send the received data to the neural network model construction module 302 through wireless transmission.

[0029] The neural network model construction module 302 is used to construct a trace element content change neural network model, which includes an input layer, a verification layer, an activation layer, a fitting layer and an output layer. The input is the content of trace elements in the sewage treatment tank at n times of detection at s sampling points, and the output is a trace element content change fitting formula. The neural network model construction module 302 sends the trace element content change fitting formula to the calculation module 303 through data transmission. The calculation module 303 is used to calculate the time when the content of trace elements in the sewage meets the standard according to the trace element content change fitting formula, and sends it to the anti-pollution energy-saving control module 304 through data transmission. The anti-pollution energy-saving control module 304 is used to issue control instructions to the valve controller 20 of the sewage treatment tank according to the time when the content of trace elements in the sewage meets the standard.

[0030] As shown in Figure 1The subsystem processor 30 also includes a pollution prevention auditing module 305 in some embodiments, which is configured to obtain the content of each trace element in the sewage, calculate the organic coefficient in the processed sewage, and determine that the sewage treatment is qualified if the organic coefficient δ is less than a preset threshold value; otherwise, the sewage needs to be treated in the enhanced tank.

[0031] Figure 2 FIG. 1 is a flowchart of a hospital building water system pollution prevention and energy saving control method provided by an embodiment of the present disclosure. As shown in FIG. 1, the embodiment provides a hospital building water system pollution prevention and energy saving control method, which includes the following steps. Figure 2 Step A: According to the properties and characteristics of the sewage, the hospital sewage is divided into several partitions, and the sewage in multiple sewage treatment tanks in series in different partitions is collected and detected to obtain the content of trace elements in the sewage. Step B: Obtain the content change value of the trace elements in each sewage treatment tank over time, construct a trace element content change neural network, and perform function fitting on the content change of the trace elements in each sewage treatment tank in sequence with time to obtain a trace element content change fitting formula, calculate the time when the content of the trace elements in the sewage meets the standard, and control the sewage treatment time.

[0032] In some embodiments, step A further includes: according to the properties and characteristics of the sewage, including but not limited to the source of the sewage, the composition, etc., the hospital sewage is divided into several partitions, and an independent subsystem is set up for each partition; the subsystem is connected with a sewage treatment platform. Specifically, the hospital sewage is classified and discharged and treated, three partitions of a pollution area, a sick area and a general area are set up, an independent subsystem is set up for different partitions, and multiple sewage treatment tanks in series are arranged in the sewage treatment platform.

[0033] In some embodiments, step A further comprises: step A1: the hospital building water system mainly consists of a water supply system, a drainage system, a rainwater system and the like. The supply water of the water supply system mainly includes domestic water supply, fire water supply, hot water supply, cooling water, direct drinking water, medical pure water, acidified water, automatic sprinkling irrigation for outdoor greening and the like; the sewage discharged by the drainage system mainly includes domestic sewage, acid sewage, cyanide-containing sewage, heavy metal-containing sewage, radioactive sewage, fecal sewage containing infectious sources, high-temperature sewage and the like. Due to the difference in functionality between the hospital and the ordinary building, there are special health requirements for the hospital. The present application mainly considers the anti-pollution and energy-saving control of the hospital building water supply and drainage, prevents water pollution and prevents the large-scale occurrence of infectious diseases, and saves the use. The hospital sewage source and composition are complex, and for the pollution containing pathogenic microorganisms, toxic, harmful physical and chemical pollutants and radioactive pollution and the like, it has the characteristics of space pollution, acute infection and latent infection and the like, and without effective treatment, it will become an important way of epidemic diffusion and serious pollution of the environment. Therefore, it is necessary to classify and discharge and treat the hospital sewage, according to the different functions of different departments and wards, set up pollution area, disease area and general area. The sewage of the pollution area corresponds to the sewage generated by the related places of the departments and wards with infectiousness; the disease area sewage corresponds to the sewage generated by the related places of the departments and wards without infectiousness; and the general area sewage corresponds to the domestic sewage generated by non-patients (such as doctors, nurses).

[0034] In some embodiments, step A further comprises step A2: setting up independent subsystems for different partitions, including a pollution area anti-pollution energy-saving control subsystem, a sick area anti-pollution energy-saving control subsystem, and a general area anti-pollution energy-saving control subsystem, each of which independently controls the anti-pollution energy-saving devices of the water supply and drainage of each area. The anti-pollution energy-saving device is a device used by the hospital to treat water supply and drainage, which can use general equipment. The sewage generated in different partitions is transported separately to the sewage treatment platform for treatment. The sewage treatment platform is a standard sewage treatment platform set according to relevant national standards and economic and technical conditions, including sedimentation, disinfection, biological treatment, etc. Taking the pollution area anti-pollution energy-saving control subsystem as an example, the time and quantity are accurately controlled during the treatment of the sewage. The detection methods of the content changes of trace elements in the sewage treatment tank are the same in different anti-pollution energy-saving control subsystems, and all can achieve the purpose of anti-pollution energy saving. The sewage first enters the sedimentation tank in the sewage treatment platform, and the solid particles in the sewage are filtered out after sedimentation. A plurality of sewage treatment tanks are arranged in series in the sewage treatment platform, and each sewage treatment tank can reduce the content of at least one trace element in the sewage. A plurality of sampling devices 10 are installed in each sewage treatment tank, which collect sewage samples in the sewage treatment tank, detect the treated sewage, and obtain the content of trace elements in the sewage. The sampling and detection methods of the sewage samples use existing technologies. The trace elements include cyanide elements, sulfur elements, chlorine elements, phosphorus elements, etc.

[0035] The step A has the beneficial effects that: according to the different functions of different departments and wards of the hospital, the hospital sewage is classified and discharged and treated, which effectively prevents secondary pollution, fundamentally controls pollution, reduces the workload of subsequent sewage treatment, and saves costs.

[0036] In some embodiments, step B further comprises:

[0037] Step B1: the sampling device 10 detects different contents of the trace elements in each sewage treatment tank with the change of time for multiple times, the sampling device 10 sends the collected data to the subsystem processor 30, which is received by the data collection module 301 in the subsystem processor 30, the environmental factors in the sewage treatment tank remain unchanged, and each sampling device 10 corresponds to one sampling point. Let the content of the trace elements in the sewage treatment tank obtained by n times of detection at s sampling points be:

[0038]

[0039] The interval time of n times of detection at s sampling points is consistent. The neural network model construction module 302 constructs a neural network model of the content change of the trace elements, and performs function fitting on the content change of the trace elements in each sewage treatment tank in sequence with time.

[0040] In some embodiments, step B further includes:

[0041] Step B2: The trace element content variation neural network includes an input layer, a test layer, an activation layer, a fitting layer, and an output layer.

[0042] B21. The content *r* of trace elements in the wastewater treatment pond from *s* sampling points in *n* measurements is input into the input layer of a neural network for trace element content variation. The input layer has *n*×*s* neurons, and the *n*×*s* input data are normalized using the following normalization formula:

[0043]

[0044] in, To Normalized data, This represents the trace element content obtained in the i-th detection at sampling point j, where i∈[1,n], j∈[1,s]. The minimum value in the input data. The maximum value in the input data. The input layer sends the processed data to the validation layer;

[0045] B22. The test layer uses the covariance function of the trace element content data to perform a pooled test, and the pooled test formula is as follows:

[0046]

[0047] in, Let d represent the sample covariance function. j,j+1 The distance between the j-th sampling point and the (j+1)-th sampling point is represented by t, where t is the monitoring time interval. The mixed testing rule for trace element content detection is as follows: if the difference in trace element content obtained from different sampling points in the same test is less than a preset threshold, it indicates that the trace elements in the wastewater are sufficiently mixed. Sufficiently mixed sampling data can more accurately represent the trace element content in the wastewater. The testing layer has a testing instruction interface. If the result does not meet the testing rules, the sampling data for this batch is discarded, and the testing instruction interface sends an instruction to the input layer to test the next batch of sampling data. If the result exceeds the testing rules, the testing layer sends the data to the activation layer.

[0048] B23. The activation layer activates the data, and the activation function is:

[0049]

[0050] The activation layer sends the activated data to the fitting layer;

[0051] B24. The fitting layer analyzes the trace element content of the time series using the autocorrelation function and the partial autocorrelation function of the time series, and the autocorrelation function of the time series is:

[0052]

[0053] wherein p j is the autocorrelation function of the time series at the jth sampling point, w j is the weight proportion of the jth sampling point.

[0054] The partial autocorrelation function is calculated according to the autocorrelation function of the time series:

[0055]

[0056] wherein, is the partial autocorrelation function of the time series at the jth sampling point. The fitting formula is obtained by using the likelihood function:

[0057]

[0058] wherein, is the fitting formula of the trace element content change at the jth sampling point, s 2 is the variance of the input data. The fitting layer sends the result to the output layer, and the output layer outputs the fitting formula.

[0059] The beneficial effect of step B is to construct a trace element content change neural network, to functionally fit the time series content change of each trace element in the sewage treatment tank, to control the sewage treatment time, to improve the sewage treatment efficiency, to reduce unnecessary energy waste in the sewage treatment process, and to achieve the purpose of pollution prevention and energy saving.

[0060] In some embodiments, the hospital building water system pollution prevention and energy saving control method further comprises step C: after all the sewage treatment processes are completed, the content of each trace element in the sewage is obtained, the organic coefficient in the treated sewage is calculated, and if the organic coefficient d is less than the preset threshold value, the sewage treatment is qualified; otherwise, the sewage needs to be treated in the enhanced tank.

[0061] In some embodiments, step C further comprises:

[0062] The trace element content change fitting formula obtained by the trace element content change neural network can calculate the time when the trace element content in the sewage meets the standard, and the anti-pollution energy-saving control module 304 sends a control instruction to the valve controller 20 of the sewage treatment tank according to the time when the trace element content in the sewage treatment tank meets the standard, so that when the sewage in the current sewage treatment tank meets the standard when flowing to the next sewage treatment tank, the sewage can be continuously injected into the first sewage treatment tank, and the sewage treatment efficiency is improved.

[0063] When all the sewage treatment processes are completed, the anti-pollution auditing module 305 obtains the content of each trace element in the sewage, and calculates an organic coefficient of the treated sewage, and the formula of the organic coefficient is:

[0064] delta = omega k r k

[0065] Wherein, delta is the organic coefficient of the sewage, r k is the content of the kth trace element, and omega k is the weight of the kth trace element, which is set by the staff according to experience. If the organic coefficient delta is less than a preset threshold, the sewage treatment is qualified; otherwise, the sewage needs to be treated in a strengthened tank.

[0066] The present application is described with reference to flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a means for implementing the functions specified in the flowcharts and / or block diagrams. Figure 1 The functions specified in one flow or multiple flows and / or blocks Figure 1 The means for implementing the functions specified in one block or multiple blocks.

[0067] These computer program instructions can also be loaded into a computer or other programmable data processing device to cause a series of operation steps to be performed on the computer or other programmable data processing device to generate a computer-implemented process, so that the instructions executed on the computer or other programmable data processing device provide a means for implementing the functions specified in the flowcharts and / or block diagrams. Figure 1 The functions specified in one flow or multiple flows and / or blocks Figure 1 The steps for implementing the functions specified in one block or multiple blocks.

[0068] While the preferred embodiments of the application have been described, additional variations and modifications can be made to these embodiments by those skilled in the art once they have the benefit of the present disclosure without departing from the spirit and scope of the application. Accordingly, it is intended that the appended claims include all such modifications and variations as fall within the scope of the present application.

[0069] It is apparent that those skilled in the art can make various changes and modifications to the application without departing from the spirit and scope of the application. It is therefore intended that the present application cover all such changes and modifications that are within its scope.

Claims

1. A hospital building water system anti-fouling energy saving control system, characterized in that, The system comprises a plurality of subsystems, including: A sampling device is arranged in the sewage treatment tank to collect sewage samples in the sewage treatment tank, detect the treated sewage, acquire and transmit trace element content data in the sewage; The subsystem processor is in data connection with the sampling device, receives the trace element content data transmitted by the sampling device, constructs a trace element content change neural network model, functionally fits the content change of the trace elements in each sewage treatment tank in sequence with time, obtains a trace element content change fitting formula, calculates the time when the trace element content in the sewage meets the standard, and transmits the time when the trace element content meets the standard; The valve controller is in data connection with the subsystem processor, and is used to control the opening and closing of the valve of the sewage treatment tank according to the received time when the trace element content meets the standard; The neural network for measuring the variation of trace element content includes an input layer, a test layer, an activation layer, a fitting layer, and an output layer; each sampling device corresponds to one sampling point, assuming the trace elements in the wastewater treatment tank are at... sampling points The content obtained from the second test was: ； The n detection intervals of the s sampling points are consistent; The input layer uses the following input data normalization processing formula: ； wherein, is the normalized data, is the normalized data, represents the trace element content obtained in the first detection at the sampling point j represents the trace element content obtained in the second detection at the sampling point i represents the trace element content obtained in the third detection at the sampling point , , is the minimum value in the input data, is the maximum value in the input data; the input layer sends the processed data to the verification layer; The hybrid test formula of the test layer is: ； wherein, denotes the sample covariance function, denotes the Euclidean distance between the th sample point and the th sample point, is the monitoring time interval; The activation function of the activation layer is: ； The activated data is sent to the fitting layer by the activation layer; the fitting layer analyzes the time sequence of the trace element content by using the autocorrelation function and the partial autocorrelation function of the time sequence, and the autocorrelation function of the time sequence is: ； wherein, is the time series autocorrelation function of the first sample point, is the weight proportion of the first sample point; and calculating the partial autocorrelation function according to the autocorrelation function of the time series: ； wherein is the time series partial autocorrelation function for the th sample point; and the fit is performed using a likelihood function, the fit being given by: ； wherein, is the fitted formula of the trace element content variation of the th sampling point, is the variance of the input data; the fitting layer sends the result to the output layer, and the output layer outputs the fitted formula; The trace elements include cyan elements, sulfur elements, chlorine elements and phosphorus elements.

2. The anti-fouling energy saving control system for hospital building water system according to claim 1, characterized in that, The subsystem processor comprises: A data acquisition module is used to receive and transmit the trace element content data from the sampling device; A neural network model construction module is in data connection with the data acquisition module, and is used to construct a trace element content change neural network model, functionally fit the content change of the trace elements in each sewage treatment tank in sequence with time, and obtain a trace element content change fitting formula; A calculation module is in data connection with the neural network model construction module, and is used to receive the trace element content change fitting formula, calculate and transmit the time when the trace element content in the sewage meets the standard; An anti-fouling energy-saving control module is in data connection with the calculation module, and is used to acquire the time when the trace element content in the sewage meets the standard and issue a control instruction to the valve controller.

3. The anti-fouling energy saving control system for hospital building water system according to claim 2, characterized in that, The subsystem processor further comprises an anti-fouling audit module in data connection with the data acquisition module, which is used to acquire the trace element content data in the treated sewage and determine whether the treated sewage is qualified.

4. The anti-fouling energy saving control system for hospital building water system according to claim 3, characterized in that, The anti-fouling audit module can calculate the organic coefficient in the treated sewage, and if the organic coefficient is less than a preset threshold, the sewage treatment is qualified, otherwise the sewage enters a strengthened tank for strengthened treatment.

5. A method for preventing contamination and saving energy in a water system of a hospital building, characterized by, The anti-fouling energy-saving control system for the hospital building water system according to any one of claims 1-4 further comprises: Step A: According to the properties and characteristics of the sewage, the hospital sewage is divided into a plurality of zones, and the sewage in a plurality of sewage treatment tanks connected in series in different zones is collected and detected to acquire the content of trace elements in the sewage; Step B: obtain the content change value of the trace element in each sewage treatment tank over time, construct a trace element content change neural network, functionally fit the content change of the trace element in each sewage treatment tank in sequence over time, obtain a trace element content change fitting formula, calculate the time when the content of the trace element in the sewage reaches the standard, and control the sewage treatment time; The content of trace elements in sewage treatment tank is determined by the method at one sampling point times ； The n detection intervals of the s sampling points are consistent in length; The step B comprises: Step B2: the trace element content change neural network comprises an input layer, a verification layer, an activation layer, a fitting layer, and an output layer; B21. The content of trace elements in the sewage treatment tank is detected in a sampling point for several times The input layer of the trace element content change neural network is input, the input layer has neurons, which respectively normalize input data, and the normalization formula is: ； wherein, is the normalized data, is the normalized data, represents the trace element content obtained in the first detection at the sampling point j is the normalized data, i is the normalized data, , , is the minimum value in the input data, is the maximum value in the input data; the processed data is sent by the input layer to the verification layer; B22. The verification layer uses a covariance function of the trace element content data for mixed verification, and the mixed verification formula is: ； wherein, represents a sample covariance function, represents the Euclidean distance between the th sampling point and the th sampling point, is a monitoring time interval; the mixed test rule for the trace element content detection is that the difference in the trace element content obtained by different sampling points in the same detection is less than a preset threshold value, indicating that the trace elements in the sewage are mixed sufficiently, and the sampling data for the sufficient mixing can more accurately represent the trace element content in the sewage; the test layer is provided with a test instruction interface, if the result does not comply with the test rule, the sampling data of the batch is abandoned, and the test instruction interface sends a test instruction for the next batch of sampling data to the input layer; if the result complies with the test rule, the test layer sends the data to the activation layer; B23. The activation layer activates the data, and the activation function is: ； The activated data is sent to the fitting layer by the activation layer; B24. The fitting layer analyzes the time series trace element content using an autocorrelation function and a partial autocorrelation function of the time series, and the autocorrelation function of the time series is: ； wherein, is the time series autocorrelation function for the first is the time series autocorrelation function for the first is the weight proportion for the first is the weight proportion for the first ； wherein is the time series partial autocorrelation function for the sample point; the fit is performed using a likelihood function, the fit formula being: ； wherein, is the fitted formula for the trace element content variation of the th sampling point, is the variance of the input data; the fitting layer sends the result to the output layer, and the output layer outputs the fitted formula.

6. The anti-fouling energy saving control method of a hospital building water system according to claim 5, characterized by, Further comprising step C: after all sewage treatment processes are completed, the content of each trace element in the sewage is obtained, the organic coefficient in the treated sewage is calculated, and if the organic coefficient δ is less than a preset threshold value, the sewage treatment is qualified; otherwise, the sewage needs to be treated in a strengthening tank.

Images