Eyewasher data monitoring management system and method based on Internet of Things

Abstract

The present invention relates to the field of data monitoring technology, and in particular to an eyewash data monitoring management system and method based on the Internet of Things. The management method comprises the following steps: obtaining a water flow distribution diagram and a cleaning frequency distribution diagram of the eyewash, analyzing the fluctuation degree of the water flow and the variation amplitude of the cleaning frequency; establishing a matching formula between the water flow and the cleaning frequency, and generating a data matching model; monitoring the water flow of the eyewash in real time, analyzing the error degree according to the normal cleaning frequency and the cleaning frequency obtained by monitoring, and adjusting the abnormal data; remotely monitoring the flow, fault, use and other states of the eyewash through the programming of a PLC template, without having to go to great lengths to conduct individual spot checks on each eyewash with a distance difference of several hundred meters, and completing the inspection of the eyewash in the entire factory by checking through an online computer or a mobile phone background, thereby ensuring the normal operation of the eyewash and the life safety of on-site staff.

Description

Technical Field

[0001] The present invention relates to the technical field of data monitoring, and in particular to an eyewasher data monitoring management system and method based on the Internet of Things. Background Art

[0002] An eyewash is a device used for emergency eye flushing, usually in industrial environments or laboratories. When a worker's eyes are splashed with harmful substances or exposed to other chemicals, the eyewash can provide emergency flushing to help clean and flush the eyes, thereby reducing damage; all eyewashes on the market are ordinary eyewashes, or electric heating and electric heating eyewashes. The control circuits use electrical components and wiring to achieve the most basic functions of the eyewash. The PLC control template has functions such as logical operations, input and output control, and data processing. It can control a variety of machines and industrial equipment; it can replace traditional circuit boards to control the various functions and operations of the eyewash;

[0003] Eyewashers need to ensure that users can get effective eye wash in an emergency, which involves the safety and health of users. Therefore, high requirements are placed on the accuracy and real-time nature of the data. The existing solution is to monitor the relevant data of the eyewashers in advance for prevention. However, during the data monitoring process, it will be affected by various factors, and some abnormal data will be omitted. There are loopholes in data monitoring, which makes the monitoring results inaccurate and cannot guarantee the safety of users. Summary of the invention

[0004] The purpose of the present invention is to provide an eyewash data monitoring and management system and method based on the Internet of Things to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: a data monitoring and management method for eyewashers based on the Internet of Things, the management method comprising the following steps:

[0006] Step S100: Obtain the water flow rate and the number of cleanings obtained from each monitoring of the eyewash in history, and generate corresponding water flow rate distribution diagrams and cleaning number distribution diagrams; analyze the fluctuation degree of the water flow rate and the change amplitude of the cleaning number according to the difference change of the water flow rate and the difference of the cleaning number at each two adjacent time points, and obtain the abnormal time points corresponding to several abnormal data; obtain the actual abnormal time point of each abnormal occurrence in the eyewash in history, and analyze the overlap between the abnormal time point and the actual abnormal time point;

[0007] Step S200: establishing a matching formula between the water flow rate and the number of cleaning times at each time point when the eyewash is in normal operation, generating a data matching model, and training the data matching model;

[0008] Step S300: monitor the water flow rate and cleaning times of the eyewash in real time, input the water flow rate into the data matching model to obtain the corresponding normal cleaning times; perform error degree analysis based on the normal cleaning times and the cleaning times obtained by monitoring, and adjust the abnormal water flow rate and cleaning times;

[0009] Step S400: Divide the time interval between any two adjacent abnormalities in the history of the eyewash into several time point sets, and calculate the abnormal frequency of each time point set according to the abnormal conditions of each time point in each time point set; obtain the actual abnormal frequency of the eyewash according to the number of time points between the current two adjacent abnormal time points of the eyewash, and predict the remaining time for the next abnormality of the eyewash.

[0010] Furthermore, step S100 includes the following steps:

[0011] Step S101: The water flow rate of the eyewash for the jth time is obtained from the PLC template as D j and the number of cleaning times is N j ; Take the time point of each monitoring as the horizontal axis and the water flow rate D j As the ordinate, generate the water flow distribution diagram of the eyewash; take the time point of each monitoring as the abscissa and the number of cleaning times N j As the ordinate, a distribution graph of the cleaning times of the eyewash station is generated;

[0012] Compared with ordinary circuit board controlled eyewash, PLC control has the following advantages: PLC uses special hardware devices, which are usually programmable and flexible, allowing programming configuration according to different application scenarios; PLC can simplify complex control tasks, and achieve control requirements through a small number of components such as control buttons and PLC itself, reducing the space requirements for circuit assembly;

[0013] Step S102: Obtain the water flow difference between two adjacent time points as ΔD, and obtain the water flow difference set D of the eyewasher = {ΔD 12 ,…,ΔD j-1,j ,…,ΔD m-1,m}, where ΔD j-1,j is the water flow difference between the j-1th monitoring and the jth monitoring, m is the total number of monitoring times of the eyewash; the sum of the differences in the water flow difference set is calculated as D t =|ΔD 12 |+…+|ΔD j-1,j |+…+|ΔD m-1,m |, and the fluctuation degree of each water flow difference is obtained as If B j-1,j >0 and ΔD j-1,j >0, then the water flow D obtained by the jth monitoringj Set as abnormal data; if B j-1,j ≤0, then obtain the water flow D obtained by the j-1th monitoring j-1 , if the water flow rate D j-1 If it is abnormal data, the water flow D obtained by the jth monitoring j Set as abnormal data; when the difference between two adjacent water flow rates is small, because both are abnormal data, it is necessary to determine whether the previous water flow rate is abnormal data;

[0014] Step S103: Obtain the difference in the number of cleaning times between two adjacent time points as ΔN, and set the difference in the number of cleaning times obtained by the j-1th monitoring and the jth monitoring as ΔN j-1,j , calculate the change range of cleaning times NC j-1.j =|ΔN j-1,j | / N j-1 ; Set an amplitude change threshold ε, if NC j-1.j >ε, the cleaning times obtained from the jth monitoring are set as abnormal data;

[0015] Step S104: Mark the set abnormal data in the two distribution graphs, set the time point corresponding to the abnormal data as the abnormal time point, summarize the abnormal time points in the two distribution graphs, and obtain the data abnormal time point set A1; obtain the actual abnormal time point of each abnormal eyewash in history to obtain the actual abnormal time point set A2; compare the time points in the two sets one by one, and obtain the number of the same abnormal time points as n yc ; Get the number of different abnormal time points in the two sets as n total =|A1∪A2|, where |A1∪A2| is the number of time points in the union of the two sets; according to the formula: δ=n yc / n total , calculate the overlap rate δ of the two sets; if δ<1, send an abnormal reminder to the eyewash station.

[0016] Further, step S200 includes the following steps:

[0017] Step S201: Except for the abnormal time point, set all other time points as normal time points and establish the formula:

[0018] D = α × [floor (N D )] β +γ

[0019] Among them, α, β, γ are constant coefficients, D is the water flow rate, N D is the number of cleaning times corresponding to the water flow rate D, and floor() is the rounding function;

[0020] Step S202: Take the water flow rate of the eyewash as input data, calculate according to the established formula, obtain the cleaning times of the eyewash, and take the cleaning times as output data to build a data matching model for the eyewash; set a constant coefficient k, take the cleaning times and water flow rates of k×Z normal time points as the training set of the data matching model, where Z is the number of normal time points, and determine the constant coefficients α, β, γ; take the cleaning times and water flow rates of (1-k)×Z normal time points as the test set of the data matching model, set the cleaning times and water flow rates of x normal time points in the test set to satisfy the formula, and obtain the accuracy of the data matching model Set an accuracy threshold τ. If F<τ, add several groups of data in the test set to the training set and retrain the data matching model until F≥τ.

[0021] Further, step S300 includes the following steps:

[0022] Step S301: remotely control the start or stop of the eyewash through the electromagnetic switch, and remotely monitor the real-time water flow of the eyewash through the electronic flowmeter or turbine flowmeter to ensure that the eyewash and shower flow rates meet the national standards, and display them on the LED screen of the eyewash, and store the monitored water flow in the eyewash control chip; set the water flow rate monitored when the eyewash is currently at time t to D t , the water flow rate D t The input data is processed in the matching model according to the formula:

[0023]

[0024] Among them, floor() is the rounding function, α, β, γ are constant coefficients, and the water flow D is calculated. t Corresponding normal cleaning times

[0025] Step S302: Set the number of cleaning times monitored by the eyewash station at time t to N t , according to the formula:

[0026]

[0027] The error degree of the eyewash at time t is calculated to be η t ; Set an error threshold θ, if η t >θ, an abnormal reminder is sent to the data monitored by the eyewash station at time t;

[0028] Step S303: Set the eyewash to be monitored once every unit period T, and extract the water flow D obtained by monitoring the eyewash at time tT t-T ,like Among them, θ' is the water flow error threshold, according to the formula:

[0029]

[0030] Adjust the water flow of the eyewash at time t to D' t ; +1 or -1, the water flow is appropriately adjusted according to the increase or decrease of two adjacent water flows, so that the adjustment result is more accurate;

[0031] Step S304: Obtain the cleaning times N obtained by monitoring the eyewash station at time tT t-T ,when If the water flow of the eyewash at time t is adjusted, the water flow is D t , then adjust the cleaning times to If the adjusted water flow is D' t , then adjust the cleaning times to Adjustments to the monitored abnormal data can facilitate subsequent predictions of the remaining abnormal time to be more accurate and effectively protect the safety of users.

[0032] Further, step S400 includes the following steps:

[0033] Step S401: Obtain the time interval between any two adjacent abnormalities in the eyewash history, divide all time points into several time point sets evenly, set the number of time points in a time point set to p; obtain the number of abnormal time points in each time point set, where the number of abnormal time points in the i-th time point set is q i , the abnormal frequency of the i-th time point set is calculated to be g i =q i / p; Set the number of time point sets to r, and get the abnormal frequency of the rth time point set to g r ; The time point between two adjacent abnormalities includes the time point of one abnormality, but does not include the time point of the other abnormality;

[0034] Step S402: Obtain the abnormal frequency of the last time point set in each time interval of the eyewash, and calculate the average value to obtain the theoretical abnormal frequency when the eyewash is abnormal: Get the abnormal frequency difference between every two adjacent time points, and get the average difference as

[0035] Step S403: Obtain the number of time points between two adjacent abnormal time points of the current eyewash as r', and obtain the actual abnormal frequency of the current eyewash as g ac =1 / r'; According to the formula:

[0036]

[0037] Among them, T is the unit cycle of eyewash monitoring, and the predicted remaining time from the next abnormality of the eyewash is calculated to be T remain ;

[0038] In order to better implement the above method, an eyewash data monitoring and management system based on the Internet of Things is also proposed. The management system includes a historical data analysis module, a data relationship establishment module, an abnormal data correction module and an abnormal time prediction module;

[0039] The historical data analysis module is used to obtain the water flow rate and the number of cleaning times obtained from each monitoring of the eyewash in history, and generate the corresponding water flow rate distribution diagram and cleaning times distribution diagram; according to the difference change of the water flow rate and the difference of the cleaning times at each two adjacent time points, the fluctuation degree of the water flow rate and the change amplitude of the cleaning times are analyzed to obtain the abnormal time points corresponding to several abnormal data; the actual abnormal time point of each abnormal occurrence in the eyewash in history is obtained, and the overlap between the abnormal time point and the actual abnormal time point is analyzed;

[0040] A data relationship building module is used to establish a matching formula between water flow and cleaning times according to the water flow and cleaning times at each time point when the eyewash is in normal operation, generate a data matching model, and train the data matching model;

[0041] The abnormal data correction module is used to monitor the water flow and cleaning times of the eyewash in real time, input the water flow into the data matching model to obtain the corresponding normal cleaning times; analyze the error degree according to the normal cleaning times and the cleaning times obtained by monitoring, and adjust the abnormal water flow and cleaning times;

[0042] The abnormal time prediction module is used to divide the time interval between any two adjacent abnormalities in the history of the eyewash into several time point sets, and calculate the abnormal frequency of each time point set according to the abnormal conditions of each time point in each time point set; according to the number of time points between the current two adjacent abnormal time points of the eyewash, the actual abnormal frequency of the eyewash is obtained, and the remaining time for the next abnormality of the eyewash is predicted.

[0043] Further, the historical data analysis module includes an abnormal time point extraction unit and a coincidence situation analysis unit;

[0044] The abnormal time point extraction unit is used to obtain the water flow rate and the number of cleaning times obtained from each monitoring of the eyewash in history, and generate the corresponding water flow rate distribution diagram and the number of cleaning times distribution diagram; according to the difference change of the water flow rate and the difference of the number of cleaning times between each two adjacent time points, the fluctuation degree of the water flow rate and the amplitude of the change of the number of cleaning times are analyzed to obtain the abnormal time points corresponding to several abnormal data; the coincidence analysis unit is used to obtain the actual abnormal time point of each abnormal occurrence in the history of the eyewash, and analyze the coincidence between the abnormal time point and the actual abnormal time point.

[0045] Furthermore, the data relationship establishment module includes a formula establishment unit and a model training unit;

[0046] The formula establishment unit is used to establish a matching formula between water flow and cleaning times according to the water flow and cleaning times at each time point when the eyewash is operating normally; the model training unit is used to generate a data matching model and train the data matching model.

[0047] Further, the abnormal data correction module includes an error data analysis unit and a data adjustment unit;

[0048] The error data analysis unit is used to monitor the water flow and cleaning times of the eyewash in real time, input the water flow into the data matching model to obtain the corresponding normal cleaning times; perform error degree analysis based on the normal cleaning times and the cleaning times obtained by monitoring; the data adjustment unit is used to adjust the abnormal water flow and cleaning times.

[0049] Further, the abnormal time prediction module includes an abnormal frequency calculation unit and a remaining time prediction unit;

[0050] The abnormal frequency calculation unit is used to divide the time interval between any two adjacent abnormalities in the history of the eyewash into several time point sets, and calculate the abnormal frequency of each time point set according to the abnormal conditions of each time point in each time point set; the remaining time prediction unit is used to obtain the actual abnormal frequency of the eyewash according to the number of time points between the current two adjacent abnormal time points of the eyewash, and predict the remaining time for the next abnormality of the eyewash.

[0051] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: (1) The present invention takes into account the abnormality of the data monitored by the eyewash, further detects the monitored data, excludes the undetected abnormal data, improves the accuracy of data monitoring, and ensures the safety of users; (2) The present invention matches the parameters of the eyewash by establishing a data matching model, and accurately adjusts the abnormal data to ensure the accuracy of the data; (3) The present invention realizes real-time monitoring of the real-time status of the eyewash, including water flow, flushing times and fault conditions; (4) The present invention remotely monitors the flow, switch, fault, usage and other states of the eyewash through the programming of the PLC template, and no longer needs to go to great lengths to conduct individual spot checks on each eyewash with a distance difference of several hundred meters. By checking the background of an online computer or mobile phone, the inspection of the eyewash in the entire factory can be completed, ensuring the normal operation of the eyewash and the life safety of the on-site staff; (5) PLC provides real-time monitoring and fault diagnosis capabilities, making it relatively easy to locate and repair problems; when a fault occurs in an ordinary circuit, it may be necessary to analyze the electrical schematic in detail and check the connecting wires one by one, making the maintenance process more complicated. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0053] Figure 1 It is a schematic diagram of the steps of an eyewash device data monitoring and management method based on the Internet of Things;

[0054] Figure 2 The present invention is a structural diagram of an eyewash device data monitoring and management system based on the Internet of Things. DETAILED DESCRIPTION

[0055] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0056] See also Figure 1 to Figure 2 The present invention provides a technical solution: an eyewash data monitoring and management method based on the Internet of Things, the management method comprising the following steps:

[0057] Step S100: Obtain the water flow rate and the number of cleanings obtained from each monitoring of the eyewash in history, and generate corresponding water flow rate distribution diagrams and cleaning number distribution diagrams; analyze the fluctuation degree of the water flow rate and the change amplitude of the cleaning number according to the difference change of the water flow rate and the difference of the cleaning number at each two adjacent time points, and obtain the abnormal time points corresponding to several abnormal data; obtain the actual abnormal time point of each abnormal occurrence in the eyewash in history, and analyze the overlap between the abnormal time point and the actual abnormal time point;

[0058] Wherein, step S100 includes the following steps:

[0059] Step S101: The water flow rate of the eyewash for the jth time is obtained from the PLC template as D j and the number of cleaning times is N j ; Take the time point of each monitoring as the horizontal axis and the water flow rate D j As the ordinate, generate the water flow distribution diagram of the eyewash; take the time point of each monitoring as the abscissa and the number of cleaning times N j As the ordinate, a distribution graph of the cleaning times of the eyewash station is generated;

[0060] Step S102: Obtain the water flow difference between two adjacent time points as ΔD, and obtain the water flow difference set D of the eyewasher = {ΔD 12 ,…,ΔD j-1,j ,…,ΔD m-1,m}, where ΔD j-1,j is the water flow difference between the j-1th monitoring and the jth monitoring, m is the total number of monitoring times of the eyewash; the sum of the differences in the water flow difference set is calculated as D t =|ΔD 12 |+…+|ΔD j-1,j |+…+|ΔD m-1,m |, and the fluctuation degree of each water flow difference is obtained as If B j-1,j >0 and ΔD j-1,j >0, then the water flow D obtained by the jth monitoring j Set as abnormal data; if B j-1,j ≤0, then obtain the water flow D obtained by the j-1th monitoring j-1 , if the water flow rate D j-1 If it is abnormal data, the water flow D obtained by the jth monitoring j Set as abnormal data;

[0061] Step S103: Obtain the difference in the number of cleaning times between two adjacent time points as ΔN, and set the difference in the number of cleaning times obtained by the j-1th monitoring and the jth monitoring as ΔN j-1,j , calculate the change range of cleaning times NC j-1.j =|ΔNj-1,j | / N j-1 ; Set an amplitude change threshold ε, if NC j-1.j >ε, the cleaning times obtained from the jth monitoring are set as abnormal data;

[0062] Step S104: Mark the set abnormal data in the two distribution graphs, set the time point corresponding to the abnormal data as the abnormal time point, summarize the abnormal time points in the two distribution graphs, and obtain the data abnormal time point set A1; obtain the actual abnormal time point of each abnormal eyewash in history to obtain the actual abnormal time point set A2; compare the time points in the two sets one by one, and obtain the number of the same abnormal time points as n yc ; Get the number of different abnormal time points in the two sets as n total =|A1∪A2|, where |A1∪A2| is the number of time points in the union of the two sets; according to the formula: δ=n yc / n total , calculate the overlap rate δ of the two sets; if δ<1, send an abnormal reminder to the eyewash station.

[0063] Step S200: establishing a matching formula between the water flow rate and the number of cleaning times at each time point when the eyewash is in normal operation, generating a data matching model, and training the data matching model;

[0064] Wherein, step S200 includes the following steps:

[0065] Step S201: Except for the abnormal time point, set all other time points as normal time points and establish the formula:

[0066] D = α × [floor (N D )] β +γ

[0067] Among them, α, β, γ are constant coefficients, D is the water flow rate, N D is the number of cleaning times corresponding to the water flow rate D, and floor() is the rounding function;

[0068] Step S202: Take the water flow rate of the eyewash as input data, calculate according to the established formula, obtain the cleaning times of the eyewash, and take the cleaning times as output data to build a data matching model for the eyewash; set a constant coefficient k, take the cleaning times and water flow rates of k×Z normal time points as the training set of the data matching model, where Z is the number of normal time points, and determine the constant coefficients α, β, γ; take the cleaning times and water flow rates of (1-k)×Z normal time points as the test set of the data matching model, set the cleaning times and water flow rates of x normal time points in the test set to satisfy the formula, and obtain the accuracy of the data matching model Set an accuracy threshold τ. If F<τ, add several groups of data in the test set to the training set and retrain the data matching model until F≥τ.

[0069] Step S300: monitor the water flow rate and cleaning times of the eyewash in real time, input the water flow rate into the data matching model to obtain the corresponding normal cleaning times; perform error degree analysis based on the normal cleaning times and the cleaning times obtained by monitoring, and adjust the abnormal water flow rate and cleaning times;

[0070] Wherein, step S300 includes the following steps:

[0071] Step S301: remotely control the eyewash to start or stop through the electromagnetic switch, remotely monitor the real-time water flow of the eyewash through the electronic flowmeter or turbine flowmeter, and display it on the LED screen of the eyewash, and store the monitored water flow in the eyewash control chip; set the water flow monitored when the eyewash is currently at time t to D t , the water flow rate D t The input data is processed in the matching model according to the formula:

[0072]

[0073] Among them, floor() is the rounding function, α, β, γ are constant coefficients, and the water flow D is calculated. t Corresponding normal cleaning times

[0074] Step S302: Set the number of cleaning times monitored by the eyewash station at time t to N t , according to the formula:

[0075]

[0076] The error degree of the eyewash at time t is calculated to be η t ; Set an error threshold θ, if η t >θ, an abnormal reminder is sent to the data monitored by the eyewash station at time t;

[0077] Step S303: Set the eyewash to be monitored once every unit period T, and extract the water flow D obtained by monitoring the eyewash at time tT t-T ,like Among them, θ' is the water flow error threshold, according to the formula:

[0078]

[0079] Adjust the water flow of the eyewash at time t to D' t ;

[0080] Step S304: Obtain the cleaning times N obtained by monitoring the eyewash station at time tT t-T ,when If the water flow of the eyewash at time t is adjusted, the water flow is D t , then adjust the cleaning times to If the adjusted water flow is D' t , then adjust the cleaning times to

[0081] Step S400: Divide the time interval between any two adjacent abnormalities in the history of the eyewash into a number of time point sets, and calculate the abnormal frequency of each time point set according to the abnormal conditions of each time point in each time point set; obtain the actual abnormal frequency of the eyewash according to the number of time points between the current two adjacent abnormal time points of the eyewash, and predict the remaining time for the next abnormality of the eyewash;

[0082] Wherein, step S400 includes the following steps:

[0083] Step S401: Obtain the time interval between any two adjacent abnormalities in the eyewash history, divide all time points into several time point sets evenly, set the number of time points in a time point set to p; obtain the number of abnormal time points in each time point set, where the number of abnormal time points in the i-th time point set is q i , the abnormal frequency of the i-th time point set is calculated to be g i =q i / p; Set the number of time point sets to r, and get the abnormal frequency of the rth time point set to g r ;

[0084] Step S402: Obtain the abnormal frequency of the last time point set in each time interval of the eyewash, and calculate the average value to obtain the theoretical abnormal frequency when the eyewash is abnormal: Get the abnormal frequency difference between every two adjacent time points, and get the average difference as

[0085] Step S403: Obtain the number of time points between two adjacent abnormal time points of the current eyewash as r', and obtain the actual abnormal frequency of the current eyewash as g ac =1 / r'; According to the formula:

[0086]

[0087] Among them, T is the unit cycle of eyewash monitoring, and the predicted remaining time from the next abnormality of the eyewash is calculated to be T remain .

[0088] An eyewash data monitoring and management system based on the Internet of Things, the management system includes a historical data analysis module, a data relationship establishment module, an abnormal data correction module and an abnormal time prediction module;

[0089] The historical data analysis module is used to obtain the water flow rate and the number of cleaning times obtained from each monitoring of the eyewash in history, and generate the corresponding water flow rate distribution diagram and cleaning times distribution diagram; according to the difference change of the water flow rate and the difference of the cleaning times at each two adjacent time points, the fluctuation degree of the water flow rate and the change amplitude of the cleaning times are analyzed to obtain the abnormal time points corresponding to several abnormal data; the actual abnormal time point of each abnormal occurrence in the eyewash in history is obtained, and the overlap between the abnormal time point and the actual abnormal time point is analyzed;

[0090] A data relationship building module is used to establish a matching formula between water flow and cleaning times according to the water flow and cleaning times at each time point when the eyewash is in normal operation, generate a data matching model, and train the data matching model;

[0091] The abnormal data correction module is used to monitor the water flow and cleaning times of the eyewash in real time, input the water flow into the data matching model to obtain the corresponding normal cleaning times; analyze the error degree according to the normal cleaning times and the cleaning times obtained by monitoring, and adjust the abnormal water flow and cleaning times;

[0092] The abnormal time prediction module is used to divide the time interval between any two adjacent abnormalities in the history of the eyewash into several time point sets, and calculate the abnormal frequency of each time point set according to the abnormal conditions of each time point in each time point set; according to the number of time points between the current two adjacent abnormal time points of the eyewash, the actual abnormal frequency of the eyewash is obtained, and the remaining time for the next abnormality of the eyewash is predicted.

[0093] Among them, the historical data analysis module includes an abnormal time point extraction unit and a coincidence situation analysis unit;

[0094] The abnormal time point extraction unit is used to obtain the water flow rate and the number of cleaning times obtained from each monitoring of the eyewash in history, and generate the corresponding water flow rate distribution diagram and the number of cleaning times distribution diagram; according to the difference change of the water flow rate and the difference of the number of cleaning times between each two adjacent time points, the fluctuation degree of the water flow rate and the amplitude of the change of the number of cleaning times are analyzed to obtain the abnormal time points corresponding to several abnormal data; the coincidence analysis unit is used to obtain the actual abnormal time point of each abnormal occurrence in the history of the eyewash, and analyze the coincidence between the abnormal time point and the actual abnormal time point.

[0095] Among them, the data relationship establishment module includes a formula establishment unit and a model training unit;

[0096] The formula establishment unit is used to establish a matching formula between water flow and cleaning times according to the water flow and cleaning times at each time point when the eyewash is operating normally; the model training unit is used to generate a data matching model and train the data matching model.

[0097] Wherein, the abnormal data correction module includes an error data analysis unit and a data adjustment unit;

[0098] The error data analysis unit is used to monitor the water flow and cleaning times of the eyewash in real time, input the water flow into the data matching model to obtain the corresponding normal cleaning times; perform error degree analysis based on the normal cleaning times and the cleaning times obtained by monitoring; the data adjustment unit is used to adjust the abnormal water flow and cleaning times.

[0099] Among them, the abnormal time prediction module includes an abnormal frequency calculation unit and a remaining time prediction unit;

[0100] The abnormal frequency calculation unit is used to divide the time interval between any two adjacent abnormalities in the history of the eyewash into several time point sets, and calculate the abnormal frequency of each time point set according to the abnormal conditions of each time point in each time point set; the remaining time prediction unit is used to obtain the actual abnormal frequency of the eyewash according to the number of time points between the current two adjacent abnormal time points of the eyewash, and predict the remaining time for the next abnormality of the eyewash.

[0101] This solution uses a PLC control template to replace the traditional circuit board to control the functions and operations of the eyewash. Through the background, all basic information of each eyewash can be remotely viewed, including manufacturing information / nameplate / model type, etc. Through the explosion-proof electromagnetic switch start and stop and the electronic flow device, the shower flow and eyewash flow data of the eyewash can be remotely viewed; through the flow switch or travel switch, remote signal upload can be achieved, and the working status of the eyewash can be remotely viewed; through the PT100 temperature sensor and thermostat, PLC, etc., the heating temperature of the eyewash can be remotely viewed, and low and high temperature alarms can be realized; through the PLC background server, it is known at the first time when and where the eyewash fails, and an alarm can be immediately triggered.

[0102] The time points at which the eyewash machine's history was obtained for three times were time 1, time 5, time 7, and time 10; the monitored water flow rates were 12L / min, 13L / min, 13L / min, and 12L / min, respectively, and the corresponding cleaning times were 4, 3, 3, and 7. The water flow differences between two adjacent time points were 1L / min, -1L / min, and 0, indicating that there was no abnormal data in the water flow rate;

[0103] The difference between the number of cleaning times at two adjacent time points is obtained as -1, 0, and 4. The change amplitude of the cleaning times is calculated to be 0.25, 0, and 1.25. A change amplitude threshold is set to 0.5. Since 1.25>0.5, the 4th cleaning times is set as abnormal data.

[0104] The time point at which the eyewash machine's abnormality occurred in history is obtained as 8 seconds, and the coincidence rate of the abnormal time point is 0, so a data error reminder is sent to the eyewash machine;

[0105] Establish the formula: D = α × [floor (N D )] β +γ, substitute (12L / min, 4 times), (13L / min, 3 times), (12L / min, 3 times) into the formula to obtain the values ​​of α, β, and γ, and establish a data matching model;

[0106] Substituting the water flow rate of 12L / min into the formula, the corresponding cleaning times are 3 times, so adjust the cleaning times at time 10;

[0107] Get the abnormal frequency of the last time point set in each time interval of the eyewash, and calculate the average value to get the theoretical abnormal frequency when the eyewash is abnormal: Get the abnormal frequency difference between every two adjacent time points, and get the average difference as The actual abnormal frequency of the current eyewash station is g ac =1 / r'=1 / 20, according to the formula:

[0108]

[0109] Get T remain =1×4.5 moments, and the predicted remaining time until the next abnormality of the eyewash station is 4.5 moments.

[0110] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0111] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A data monitoring and management method for eyewashers based on the Internet of Things, characterized in that: The management method comprises the following steps: Step S100: Obtain the water flow rate and the number of cleanings obtained from each monitoring of the eyewash in history, and generate corresponding water flow rate distribution diagrams and cleaning number distribution diagrams; analyze the fluctuation degree of the water flow rate and the change amplitude of the cleaning number according to the difference change of the water flow rate and the difference of the cleaning number at each two adjacent time points, and obtain the abnormal time points corresponding to several abnormal data; obtain the actual abnormal time point of each abnormal occurrence in the eyewash in history, and analyze the overlap between the abnormal time point and the actual abnormal time point; Step S200: establishing a matching formula between the water flow rate and the number of cleaning times at each time point when the eyewash is in normal operation, generating a data matching model, and training the data matching model; Step S300: monitor the water flow rate and cleaning times of the eyewash in real time, input the water flow rate into the data matching model to obtain the corresponding normal cleaning times; perform error degree analysis based on the normal cleaning times and the cleaning times obtained by monitoring, and adjust the abnormal water flow rate and cleaning times; Step S400: Divide the time interval between any two adjacent abnormalities in the history of the eyewash into a number of time point sets, and calculate the abnormal frequency of each time point set according to the abnormal conditions of each time point in each time point set; obtain the actual abnormal frequency of the eyewash according to the number of time points between the current two adjacent abnormal time points of the eyewash, and predict the remaining time for the next abnormality of the eyewash; The step S200 includes the following steps: Step S201: Except for the abnormal time point, set all other time points as normal time points and establish the formula: ； in, is the constant coefficient, D is the water flow rate, is the number of cleaning times corresponding to the water flow rate D, and floor() is the rounding function; Step S202: Take the water flow rate of the eyewash as input data, calculate according to the established formula, obtain the cleaning times of the eyewash, and take the cleaning times as output data to build a data matching model for the eyewash; set a constant coefficient k, take the cleaning times and water flow rates of k×Z normal time points as the training set of the data matching model, where Z is the number of normal time points, and determine the constant coefficient ; Take the cleaning times and water flow rates at (1-k)×Z normal time points as the test set of the data matching model, assume that there are x cleaning times and water flow rates at normal time points in the test set that satisfy the formula, and obtain the accuracy of the data matching model , set an accuracy threshold ,like , then add several groups of data in the test set to the training set and retrain the data matching model until until.

2. According to the method for monitoring and managing eyewash data based on the Internet of Things in claim 1, it is characterized by: The step S100 includes the following steps: Step S101: The water flow rate of the eyewash at the jth time is obtained from the PLC template: and the number of cleaning times is ; Take the time point of each monitoring as the horizontal axis and the water flow rate as the horizontal axis. As the ordinate, generate the water flow distribution diagram of the eyewash station; take the time point of each monitoring as the abscissa and the number of cleaning times as the As the ordinate, a distribution graph of the cleaning times of the eyewash station is generated; Step S102: Obtain the water flow difference between two adjacent time points , get the water flow difference set of the eyewash ,in, is the water flow difference between the j-1th monitoring and the jth monitoring, m is the total number of monitoring times of the eyewash; the sum of the differences in the water flow difference set is calculated as , the fluctuation degree of each water flow difference is obtained as ,like and , then the water flow rate obtained by the jth monitoring Set as abnormal data; if , then the water flow rate obtained by the j-1th monitoring is obtained If the water flow If it is abnormal data, the water flow rate obtained by the jth monitoring Set as abnormal data; Step S103: Obtain the difference between the number of cleaning times at two adjacent time points. , set the difference between the cleaning times obtained from the j-1th monitoring and the jth monitoring to , calculate the change range of cleaning times ; Set an amplitude change threshold ,like , then the cleaning times obtained by the jth monitoring are set as abnormal data; Step S104: Mark the set abnormal data in the two distribution graphs, set the time point corresponding to the abnormal data as the abnormal time point, and summarize the abnormal time points in the two distribution graphs to obtain a data abnormal time point set. ; Get the actual abnormal time point of each abnormal eyewash in history, and get the actual abnormal time point set ; Compare the time points in the two sets one by one, and get the number of the same abnormal time points as ; Get the number of different abnormal time points in the two sets as ,in, is the number of time points of the union of two sets; according to the formula: , calculate the overlap rate of the two sets ;like , an abnormal reminder will be sent to the eyewash station.

3. According to the method for monitoring and managing eyewash data based on the Internet of Things in claim 2, it is characterized by: The step S300 includes the following steps: Step S301: remotely control the eyewash to start or stop through the electromagnetic switch, remotely monitor the real-time water flow of the eyewash through the electronic flowmeter or turbine flowmeter, and display it on the LED screen of the eyewash, and store the monitored water flow in the eyewash control chip; set the water flow monitored when the eyewash is currently at time t to be , the water flow The input data is processed in the matching model according to the formula: ； in, is the floor function, is a constant coefficient, and the water flow rate is calculated Corresponding normal cleaning times ; Step S302: Set the number of cleaning times monitored by the eyewash station at time t to , according to the formula: ； The error degree of the eyewash at time t is calculated as ; Set an error threshold ,like , then send an abnormal reminder to the data monitored by the eyewash station at time t; Step S303: Set the eyewash to be monitored once every unit period T, and extract the water flow rate monitored at the eyewash at time tT ,like ,in, is the water flow error threshold, according to the formula: ； Adjust the water flow of the eyewash at time t to ; Step S304: Obtain the cleaning times monitored by the eyewash station at time tT ,when If the water flow of the eyewash at time t is adjusted, the water flow is , then adjust the cleaning times to , if the adjusted water flow is , then adjust the cleaning times to .

4. According to the method for monitoring and managing eyewash data based on the Internet of Things in claim 3, it is characterized by: The step S400 includes the following steps: Step S401: Obtain the time interval between any two adjacent abnormalities in the eyewash history, divide all time points into several time point sets evenly, and set the number of time points in a time point set to ; Get the number of abnormal time points in each time point set, where the number of abnormal time points in the i-th time point set is , the abnormal frequency of the i-th time point set is calculated as ; Set the number of time point sets to r, and get the abnormal frequency of the rth time point set as ; Step S402: Obtain the abnormal frequency of the last time point set in each time interval of the eyewash, and calculate the average value to obtain the theoretical abnormal frequency when the eyewash is abnormal: ; Get the abnormal frequency difference between every two adjacent time points, and get the average difference as ; Step S403: Get the number of time points between two adjacent abnormal time points of the current eyewash station. , the actual abnormal frequency of the current eyewash station is ; According to the formula: ； Among them, T is the unit cycle of eyewash monitoring, and the predicted remaining time from the next abnormality of the eyewash is calculated as .

5. An eyewash data monitoring and management system applied to an eyewash data monitoring and management method based on the Internet of Things as described in any one of claims 1 to 4, characterized in that: The management system includes a historical data analysis module, a data relationship establishment module, an abnormal data correction module and an abnormal time prediction module; The historical data analysis module is used to obtain the water flow rate and the number of cleaning times obtained from each monitoring of the eyewash in history, and generate corresponding water flow rate distribution diagrams and cleaning times distribution diagrams; analyze the fluctuation degree of the water flow rate and the change amplitude of the cleaning times according to the difference change of the water flow rate and the difference of the cleaning times at each two adjacent time points, and obtain the abnormal time points corresponding to a number of abnormal data; obtain the actual abnormal time point of each abnormal occurrence in the eyewash in history, and analyze the overlap between the abnormal time point and the actual abnormal time point; The data relationship establishment module is used to establish a matching formula between water flow and cleaning times according to the water flow and cleaning times at each time point when the eyewash is operating normally, generate a data matching model, and train the data matching model; The abnormal data correction module is used to monitor the water flow rate and cleaning times of the eyewash in real time, and input the water flow rate into the data matching model to obtain the corresponding normal cleaning times; Analyze the error degree based on the normal cleaning times and the cleaning times obtained by monitoring, and adjust the abnormal water flow and cleaning times; The abnormal time prediction module is used to divide the time interval between any two adjacent abnormalities in the history of the eyewash into several time point sets, and calculate the abnormal frequency of each time point set according to the abnormal conditions of each time point in each time point set; according to the number of time points between the current two adjacent abnormal time points of the eyewash, the actual abnormal frequency of the eyewash is obtained, and the remaining time for the next abnormality of the eyewash is predicted.

6. The eyewash data monitoring and management system according to claim 5 is characterized in that: The historical data analysis module includes an abnormal time point extraction unit and a coincidence situation analysis unit; The abnormal time point extraction unit is used to obtain the water flow rate and the number of cleaning times obtained by each monitoring in the history of the eyewash, and generate corresponding water flow rate distribution diagrams and cleaning times distribution diagrams; according to the difference changes in the water flow rate and the difference in the number of cleaning times between each two adjacent time points, the fluctuation degree of the water flow rate and the amplitude of the change in the number of cleaning times are analyzed to obtain abnormal time points corresponding to a number of abnormal data; the coincidence analysis unit is used to obtain the actual abnormal time point of each abnormal occurrence in the history of the eyewash, and analyze the coincidence between the abnormal time point and the actual abnormal time point.

7. The eyewash station data monitoring and management system according to claim 5, characterized in that: The data relationship establishment module includes a formula establishment unit and a model training unit; The formula establishment unit is used to establish a matching formula between water flow and cleaning times according to the water flow and cleaning times at each time point when the eyewash is operating normally; the model training unit is used to generate a data matching model and train the data matching model.

8. The eyewash data monitoring and management system according to claim 5 is characterized by: The abnormal data correction module includes an error data analysis unit and a data adjustment unit; The error data analysis unit is used to monitor the water flow rate and cleaning times of the eyewash in real time, and input the water flow rate into the data matching model to obtain the corresponding normal cleaning times; The error degree analysis is performed based on the normal cleaning times and the cleaning times obtained by monitoring; the data adjustment unit is used to adjust the abnormal water flow and cleaning times.

9. The eyewash data monitoring and management system according to claim 5, characterized in that: The abnormal time prediction module includes an abnormal frequency calculation unit and a remaining time prediction unit; The abnormal frequency calculation unit is used to divide the time interval between any two adjacent abnormalities in the history of the eyewash into a number of time point sets, and calculate the abnormal frequency of each time point set according to the abnormal conditions of each time point in each time point set; the remaining time prediction unit is used to obtain the actual abnormal frequency of the eyewash according to the number of time points between two current adjacent abnormal time points of the eyewash, and predict the remaining time for the next abnormality of the eyewash.

Images