Intelligent operation and maintenance management system for mine drainage water treatment equipment based on Internet of Things

Abstract

The invention relates to the technical field of water treatment equipment management, in particular to an intelligent operation and maintenance management system for mine drainage water treatment equipment based on the Internet of Things, and the system comprises a data collection module which is used for collecting the operation parameters of the water treatment equipment during drainage water treatment and the water quality parameters of drainage water treatment; the operation parameters comprise a flow parameter and a pressure parameter; the flow parameters comprise the flow of the input end of the ultrafiltration membrane assembly and the flow of the output end of the ultrafiltration membrane assembly; the pressure parameters comprise corresponding water inlet pressure, water outlet pressure and backwashing pressure when the mine drainage water enters the ultrafiltration membrane assembly; the drainage water pretreatment module is used for pretreating mine drainage water and determining the change trend of water quality parameters after pretreatment; the ultrafiltration membrane assembly module is used for treating the pretreated mine drainage water and determining the change trend of a flow parameter and the change trend of a pressure parameter when the mine drainage water is filtered; the operation efficiency and the treatment effect of the water treatment equipment are realized, and the stability of water quality is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of water treatment equipment management, and in particular to an intelligent operation and maintenance management system for mine drainage water treatment equipment based on the Internet of Things. Background Art

[0002] The discharge of mine drainage water not only wastes a large amount of precious groundwater resources, but also causes a series of serious environmental pollution problems. Treating and utilizing mine water can not only prevent the loss of water resources and avoid pollution to the water environment, but also has important significance for alleviating the shortage of water supply in mining areas, improving the ecological environment in mining areas, and meeting the needs of production and life to the maximum extent. Most of the mine drainage water is deep groundwater with excellent water quality, but it is polluted by humans during the mining process. The drainage volume of mines is relatively stable throughout the year during the mining process, and can be used as a stable water supply source after treatment.

[0003] In the process of mine drainage water treatment, traditional operation and maintenance management methods often rely on manual monitoring and operation. This method is not only inefficient, but also difficult to grasp the operating status of water treatment equipment and water quality changes in real time and accurately. Summary of the invention

[0004] In order to solve the above technical problems, the technical solution adopted by the present invention is: an intelligent operation and maintenance management system for mine drainage water treatment equipment based on the Internet of Things, including: a data acquisition module for collecting operating parameters of water treatment equipment during drainage water treatment and water quality parameters of drainage water treatment; operating parameters include flow parameters and pressure parameters; flow parameters include the flow rate at the input end of the ultrafiltration membrane component and the flow rate at the output end of the ultrafiltration membrane component; pressure parameters include the water inlet pressure, water outlet pressure, and backwash pressure corresponding to the mine drainage water entering the ultrafiltration membrane component.

[0005] Drainage water pretreatment module, used to pre-treat mine drainage water and determine the change trend of water quality parameters after pre-treatment;

[0006] The ultrafiltration membrane component module is used to process the pre-treated mine drainage water and determine the change trend of the flow parameter and the change trend of the pressure parameter during the filtration of the mine drainage water.

[0007] The backwash device module is used to backwash the ultrafiltration membrane and adjust the backwash strategy according to the changing trend of the flow parameter and the changing trend of the pressure parameter.

[0008] The control module is used to determine the stability of water quality treatment according to the changing trend of water quality parameters, the changing trend of flow parameters and the changing trend of pressure parameters.

[0009] The beneficial effects of the present invention are as follows: the present invention identifies the changing trends of water quality parameters, flow parameters and pressure parameters by analyzing the pre-treated data; based on these changing trends, the stability of water quality treatment is intelligently judged, and the operation strategy of the water treatment equipment is adjusted in real time; by real-time monitoring the flow at the input and output ends of the ultrafiltration membrane assembly, as well as the water inlet pressure, water outlet pressure and backwash pressure, precise control of the flow and pressure parameters is achieved; when abnormal flow or pressure is detected, the system automatically adjusts the backwash strategy to ensure the normal operation of the ultrafiltration membrane and the stability of water quality; using the changing trend of water quality parameters as an input vector, the MLP model is used for in-depth analysis to evaluate the stability of water quality treatment; according to the output results of the MLP model, the water treatment strategy is adjusted in real time to ensure the continuous stability of water quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The present invention is further described below in conjunction with the accompanying drawings and embodiments.

[0011] Figure 1 It is a system diagram of the intelligent operation and maintenance management system of mine drainage water treatment equipment based on the Internet of Things.

[0012] Figure 2 It is a schematic diagram of the implementation of the intelligent operation and maintenance management system of mine drainage water treatment equipment based on the Internet of Things. DETAILED DESCRIPTION

[0013] The embodiments of the present invention are described in detail below. The embodiments described below are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention. If no specific techniques or conditions are specified in the embodiments, the techniques or conditions described in the literature in the art or the product specifications are used.

[0014] See also Figure 1 , Figure 2 The intelligent operation and maintenance management system of mine drainage water treatment equipment based on the Internet of Things includes: data acquisition module, drainage water pretreatment module, ultrafiltration membrane component module, backwash device module and control module.

[0015] The data acquisition module is connected with the drain water pretreatment module and the ultrafiltration membrane assembly module through sensors to obtain data of the drain water pretreatment module and the ultrafiltration membrane assembly module in real time; the data acquisition module communicates with the control module wirelessly to transmit the collected data to the control module for analysis and processing; the drain water enters the drain water pretreatment module through a pipeline, and the pretreated water enters the ultrafiltration membrane assembly module through a pipeline for further purification; the ultrafiltration membrane assembly module is connected with the backwashing device module; the ultrafiltration membrane assembly module receives instructions from the control module to reflect the purification effect of the drain water; the backwashing device module is connected with the control module, and the backwashing device module receives instructions from the control module to backwash the ultrafiltration membrane in the ultrafiltration membrane assembly module.

[0016] The data acquisition module is used to collect the operating parameters of the water treatment equipment during the drainage water treatment and the water quality parameters of the drainage water treatment; the operating parameters include flow parameters and pressure parameters.

[0017] The drainage water pretreatment module is used to pretreat the mine drainage water and determine the change trend of the water quality parameters after pretreatment.

[0018] The ultrafiltration membrane component module is used to treat the pre-treated mine drainage water. Through the screening mechanism, the particles and macromolecules larger than the ultrafiltration membrane pores are retained to purify the mine drainage water and determine the changing trends of the flow parameters and pressure parameters during the filtration of the mine drainage water.

[0019] The backwash device module is used to backwash the ultrafiltration membrane to remove the deposited dirt on the surface of the ultrafiltration membrane, prevent the ultrafiltration membrane from being polluted and blocked, and adjust the backwash strategy according to the changing trend of the flow parameter and the changing trend of the pressure parameter.

[0020] The control module is used to determine the stability of water quality treatment according to the changing trend of water quality parameters, the changing trend of flow parameters and the changing trend of pressure parameters.

[0021] Various sensors are used to obtain operating parameters and water quality parameters, including: water quality sensors, flow meters, and pressure sensors.

[0022] Water quality parameters include the corresponding contents of Fe, Mn, sulfate, total hardness, fluoride ion, turbidity, zinc, chlorite, and chromaticity; flow parameters include the flow at the input end of the ultrafiltration membrane component and the flow at the output end of the ultrafiltration membrane component; pressure parameters include the inlet pressure, outlet pressure, and backwash pressure corresponding to the mine drainage water entering the ultrafiltration membrane component.

[0023] Water quality sensors are used to obtain parameters related to water treatment, such as Fe, Mn, sulfate, total hardness, fluoride, turbidity, zinc, chlorite, and color, to determine the changes in corresponding parameters during the treatment of each module of the current water treatment, thereby identifying whether the current treated water quality can reach the reference level.

[0024] The hardness obtained by the water quality sensor refers to the total concentration of metal ions such as calcium and magnesium contained in the water, usually expressed as the content of calcium carbonate. Hardness is an important indicator of water quality. It reflects the mineral content in the water and has a certain impact on the taste of water, washing effect and human health.

[0025] The chromaticity obtained by the water quality sensor refers to the color depth of water dissolved or suspended in water under the influence of natural or human factors; it reflects the impact of various dissolved substances, microorganisms, suspended matter and bottom soil in the water on the water color; chromaticity is an important aspect of the appearance characteristics of water bodies and is also an indicator for evaluating the cleanliness of water quality.

[0026] The flow meter is used to determine the flow rate of mine drainage water when the membrane assembly is filtering to ensure the stability of the flow rate; the acquisition of flow parameters is mainly to determine the flow rate of water passing through the ultrafiltration membrane in the ultrafiltration membrane assembly during backwashing and normal filtration, thereby ensuring the stability of the flow rate during water filtration and backwashing of the membrane assembly, thereby improving the utilization rate of the membrane assembly.

[0027] The pressure sensor is used to obtain the pressure difference inside the membrane assembly, including the corresponding water inlet pressure, water outlet pressure, and backwash pressure during water treatment. The water inlet pressure and water outlet pressure can obtain the trans-membrane pressure difference of water treatment, and the degree of contamination of the membrane assembly can be determined according to the change of the trans-membrane pressure difference; the water outlet pressure can reflect the treatment efficiency of the membrane assembly, and the backwash pressure indicates the pressure used when backwashing the membrane assembly to prevent damage to the membrane assembly.

[0028] In one embodiment of the present invention, the implementation method of pre-treating mine drain water in the drain water pre-treatment module includes: inputting the mine drain water into the mixing tank, performing preliminary physical and chemical treatment on the mine drain water, the preliminary physical and chemical treatment is sedimentation and coagulation, and inputting the mine drain water after sedimentation and coagulation treatment into the intermediate water tank, and determining the change of water quality parameters according to the water quality parameters of the intermediate water tank and the mine drain water when it is input; at the same time, obtaining the change of water quality parameters when the intermediate water tank passes to the multi-media filter, and determining the final value of the water quality parameters after completing the ultrafiltration treatment.

[0029] In one embodiment of the present invention, the changing trend of the flow parameters in the ultrafiltration membrane component module is expressed as: obtaining the flow at the input end of the ultrafiltration membrane component when entering the ultrafiltration membrane, and judging whether the flow at the input end of the ultrafiltration membrane component is greater than a first preset value, and the first preset value is used to determine whether the current input flow is a normally processed flow.

[0030] If the flow rate is greater than the first preset value, a first flow difference entering the input end of the ultrafiltration membrane component is obtained. The first flow difference is obtained by calculating the difference between the real-time flow value of the flow entering the input end of the ultrafiltration membrane component within a preset time period and the first preset value; the preset time period is expressed as a time period of 1 hour, 3 hours, 1 day, and 7 days to determine the change in flow within a fixed preset time period.

[0031] Obtain the time period when the flow at the input end of the ultrafiltration membrane assembly reaches a first preset value, and calculate a first average difference based on the first flow difference; determine a second preset value based on the obtained first average difference, and the second preset value is the sum of the first average difference and the first preset value.

[0032] Determine whether the real-time flow value will exceed the second preset value, mark the flow that exceeds the second preset value, obtain a third preset value, the third preset value is the second preset value plus half of the first average difference, and adjust the flow at the input end of the ultrafiltration membrane assembly until the flow at the input end of the ultrafiltration membrane assembly is between the first preset value and the third preset value.

[0033] Record the time period when the flow at the input end of the ultrafiltration membrane assembly is between the first preset value and the third preset value, determine the flow at the output end of the ultrafiltration membrane assembly at this time, and obtain a second flow difference according to the flow at the output end of the ultrafiltration membrane assembly; the second flow difference is the difference between the flow at the output end of the ultrafiltration membrane assembly and the first preset value, which is used to determine the change in the flow of the water body after filtration, to determine the filtration of impurities such as particles and large molecular organic matter in the water by the currently used ultrafiltration membrane, and at the same time, the second flow difference can represent the difference in flow between the output end and the input end of the ultrafiltration membrane assembly when a higher amount of water passes through the ultrafiltration membrane, to assist in determining the stability of the use of the ultrafiltration membrane assembly and whether the current device operation is stable.

[0034] Determine the change size of the first flow difference and the second flow difference; and generate a flow change trend according to the time period, process the flow change trend, and use the processed flow change trend as the change trend of the output flow parameter.

[0035] The performance status of the ultrafiltration membrane will be highlighted in the change of the flux of the ultrafiltration membrane. The flux of the ultrafiltration membrane refers to the amount of water passing through a unit membrane area per unit time; the change in water flow before and after treatment can intuitively reflect the change in membrane flux; if the water flow after treatment decreases significantly, it may mean that the membrane flux has decayed, which may be caused by membrane pollution, blockage or aging. At the same time, to determine the ultrafiltration membrane flow rate, it is also necessary to determine the corresponding pressure parameters. Increasing the pressure within a certain range can increase the membrane flux of the ultrafiltration membrane.

[0036] At this time, the change in water flow before and after treatment can reflect the influence of operating pressure on membrane flux. When the working pressure is less than 0.3MPa, the water production rate of the ultrafiltration membrane is proportional to the pressure; when the pressure reaches above 0.3MPa, the water production basically no longer increases; therefore, the pressure parameters corresponding to the ultrafiltration membrane assembly should be obtained at this time to determine whether the pressure parameters affect the filtration of the ultrafiltration membrane.

[0037] The method for processing the flow rate change trend includes calculating the autocorrelation coefficient and the predictable condition corresponding to the first flow rate difference and the second flow rate difference.

[0038] The autocorrelation coefficient corresponding to the first flow difference and the second flow difference is expressed as follows: determine the mean of the first flow difference and the second flow difference, calculate the covariance of the first flow difference and the second flow difference based on the mean of the first flow difference and the second flow difference, and obtain the autocorrelation coefficient of the first flow difference and the second flow difference according to the covariance of the first flow difference and the second flow difference; the autocorrelation coefficient is used to detect whether there is a periodic pattern in the current flow change trend, and whether the current trend is a monotonic trend or a seasonal trend, and output the flow change trends corresponding to this part respectively, so as to facilitate the subsequent analysis of flow parameters, pressure parameters, and water quality parameters according to different trend time periods, so as to obtain more accurate analysis results.

[0039] The calculation method for the autocorrelation coefficient is as follows: given a time series {S 1 ,S 2 ,,,S t}, t = 1, 2,,, T; the value of each time point in the time series can represent the value corresponding to the first flow difference and the second flow difference. First, the mean is calculated. in, is the mean of the time series, T represents the length of the time series, S t is the value of the time series at time point t; then calculate the k-th order covariance γ of the time series k , When k = 0, γ 0 That is the variance of the time series; the autocorrelation coefficient is finally calculated The above k represents the lag order, which is the number of time steps between two values ​​in the time series, so as to determine the overall trend of traffic change when identifying trends, S t+k It is the value of the time series at time point t plus k lag orders.

[0040] The predictable condition corresponding to the first flow difference and the second flow difference is expressed as obtaining the error term of the first flow difference and the second flow difference, the error term of the first flow difference and the second flow difference is the difference between the current first flow difference and the second flow difference and the predicted value, and the predicted value in each time period in the flow change trend is the moving average of the error term of the previous time period multiplied by the error coefficient plus the constant term; the error coefficient is used to adjust according to the value of the error term in each time period.

[0041] The error term between the first flow difference and the second flow difference is determined by comparing the current first flow difference and the second flow difference with the predicted value.

[0042] The flow change trends that meet the predictable conditions corresponding to the calculation of the first flow difference and the second flow difference are classified according to the trend of the autocorrelation coefficient, and the classified flow change trends are output.

[0043] At this time, classification according to the trend of the autocorrelation coefficient includes: if the autocorrelation coefficient decreases rapidly to close to 0 as the lag order increases, the corresponding flow change trend is classified into one category; if the autocorrelation coefficient has a peak at a specific lag order, the corresponding flow change trend is classified into one category; if the autocorrelation coefficient decays slowly, the corresponding flow change trend is classified into one category.

[0044] The purpose of classification according to the trend of the autocorrelation coefficient at this time is to divide the autocorrelation coefficient according to the different displays of flow change trends; the autocorrelation coefficient decreases rapidly to close to 0 with the increase of the lag order, indicating that the correlation between flow data is very weak, that is, there is almost no correlation between the current flow value and the past flow value; the existence of a peak in the autocorrelation coefficient at a specific lag order indicates that the flow data has a strong correlation within a specific time interval, that is, there is a correlation between the current flow value and the flow value at a specific time point in the past; the slow decay of the autocorrelation coefficient indicates that the correlation between flow data is strong, and this correlation slowly weakens over time.

[0045] At this time, the flow change trend is divided according to the situation corresponding to the identified autocorrelation coefficient, so as to find the correlation between the flow data in different time periods, and then the flow change trend is classified according to the trend in different time periods.

[0046] In one embodiment of the present invention, the method for identifying the change trend of the pressure parameter in the ultrafiltration membrane component module is as follows.

[0047] When the flow rate at the input end and the flow rate at the output end of the ultrafiltration membrane assembly change, the corresponding water inlet pressure, water outlet pressure and backwash pressure of the ultrafiltration membrane assembly are obtained.

[0048] Determine the transmembrane pressure difference according to the corresponding inlet water pressure and outlet water pressure when the flow rate changes; the transmembrane pressure difference is the difference between the inlet water pressure and the outlet water pressure; based on the obtained transmembrane pressure difference, determine the first change curve corresponding to the transmembrane pressure difference; and determine the second change curve corresponding to the inlet water pressure and the third change curve of the outlet water pressure corresponding to the transmembrane pressure difference.

[0049] Based on the acquired first change curve, determine the change interval corresponding to the change of the first change curve, and determine whether the maximum value of the first change curve is within the preset range of the transmembrane pressure difference; if the maximum value of the first change curve is within the preset range of the transmembrane pressure difference, determine the second correlation between the water inlet pressure corresponding to each transmembrane pressure difference and the second change curve, and determine the third correlation between the water outlet pressure corresponding to each transmembrane pressure difference and the third change curve; use the comparison result of the second correlation and the third correlation as the change trend of the output pressure parameter.

[0050] For the set transmembrane pressure difference, the maximum transmembrane pressure difference is not greater than 0.2MPa; and can be set to a smaller value according to system requirements, such as less than 80KPa (0.08MPa).

[0051] If the maximum value of the first variation curve is less than the lower limit of the preset range of the transmembrane pressure difference, a first correlation of the first variation curve is determined, and the first variation curve is used as a variation trend of the output pressure parameter.

[0052] If the maximum value of the first change curve is greater than the upper limit value of the preset range of the transmembrane pressure difference, obtain the fourth change curve corresponding to the backwash pressure, as well as the corresponding change of the transmembrane pressure difference when the backwash pressure changes, and determine the fourth correlation between the backwash pressure corresponding to the transmembrane pressure difference and the fourth change curve; use the fourth change curve as the change trend of the output pressure parameter.

[0053] At this time, the upper limit value exceeding the preset range indicates that the ultrafiltration membrane may be obviously contaminated and needs to be backwashed, and the correlation between the corresponding parameters during the backwash operation needs to be determined to assist in adjusting the pressure used during backwashing; the changes in the pressure parameters that need to be centrally processed at this time are represented by the set fourth change curve, so that the performance of the current ultrafiltration membrane can be restored in time; if the current maximum value of the first change curve does not reach the lower limit value of the preset range, it means that the current transmembrane pressure difference does not meet the requirements, and the central processing at this time is how the transmembrane pressure difference is caused; if the current maximum value of the transmembrane pressure difference is always within the preset range, then the water inlet pressure and the water outlet pressure need to be processed, that is, the second correlation and the third correlation are determined, so that the working environment of the current ultrafiltration membrane component can be adjusted in time.

[0054] The first correlation, the second correlation, the third correlation, and the fourth correlation are all obtained in the same way, and the Pearson correlation coefficient is used to represent the first correlation, the second correlation, the third correlation, and the fourth correlation.

[0055] The first correlation is to calculate the Pearson correlation coefficient between the corresponding transmembrane pressure difference and all the index values ​​in the first change curve when the maximum value of the first change curve is less than the lower limit value of the preset range of the transmembrane pressure difference.

[0056] The second correlation is the Pearson correlation coefficient between the corresponding water inlet pressure when the maximum value of the first change curve is within the preset range of the transmembrane pressure difference and all the index values ​​in the second change curve.

[0057] The third correlation is the Pearson correlation coefficient between the outlet water pressure corresponding to when the maximum value of the first variation curve is within the preset range of the transmembrane pressure difference and all the index values ​​in the third variation curve.

[0058] The fourth correlation is the Pearson correlation coefficient between the backwash pressure corresponding to when the maximum value of the first variation curve is greater than the upper limit value of the preset range of the transmembrane pressure difference and all the index values ​​in the fourth variation curve.

[0059] The implementation method for comparing the second correlation and the third correlation is as follows.

[0060] Obtain the difference value between the second correlation and the third correlation, which is obtained by subtracting the Pearson correlation coefficient of the second correlation from that of the third correlation; determine the outlet water pressure and inlet water pressure corresponding to when the difference value between the second correlation and the third correlation takes a maximum value, and use the data of the time period corresponding to the outlet water pressure and inlet water pressure corresponding to when the difference value takes a maximum value as the output comparison result of the second correlation and the third correlation.

[0061] At this time, the data of the corresponding time period of the water outlet pressure and water inlet pressure when the difference value takes the maximum value represents all the water inlet pressures and water outlet pressures existing in the time period when the difference value of the second correlation and the third correlation reaches the maximum. In this way, when there is a large difference between the water inlet pressure and the water outlet pressure, the changes in the current water inlet and water outlet pressures can be identified, thereby analyzing these data to improve the analysis effect of the data.

[0062] In one embodiment of the present invention, the backwash device module adjusts the backwash strategy according to the change trend of the flow parameter and the change trend of the pressure parameter as shown below.

[0063] Based on the obtained flow change trend, the change amplitude of the first flow difference and the second flow difference is calculated, the time corresponding to the minimum index value in the flow change trend is obtained, and the minimum input flow at the input end of the ultrafiltration membrane component at that time is obtained. The current input flow is corrected by the ratio of the minimum input flow to the maximum input flow at the input end of the ultrafiltration membrane component to adjust the input flow rate.

[0064] By calculating the ratio of the minimum input flow to the maximum input flow, it can be determined whether the current flow is within the ideal operating range; if the current flow is not within the ideal range, the flow can be adjusted by adjusting the pump speed, valve opening, or changing the pipeline configuration; if the current flow is less than the minimum input flow, the flow can be increased by increasing the pump speed; conversely, if the flow is greater than the maximum input flow, the pump speed can be reduced to reduce the flow.

[0065] Based on the change trend of the obtained pressure parameters, the change amplitude of the backwash pressure is calculated, the time corresponding to the maximum index value of the backwash pressure change amplitude is determined, and the minimum value of the transmembrane pressure difference at the corresponding time is obtained. The backwash pressure is adjusted according to the maximum index value of the backwash pressure change amplitude and the minimum value of the transmembrane pressure difference at the corresponding time.

[0066] The backwash pressure and transmembrane pressure difference under normal settings are in a fixed ratio. For example, the backwash pressure can be set to 1.5 to 2 times of the normal working transmembrane pressure difference. The adjustment method at this time is that when the backwash pressure changes the most, it cannot exceed the bearing pressure of the ultrafiltration membrane assembly, that is, the maximum index value of the backwash pressure change range cannot exceed the bearing pressure when the transmembrane pressure difference takes the minimum value, thereby ensuring that the backwash can proceed normally.

[0067] The backwash strategy is adjusted according to the adjusted input flow rate and the adjusted backwash pressure.

[0068] When adjusting the backwash strategy, the flow rate is adjusted by setting the pump and the pressure applied to the ultrafiltration membrane assembly is adjusted to improve the cleaning effect of the ultrafiltration membrane assembly.

[0069] In one embodiment of the present invention, the control module determines the stability of water quality treatment based on the changing trends of water quality parameters, flow parameters and pressure parameters in the following manner: the changing trends of water quality parameters, flow parameters and pressure parameters are converted into input vectors, the input vectors are analyzed using an MLP model, and the stability of water quality treatment is obtained based on the output results of the MLP model.

[0070] The MLP model is used to analyze the changing trends of water quality parameters, flow parameters and pressure parameters. The MLP model includes a hidden layer with three neurons and an output layer with one neuron.

[0071] The changing trends of water quality parameters, flow parameters and pressure parameters are constructed as input vector X = {x 1 ,x 2 ,x 3}, x 1 is the water quality parameter, x 2 is the flow parameter, x 3is the pressure parameter.

[0072] Set the hidden layer weight matrix W h ∈R 3×3 , where each element wij in the hidden layer weight matrix represents the weight of the i-th input to the j-th hidden layer neural unit in the input vector, and R represents a real number set, so the hidden layer weight matrix is ​​a 3×3 real number set.

[0073] Set the hidden layer bias vector b h ∈R 3 , the hidden layer bias vector is a vector of length 3.

[0074] Set the output layer weight vector W 0 ∈R 3 , the output layer weight vector is a vector of length 3.

[0075] Set the output layer bias vector b 0 ∈R, the output layer bias vector is a vector of length 1.

[0076] Determine the hidden layer output H: H = σ (W h X+b h ), where σ is an activation function, such as ReLU or Sigmoid.

[0077] Determine the output layer output: Y = W 0 H+b h ; Where Y is the predicted value of water quality parameters after processing.

[0078] Obtain the predicted values ​​of water quality parameters after processing and the standard values ​​of water quality parameters, and determine the loss rate of water quality parameters.

[0079] Among them, L is the loss rate of water quality parameters, Y i is the predicted value of the i-th water quality parameter after processing, Y i ′ is the standard value of the i-th water quality parameter; N is the number of water quality parameters, i=1,2,,,N.

[0080] Since there is more than one water quality parameter in the acquired changing trend of the water quality parameters, when using the MLP model for calculation, the changing trend of the input water quality parameter is compared with the changing trend of the flow parameter and the changing trend of the pressure parameter in turn, and the values ​​of the water quality parameter, flow parameter and pressure parameter at the same time point are determined, and the water quality parameter, flow parameter and pressure parameter are matched one by one; the corresponding water quality parameters, flow parameters and pressure parameters are input into the MLP model until the currently calculated loss rate reaches the optimal value; when the calculated loss rate reaches the optimal value, it means that the current water quality treatment is stable and can meet the required standards.

[0081] Table 1 Water quality of mine drainage water inlet and outlet

[0082]

[0083] As shown in Table 1, the change in flow parameters is determined by obtaining the water quality of the mine drainage water before pretreatment and the water after filtration treatment to determine the change in current water quality, and at the same time, the effect after treatment is determined based on the obtained water quality parameters.

[0084] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations on the present invention. A person skilled in the art may make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention and they are still covered by the protection scope of the present invention.

Claims

1. Intelligent operation and maintenance management system of mine drainage water treatment equipment based on the Internet of Things, It is characterized in that include: A data acquisition module, used to collect the operating parameters of the water treatment equipment during the drainage water treatment and the water quality parameters of the drainage water treatment; The operating parameters include flow parameters and pressure parameters; the flow parameters include the flow at the input end of the ultrafiltration membrane assembly and the flow at the output end of the ultrafiltration membrane assembly; the pressure parameters include the inlet pressure, outlet pressure, and backwash pressure corresponding to the mine drainage water entering the ultrafiltration membrane assembly; Drainage water pretreatment module, used to pre-treat mine drainage water and determine the change trend of water quality parameters after pre-treatment; The ultrafiltration membrane component module is used to process the pre-treated mine drainage water and determine the change trend of the flow parameter and the change trend of the pressure parameter during the filtration of the mine drainage water; The backwash device module is used to backwash the ultrafiltration membrane and adjust the backwash strategy according to the change trend of the flow parameter and the change trend of the pressure parameter; The control module is used to determine the stability of water quality treatment according to the changing trend of water quality parameters, the changing trend of flow parameters and the changing trend of pressure parameters.

2. According to claim 1, the intelligent operation and maintenance management system for mine drainage water treatment equipment based on the Internet of Things, It is characterized in that The water quality parameters include the corresponding contents of Fe, Mn, sulfate, total hardness, fluoride ion, turbidity, zinc, chlorite, and chromaticity.

3. According to claim 1, the intelligent operation and maintenance management system for mine drainage water treatment equipment based on the Internet of Things, It is characterized in that The change trend of the flow parameter is expressed as follows: obtaining the flow at the input end of the ultrafiltration membrane assembly when entering the ultrafiltration membrane, and determining whether the flow at the input end of the ultrafiltration membrane assembly is greater than a first preset value; If the flow rate is greater than the first preset value, a first flow rate difference value of the flow rate at the input end of the ultrafiltration membrane assembly is obtained, wherein the first flow rate difference value is obtained by calculating the difference between the real-time flow rate value of the flow rate entering the input end of the ultrafiltration membrane assembly within a preset time period and the first preset value; Obtaining a time period during which the flow rate at the input end of the ultrafiltration membrane assembly reaches a first preset value, and calculating a first average difference value based on the first flow rate difference value; Determine a second preset value according to the obtained first average difference, where the second preset value is the sum of the first average difference and the first preset value; Determine whether the real-time flow value exceeds the second preset value, mark the flow that exceeds the second preset value, obtain a third preset value, the third preset value is the second preset value plus half of the first average difference, and adjust the flow at the input end of the ultrafiltration membrane assembly until the flow at the input end of the ultrafiltration membrane assembly is between the first preset value and the third preset value; Recording a time period when the flow rate at the input end of the ultrafiltration membrane assembly is between the first preset value and the third preset value, determining the flow rate at the output end of the ultrafiltration membrane assembly at this time, and obtaining a second flow difference value according to the flow rate at the output end of the ultrafiltration membrane assembly; The second flow difference is the difference between the flow at the output end of the ultrafiltration membrane assembly and the first preset value; Determine the change size of the first flow difference and the second flow difference; and generate a flow change trend according to the time period, process the flow change trend, and use the processed flow change trend as the change trend of the output flow parameter.

4. According to claim 3, the intelligent operation and maintenance management system for mine drainage water treatment equipment based on the Internet of Things, It is characterized in that The flow rate change trend is processed by calculating the autocorrelation coefficient and the predictability condition corresponding to the first flow rate difference and the second flow rate difference; The flow change trends that meet the predictable conditions corresponding to the calculation of the first flow difference and the second flow difference are classified according to the trend of the autocorrelation coefficient, and the classified flow change trends are output.

5. According to claim 4, the intelligent operation and maintenance management system for mine drainage water treatment equipment based on the Internet of Things, It is characterized in that The calculation method for the autocorrelation coefficient is as follows: given a time series {S 1 ,S 2 ,,,S t }, t=1,2,,,T, first calculate the mean, in, is the mean of the time series, T represents the length of the time series, S t is the value of the time series at time point t; then calculate the k-th order covariance γ of the time series k , When k = 0, γ 0 That is the variance of the time series; the autocorrelation coefficient is finally calculated The k above represents the lag order, S t+k It is the value of the time series at time point t plus k lag orders.

6. According to claim 4, the intelligent operation and maintenance management system for mine drainage water treatment equipment based on the Internet of Things, It is characterized in that The predictable condition corresponding to the first flow difference and the second flow difference is expressed as obtaining the error term of the first flow difference and the second flow difference, the error term of the first flow difference and the second flow difference is the difference between the current first flow difference and the second flow difference and the predicted value, and the predicted value in each time period in the flow change trend is the moving average of the error term of the previous time period multiplied by the error coefficient plus the constant term.

7. According to claim 1, the intelligent operation and maintenance management system for mine drainage water treatment equipment based on the Internet of Things, It is characterized in that The identification method for the change trend of pressure parameters is: When the flow rate at the input end and the flow rate at the output end of the ultrafiltration membrane assembly change, the inlet pressure, outlet pressure, and backwash pressure corresponding to the ultrafiltration membrane assembly are obtained; Determine the transmembrane pressure difference according to the corresponding inlet pressure and outlet pressure when the flow rate changes; the transmembrane pressure difference is the difference between the inlet pressure and the outlet pressure; determine the first change curve corresponding to the transmembrane pressure difference based on the obtained transmembrane pressure difference; and determine the second change curve corresponding to the inlet pressure and the third change curve of the outlet pressure corresponding to the transmembrane pressure difference respectively; Based on the acquired first change curve, determine the change interval corresponding to the change of the first change curve, and determine whether the maximum value of the first change curve is within the preset range of the transmembrane pressure difference; if the maximum value of the first change curve is within the preset range of the transmembrane pressure difference, determine the second correlation between the water inlet pressure corresponding to each transmembrane pressure difference and the second change curve, and determine the third correlation between the water outlet pressure corresponding to each transmembrane pressure difference and the third change curve; The comparison results of the second correlation and the third correlation are used as the change trend of the output pressure parameter; If the maximum value of the first variation curve is less than the lower limit of the preset range of the transmembrane pressure difference, determining a first correlation of the first variation curve, and using the first variation curve as a variation trend of the output pressure parameter; If the maximum value of the first change curve is greater than the upper limit value of the preset range of the transmembrane pressure difference, obtain the fourth change curve corresponding to the backwash pressure, as well as the corresponding change of the transmembrane pressure difference when the backwash pressure changes, and determine the fourth correlation between the backwash pressure corresponding to the transmembrane pressure difference and the fourth change curve; use the fourth change curve as the change trend of the output pressure parameter.

8. According to claim 7, the intelligent operation and maintenance management system for mine drainage water treatment equipment based on the Internet of Things, It is characterized in that The comparison results of the second correlation and the third correlation are implemented as follows: Obtain the difference value between the second correlation and the third correlation, which is obtained by subtracting the Pearson correlation coefficient of the second correlation from that of the third correlation; determine the outlet water pressure and inlet water pressure corresponding to when the difference value between the second correlation and the third correlation takes a maximum value, and use the data of the time period corresponding to the outlet water pressure and inlet water pressure corresponding to when the difference value takes a maximum value as the output comparison result of the second correlation and the third correlation.

9. According to claim 3, the intelligent operation and maintenance management system for mine drainage water treatment equipment based on the Internet of Things, It is characterized in that According to the changing trend of flow parameters and pressure parameters, the backwash strategy is adjusted as follows: Based on the acquired flow change trend, the change amplitude of the first flow difference and the second flow difference is calculated, the time corresponding to the minimum index value in the flow change trend is obtained, and the minimum input flow at the input end of the ultrafiltration membrane component at this time is obtained, and the current input flow is corrected by the ratio of the minimum input flow at the input end of the ultrafiltration membrane component to the maximum input flow, so as to adjust the input flow rate; Based on the change trend of the obtained pressure parameters, the change amplitude of the backwash pressure is calculated, the time corresponding to the maximum index value of the backwash pressure change amplitude is determined, and the minimum value of the transmembrane pressure difference at the corresponding time is obtained. The backwash pressure is adjusted according to the maximum index value of the backwash pressure change amplitude and the minimum value of the transmembrane pressure difference at the corresponding time; The backwash strategy is adjusted according to the adjusted input flow rate and the adjusted backwash pressure.

10. The intelligent operation and maintenance management system for mine drainage water treatment equipment based on the Internet of Things according to claim 1, It is characterized in that The stability of water quality treatment is determined by converting the changing trends of water quality parameters, flow parameters and pressure parameters into input vectors, analyzing the input vectors using the MLP model, and obtaining the stability of water quality treatment based on the output results of the MLP model.

Images