Marine integrated sanitary unit assembling process

Abstract

The invention relates to the technical field of integrated sanitary units in ship engineering, and particularly discloses a marine integrated sanitary unit assembly process which realizes accurate identification of a system fault source by monitoring water flow in real time and performing correlation analysis on the water flow and the working state of a pump, and the specific method comprises the following steps: continuously collecting water flow data by using a high-precision flow meter; recording the rotating speed and the current consumption of the pump; predicting a future water flow trend based on the prediction model, and judging abnormality by comparing a predicted value with an actual value; recording operation parameters of the pump in each sub-cycle, and evaluating the health condition of the pump; by comparing a water flow abnormal period with a pump fault period, determining a fault source and pushing early warning information to a manager, the monitoring capability of the sanitary unit waterway system is enhanced, a fault diagnosis mechanism based on data analysis is provided, the stability and maintenance efficiency of the system are remarkably improved, and the system is suitable for long-term reliable operation in a ship environment.

Description

Technical Field

[0001] The invention relates to the technical field of integrated sanitary units in ship engineering, and in particular to an assembly process of a ship-used integrated sanitary unit. Background Art

[0002] As an important part of ship living facilities, the operating status of the marine integrated sanitary unit directly affects the quality of life of crew members and passengers. With the development of ship technology, higher requirements are placed on the automation management level of the sanitary unit. However, in practical applications, due to the complex operating environment of the ship, the waterway system in the sanitary unit is easily disturbed by external factors, resulting in frequent problems such as abnormal water flow. The traditional manual inspection method is inefficient and difficult to detect potential faults in time. Therefore, a technical solution that can achieve automatic monitoring and fault warning is urgently needed.

[0003] At present, the monitoring and maintenance of marine integrated sanitary units mainly rely on technical means such as regular manual inspections, threshold-based monitoring systems, and rule-based diagnostic systems. Regular manual inspections involve professionals regularly inspecting the sanitary units, recording the equipment's operating status, and troubleshooting. Although this is intuitive and reliable, it is inefficient and prone to missing details. Threshold-based monitoring systems install sensors at key locations to collect data in real time and set alarm thresholds. Once the threshold is exceeded, an alarm is triggered. This method is simple and practical, but it can only reflect the instantaneous state and lacks the ability to analyze trend changes. Rule-based diagnostic systems use expert knowledge bases and real-time data for intelligent diagnosis. Although they have certain adaptive capabilities, they are still insufficient when faced with complex dynamic changes. Although these technical means can guarantee the normal operation of sanitary units to a certain extent, they still have limitations in terms of accuracy, real-time response capabilities, and intelligence levels.

[0004] The present invention proposes a marine integrated sanitary unit assembly process, which can effectively identify and locate system faults by real-time monitoring of the water flow change trend and conducting a comprehensive analysis in combination with the working status of the pump, and take timely measures for regulation or maintenance, thereby significantly improving the stability and maintenance efficiency of the system. Summary of the invention

[0005] The purpose of the present invention is to provide an assembly process for a ship-based integrated sanitary unit. The present invention proposes a new assembly process for a ship-based integrated sanitary unit, which relates to the technical field of integrated sanitary units in ship engineering. This technical field is committed to improving the stability and reliability of the operation of ship sanitary systems by optimizing monitoring methods and fault diagnosis processes. The present invention particularly focuses on using data analysis methods to monitor water flow changes in real time, and conducts a comprehensive evaluation in combination with the working status of the pump to achieve rapid response and processing of potential faults. This technological innovation is of great significance for ensuring ship safety and improving the quality of life of crew members. Specifically, the process can effectively identify and accurately locate the source of faults in the system by monitoring the changing trend of water flow in real time and conducting a comprehensive analysis in combination with the working status of the pump, so that managers can quickly take corresponding control or maintenance measures, thereby greatly improving the stability and maintenance efficiency of the system. Specifically, in the basic monitoring process, firstly, a high-precision flow meter is used to continuously collect the water flow data of the internal waterway of the sanitary unit, and an ARIMA prediction model is constructed based on these data to predict the change trend of the future water flow; then, the prediction result is compared with the actual water flow value, and the error is calculated. When the error exceeds the preset threshold, an abnormal signal is generated, otherwise a normal signal is generated; at the same time, the speed and current consumption of the pump are recorded on the same time scale, and the correlation between the waterway state signal and the pump state signal is analyzed, and a comprehensive assessment is made whether there is a causal relationship between the two, and a water pump influence signal or a non-influence signal is generated accordingly; finally, a fault warning information is sent to the management personnel based on the water pump influence signal. In addition, in terms of time series refinement monitoring, the present invention also subdivides the monitoring cycle into multiple equal-length time subunits, and further divides it into smaller time units, collects water flow data at the middle time point of each time unit, eliminates the influence of instantaneous fluctuations by averaging, and then uses the sliding window technology to extract time series features, and builds an ARIMA model based on this and trains, adjusts and evaluates its performance, and finally uses the trained model to predict the water flow in the future period of time, and compares it with the actual value to determine whether there is an abnormality. In terms of detailed analysis of the pump status, the speed and current consumption of the pump in the middle of each time unit are recorded, the average speed and current consumption of the pump in the entire monitoring period are calculated, and correlation analysis is performed to determine whether the pump operation status is normal. If there is a strong positive correlation between the speed and current consumption of the pump, a normal signal is generated, otherwise an abnormal signal is generated. Finally, in the comprehensive judgment of causal relationships, the abnormal water flow period is compared with the abnormal pump period to find out whether there is an overlapping time period. If most of the abnormal conditions occur during the pump failure, the water flow abnormality is determined to be caused by the pump and an impact signal is generated. Otherwise, a non-impact signal is generated, and corresponding measures are taken according to the specific situation.In summary, the present invention not only realizes the accurate monitoring of the operating status of the water system of the marine integrated sanitary unit, but also provides a scientific and reasonable fault diagnosis method, which helps to significantly improve the stability and reliability of the system.

[0006] The purpose of the present invention can be achieved through the following technical solutions:

[0007] A marine integrated sanitary unit assembly process comprises the following steps:

[0008] Collect water flow data in the waterways within the sanitary unit;

[0009] Based on water flow data, a prediction model is constructed to predict the trend of water flow changes;

[0010] Compare the predicted result of water flow with the actual water flow value to obtain the error between the two;

[0011] Compare the error with a preset error threshold and generate a waterway status signal;

[0012] The pump speed and current consumption were recorded synchronously on the same time scale as the water flow data acquisition;

[0013] Based on the water circuit status signal, evaluating the strength of the relationship between the rotational speed and the current consumption of the pump, and generating a pump status signal;

[0014] Comprehensively analyze the causal relationship between the waterway status signal and the pump status signal to generate the pump impact signal and the pump non-impact signal;

[0015] Based on the pump impact signal, an alarm message is sent to the management staff.

[0016] As a further solution of the present invention: defining a monitoring period, subdividing the monitoring period into a plurality of time sub-units of equal length, and further dividing the sub-units into smaller time sub-units;

[0017] Collect water flow data at the middle point of each time unit;

[0018] The water flow data collected at the middle time point of each time sub-unit are integrated and processed to obtain a water flow unit group within the time sub-unit;

[0019] The water flow unit group is processed according to the mean calculation formula to obtain the water flow unit mean in the time subunit, which is recorded as the unit water flow value.

[0020] As a further solution of the present invention: based on all unit water flow values ​​obtained during the monitoring period, a sliding window technique is used to extract time series features, and a water flow prediction model is constructed based on the features;

[0021] Use the constructed water flow prediction model to predict the water flow in the future and obtain the predicted value of the water flow;

[0022] Based on the predicted value of the water flow, actual water flow data at a time corresponding to the predicted value of the water flow is obtained.

[0023] As a further solution of the present invention: according to the predicted value and the actual value of the water flow, the difference between the predicted value and the actual value of the water flow is calculated and recorded as the water flow prediction error;

[0024] All the obtained prediction errors are integrated to obtain a water flow prediction error group;

[0025] The water flow prediction error group is calculated according to the standard deviation calculation formula to obtain the standard deviation of the water flow prediction error;

[0026] Using the standard deviation multiple method, the error threshold is set to twice the standard deviation of the water flow prediction error.

[0027] As a further solution of the present invention: comparing the prediction error with an error threshold;

[0028] If the prediction error is greater than the error threshold, a waterway abnormality signal is generated;

[0029] If the prediction error is less than or equal to the error threshold, a normal waterway signal is generated.

[0030] As a further solution of the present invention: synchronously recording the speed and current consumption of the pump at the middle moment of each time unit;

[0031] All the speeds and currents collected in the time sub-unit are integrated and averaged to obtain the average values ​​of the speed and current in the time sub-unit, which are recorded as the unit speed value and the unit current value respectively;

[0032] All unit speed values ​​and unit current values ​​collected during the monitoring period are integrated and averaged to obtain the average speed and current of the pump during the monitoring period;

[0033] By formula The difference between the speed and the current is calculated C(Z,D);

[0034] Among them, Z is the speed value, ZJ is the average speed value, D is the current value, DJ is the average current value, and i is the number of time subunits, i=1,2,...,n.

[0035] As a further solution of the present invention: based on the difference between the speed and the current, the speed value group and the current value group are processed according to the standard deviation calculation formula to obtain the speed standard deviation and the current standard deviation;

[0036] The difference between the speed and the current is multiplied by the product of the standard deviation between the speed and the current to calculate the correlation coefficient between the speed and the current;

[0037] Compare the correlation coefficient r between the rotation speed and the current with a correlation threshold;

[0038] If the correlation coefficient is greater than or equal to the correlation threshold, a pump normal signal is generated;

[0039] If the correlation coefficient is less than the correlation threshold, a pump abnormality signal is generated.

[0040] As a further solution of the present invention: based on the waterway abnormality signal and the pump abnormality signal, all unit water flow values ​​collected during the monitoring period are integrated and processed to obtain a water flow group;

[0041] Each value in the speed value group is matched with each value in the current value group in a one-to-one manner according to a time series to obtain a pump state group;

[0042] The water flow group and the pump status group are analyzed and judged, all data points with abnormal water flow and pump conditions are identified, and all data points in the water flow group and the pump status group are divided into normal data points and abnormal data points.

[0043] As a further solution of the present invention: based on all normal data points and abnormal data points in the water flow group and the pump status group, a label is added to each data point in the water flow group, the data point of the abnormal water flow is marked as -1, and the data point of the normal water flow is marked as 1;

[0044] Based on the label of each data point in the water flow group, a positive and negative scatter plot of water flow is drawn with time as the horizontal axis and the label of each data point in the water flow group as the vertical axis;

[0045] Based on the data points of the pump abnormality, a label is added to the working status of the pump at each moment in the pump status group, and the data points of the pump normal condition are recorded as 1, and the data points of the pump abnormal condition are recorded as -1;

[0046] With time as the horizontal axis and the label of each data point in the pump state group as the vertical axis, draw a positive and negative scatter plot of the pump state.

[0047] As a further solution of the present invention: the positive and negative scatter diagram of water flow and the positive and negative scatter diagram of pump status are merged according to time to obtain a water pump relationship diagram;

[0048] Extract the time period of abnormal water flow and the time period of pump abnormality in the water pump relationship diagram, and obtain the time period in which the abnormal water flow time period overlaps with the abnormal pump time period, which is recorded as the overlapping time period;

[0049] Integrate all the overlapping time periods in the pump relationship diagram to obtain the total overlapping time;

[0050] comparing the total coincidence time to a time threshold;

[0051] If the total overlap time is greater than or equal to the time threshold, a water pump impact signal is generated;

[0052] If the total coincidence time is less than the time threshold, a pump non-impact signal is generated.

[0053] Beneficial effects of the present invention:

[0054] (1) The present invention proposes an assembly process for a marine integrated sanitary unit. Specifically, in the basic monitoring process, a high-precision flow meter is used to continuously collect water flow data, and the future water flow change trend is predicted based on a prediction model. This technical means effectively overcomes the problem of difficulty in accurate prediction due to large data fluctuations, ensures the reliability of the prediction results, and facilitates timely adoption of control or maintenance measures to ensure the smooth operation of the system. In addition, the present invention subdivides the monitoring cycle into multiple equal-length time subunits, and further divides it into smaller time units. Water flow data is collected at the middle time point of each time unit, and the influence of instantaneous fluctuations is eliminated by averaging. This makes monitoring more meticulous and solves the problem of information omission caused by low sampling frequency in traditional methods. Then, a sliding window technology is used to extract time series features, and an ARIMA model is constructed based on this and trained, adjusted and evaluated for performance. Finally, the trained model is used to predict the water flow in the future period of time, and compared with the actual value to determine whether there is an abnormality. This multi-level monitoring strategy not only improves the sensitivity of detection, but also can more effectively identify potential system failures and prevent small problems from turning into major accidents.

[0055] (2) The present invention records the speed and current consumption of the pump at the middle moment of each time unit, calculates the average speed and current consumption of the pump in the entire monitoring period, and performs correlation analysis to determine whether the pump operation status is normal. This technical feature solves the problem that the method of judging the health status of the pump by relying on only a single indicator in the past is not comprehensive enough. If there is a strong positive correlation between the speed and current consumption of the pump, a normal signal is generated, otherwise an abnormal signal is generated. Through this refined analysis method, the present invention can more accurately evaluate the actual working status of the pump, thereby providing reliable data support for maintenance decisions, ensuring the efficient operation of the pump, reducing the occurrence of unplanned downtime events, and improving the stability and reliability of the overall system;

[0056] (3) The present invention compares the water flow abnormality period with the pump abnormality period to find out whether there is an overlapping time period. If most of the abnormal conditions occur during the pump failure, it is determined that the water flow abnormality is caused by the pump and an impact signal is generated. Otherwise, a non-impact signal is generated, and corresponding measures are taken according to the specific situation. This technical feature solves the limitation of simply relying on water flow changes to determine the source of the fault by deeply analyzing the relationship between the water flow abnormality and the pump status, and provides a more scientific and reasonable fault diagnosis method. By accurately distinguishing the impact of pump failures on water flow changes, misjudgment and missed judgment are avoided, thereby significantly improving the stability and reliability of the system and ensuring the continuous and efficient operation of the marine integrated sanitary unit in complex environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] The present invention will be further described below in conjunction with the accompanying drawings.

[0058] Figure 1 is a schematic diagram of a flow chart of Embodiment 1 of the present invention;

[0059] Figure 2 is a schematic diagram of a flow chart of Embodiment 2 of the present invention;

[0060] Figure 3 It is a schematic diagram of the flow chart of Example 3 of the present invention. DETAILED DESCRIPTION

[0061] 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.

[0062] Example 1

[0063] See also Figure 1 As shown, the present invention is a process for assembling a marine integrated sanitary unit, comprising the following steps:

[0064] Collect water flow data in the waterways within the sanitary unit;

[0065] Based on water flow data, a prediction model is constructed to predict the trend of water flow changes;

[0066] Compare the predicted result of water flow with the actual water flow value to obtain the error between the two;

[0067] Compare the error with a preset error threshold and generate a waterway status signal;

[0068] The pump speed and current consumption were recorded synchronously on the same time scale as the water flow data acquisition;

[0069] Based on the water circuit status signal, evaluating the strength of the relationship between the rotational speed and the current consumption of the pump, and generating a pump status signal;

[0070] Comprehensively analyze the causal relationship between the waterway status signal and the pump status signal to generate the pump impact signal and the pump non-impact signal;

[0071] Based on the pump impact signal, an alarm message is sent to the management staff.

[0072] Example 2

[0073] This embodiment describes in detail how to collect and process water flow data in a waterway during a monitoring period and perform abnormality detection on the water flow data:

[0074] Divide the monitoring period into a number of time sub-units of equal length, divide the time sub-unit into a number of time small units of equal length, and collect water flow data of the waterway in the sanitary unit at the middle time point of each time small unit;

[0075] Wherein, the monitoring period is a preset time period, such as 1 hour, 1 day, 1 week, the equal-length time subunits are equal time periods obtained by dividing the equal time zone division method, the time length of each time subunit is a preset length, such as 1 minute, the time length of the time subunit is a preset length, such as 1 second, the middle time point of the time subunit is the time point when the time subunit is in the middle time, for example, if the time length of the time subunit is 1 second, the middle time point of the time subunit is 0.5 seconds, and the water flow data of the waterway is obtained by installing a flow meter on the main water supply branch;

[0076] The water flow data collected at the middle time point of each time sub-unit are integrated and processed to obtain a water flow unit group within the time sub-unit;

[0077] The water flow unit group is processed according to the mean calculation formula to obtain the water flow unit mean in the time subunit, which is recorded as the unit water flow value;

[0078] It should be noted that in the abnormal analysis of the waterway, the water flow in the waterway may change instantaneously, that is, the collected data is instantaneous data, which cannot accurately represent the overall state of the waterway. Therefore, the collection method of using the average value for the water flow will have higher accuracy;

[0079] Based on all the unit water flow values ​​obtained during the monitoring period, a prediction model is constructed to predict the water flow in the future. Specifically:

[0080] All unit water flow values ​​obtained within the monitoring period are integrated to obtain a water flow value group;

[0081] Apply sliding window technique to the data set to calculate the average value and obtain the time series feature, i.e., the sliding window average value;

[0082] Build ARIMA model based on time series characteristics;

[0083] It should be noted that the ARIMA model is an autoregressive integrated moving average model, which is suitable for the prediction of stable time series data. The general form of the ARIMA model is ARIMA (p, d, q), which consists of three parameters, where p is the order of the autoregressive term, d is the number of differences, which is used to make the time series stable, and q is the order of the moving average term. The values ​​of p and q are obtained through the autocorrelation function (ACF) and partial autocorrelation function (PACF) charts, and the d value is obtained through the unit root test (ADF);

[0084] The general form of the ARIMA(p,d,q) model is Among them, YC t is the observed value at time t, that is, the water flow value of the waterway at time t obtained by monitoring, φ1, φ2, ..., φ p is the autoregressive coefficient, ∈ t is the white noise error term at time t, θ1,θ2,...,θ q is the moving average coefficient, is d times difference operation;

[0085] It should be noted that the ARIMA (p, d, q) model includes an autoregressive part (AR), a moving average part (MA) and an integration part (I). The autoregressive part captures the linear relationship of the time series itself, the integration part removes the trend and seasonality through the difference operation to make the time series stable, and the moving average part captures the correlation between random error terms.

[0086] Use the constructed prediction model to predict the water flow in the future and obtain the predicted value of the water flow;

[0087] It should be noted that the future period is the set value, because in the process of predicting future data by the prediction model, the farther away from the current moment, the lower the accuracy of the prediction result, and it has no reference value. Therefore, for the future prediction data, only the data of the recent period is selected. For example, after using the prediction model to predict the future water pressure and water flow, the prediction values ​​for the next week and month are obtained, and only the data of the next 24 hours are selected as the prediction value;

[0088] Based on the predicted water flow values ​​in the future, actual water flow data in the waterway is collected in real time from the current moment until all the collected actual values ​​match the model predicted values ​​one by one;

[0089] According to the predicted value and the actual value of water flow, a corresponding chart between the predicted value and the actual value is constructed;

[0090] Based on the corresponding chart, the difference between the predicted value and the actual value of the water flow is calculated and recorded as the water flow prediction error;

[0091] All the obtained prediction errors are integrated to obtain a water flow prediction error group;

[0092] The water flow prediction error group is calculated according to the standard deviation calculation formula to obtain the standard deviation of the water flow prediction error;

[0093] The standard deviation multiple method was used to set the error threshold to twice the standard deviation of the water flow prediction error;

[0094] comparing the prediction error to an error threshold;

[0095] If the prediction error is greater than the error threshold, the data point is considered to be an abnormal point, that is, the water flow at this moment is abnormal, and a waterway abnormality signal is generated;

[0096] If the prediction error is less than or equal to the error threshold, the current data point is considered to be a normal point, that is, the current water flow is normal, and a normal waterway signal is generated.

[0097] Example 3

[0098] This embodiment describes in detail how to perform a detailed analysis of the pump status through the pump speed and current consumption:

[0099] Based on the waterway abnormality signal generated above, since the abnormality of the working state of the pump when working will cause the abnormality of the waterway, it is analyzed and judged whether the abnormality of the waterway is related to the abnormality of the working state of the pump when working. If there is an influence relationship, it is convenient to adjust or maintain the pump in time when the pump is working, reduce the influence of the pump on the waterway system in the marine integrated sanitary unit, effectively maintain the stability of the waterway system in the marine integrated sanitary unit, and thus reduce the difficulty of the actual assembly and commissioning of the marine integrated sanitary unit;

[0100] In a specific embodiment:

[0101] In a monitoring cycle, the speed and current of the pump are collected when the time unit is in the middle moment;

[0102] All the speeds and currents collected in the time sub-units are integrated to obtain a unit speed group and a unit current group;

[0103] The unit speed group and the unit current group are processed according to the mean value calculation formula to obtain the mean value of the speed and the mean value of the current in the time sub-unit, which are recorded as the unit speed value and the unit current value;

[0104] All unit speed values ​​and unit current values ​​collected during the monitoring period are integrated and processed to obtain a speed value group and a current value group;

[0105] The speed value group and the current value group are processed according to the mean value calculation formula to obtain the speed mean value and the current mean value within the monitoring period;

[0106] By formula The difference between the speed and the current is calculated C(Z,D);

[0107] Wherein, Z is the speed value, ZJ is the speed mean value, D is the current value, DJ is the current mean value, i is the number of time subunits, i=1,2,...,n;

[0108] The speed value group and the current value group are processed according to the standard deviation calculation formula to obtain the speed standard deviation ZC and the current standard deviation DC;

[0109] By formula The correlation coefficient r between the pump speed and current is calculated;

[0110] Compare the correlation coefficient r between the rotation speed and the current with a correlation threshold;

[0111] If the correlation coefficient is greater than or equal to the correlation threshold, it means that there is a strong correlation between the speed and current of the pump at that moment, and a normal pump signal is generated;

[0112] If the correlation coefficient is less than the correlation threshold, it means that the speed and current of the pump at that moment are abnormal, and a pump abnormality signal is generated;

[0113] It should be noted that by monitoring the speed and current consumption of the pump, a more comprehensive understanding of the comprehensive status of the pump can be obtained. These two parameters reflect the mechanical output and power consumption of the pump respectively. When used together, they can provide more accurate diagnostic information. Generally, there is a strong positive correlation between the speed and current of the pump. The higher the speed, the higher the current consumption.

[0114] The higher the speed of the pump, the greater the water flow rate provided by the pump. If the correlation between speed and current weakens, it means that the speed has increased but the current consumption has not increased accordingly, or the current consumption of the pump has increased but the speed has not increased. If the speed increases but the current consumption does not increase accordingly, it indicates that the efficiency of the pump has decreased or there is a mechanical failure. If the current consumption of the pump increases but the speed does not increase, it indicates that there is a foreign object stuck inside the pump or the internal parts of the pump are severely worn.

[0115] Example 4

[0116] This embodiment further describes how to comprehensively judge the causal relationship between water flow and pump through abnormal water flow status and pump abnormal status and take corresponding measures:

[0117] Based on the abnormal waterway signal and the abnormal pump signal, analyze whether the abnormal waterway is related to the abnormal pump, and take measures to improve the impact of the pump on the waterway system in the marine integrated sanitary unit. Specifically:

[0118] In one monitoring cycle, all the collected unit water flow values ​​are integrated to obtain a water flow group;

[0119] All the collected unit speed values ​​and unit current values ​​are integrated to obtain a speed value group and a current value group, and each value in the speed value group is matched one by one with each value in the current value group according to the time series to obtain a pump state group;

[0120] Analyze and judge the water flow group, extract all data points where water flow abnormalities occur, and record the corresponding time periods;

[0121] At the same time, the pump status group is analyzed and judged, all data points where pump abnormalities occur are extracted, and the corresponding time periods are recorded;

[0122] Add a label to each data point in the water flow group, mark the data point with abnormal water flow as -1, and mark the data point with normal water flow as 1;

[0123] Based on the label of each data point in the water flow group, a positive and negative scatter plot of water flow is drawn with time as the horizontal axis and the label of each data point in the water flow group as the vertical axis;

[0124] It should be noted that each point in the scatter plot has only two values, one is 1 and the other is -1, which are above and below the horizontal axis respectively. Through such a binary division, the time periods of normal and abnormal water flow can be distinguished more clearly;

[0125] Based on the data points of the pump abnormality, a label is added to the working status of the pump at each moment in the pump status group, and the data points of the pump normal condition are recorded as 1, and the data points of the pump abnormal condition are recorded as -1;

[0126] With time as the horizontal axis and the label of each data point in the pump state group as the vertical axis, draw a positive and negative scatter plot of the pump state;

[0127] The positive and negative scatter plots of water flow and the positive and negative scatter plots of pump status are merged according to time to obtain a water pump relationship diagram;

[0128] Extract the time period of abnormal water flow and the time period of pump abnormality in the water pump relationship diagram, and obtain the time period in which the abnormal water flow time period overlaps with the abnormal pump time period, which is recorded as the overlapping time period;

[0129] Integrate all the overlapping time periods in the pump relationship diagram to obtain the total overlapping time;

[0130] comparing the total coincidence time to a time threshold;

[0131] If the total overlap time is greater than or equal to the time threshold, it means that the abnormality of water flow is caused by the abnormality of the pump, and a water pump impact signal is generated;

[0132] If the total overlap time is less than the time threshold, it means that the abnormality of water flow is not caused by the abnormality of the pump, and a water pump non-influence signal is generated;

[0133] Based on the water pump impact signal, a pump failure notification is sent to the management personnel to remind the management personnel to repair or replace the pump.

[0134] Working principle of the invention: The purpose of the invention is to provide an assembly process for a ship-mounted integrated sanitary unit. The invention proposes a new assembly process for a ship-mounted integrated sanitary unit, which relates to the technical field of integrated sanitary units in ship engineering. This technical field is committed to improving the stability and reliability of the operation of ship sanitary systems by optimizing monitoring methods and fault diagnosis processes. The present invention particularly focuses on using data analysis methods to monitor water flow changes in real time, and conducts a comprehensive evaluation in combination with the working status of the pump to achieve rapid response and processing of potential faults. This technological innovation is of great significance for ensuring ship safety and improving the quality of life of crew members. Specifically, the process monitors the changing trend of water flow in real time and conducts a comprehensive analysis in combination with the working status of the pump, which can effectively identify and accurately locate the source of faults in the system, prompting managers to quickly take corresponding control or maintenance measures, thereby greatly improving the stability and maintenance efficiency of the system. Specifically, in the basic monitoring process, firstly, a high-precision flow meter is used to continuously collect the water flow data of the internal waterway of the sanitary unit, and an ARIMA prediction model is constructed based on these data to predict the change trend of the future water flow; then, the prediction result is compared with the actual water flow value, and the error is calculated. When the error exceeds the preset threshold, an abnormal signal is generated, otherwise a normal signal is generated; at the same time, the speed and current consumption of the pump are recorded on the same time scale, and the correlation between the waterway state signal and the pump state signal is analyzed, and a comprehensive assessment is made whether there is a causal relationship between the two, and a water pump influence signal or a non-influence signal is generated accordingly; finally, a fault warning information is sent to the management personnel based on the water pump influence signal. In addition, in terms of time series refinement monitoring, the present invention also subdivides the monitoring cycle into multiple equal-length time subunits, and further divides it into smaller time units, collects water flow data at the middle time point of each time unit, eliminates the influence of instantaneous fluctuations by averaging, and then uses the sliding window technology to extract time series features, and builds an ARIMA model based on this and trains, adjusts and evaluates its performance, and finally uses the trained model to predict the water flow in the future period of time, and compares it with the actual value to determine whether there is an abnormality. In terms of detailed analysis of the pump status, the speed and current consumption of the pump in the middle of each time unit are recorded, the average speed and current consumption of the pump in the entire monitoring period are calculated, and correlation analysis is performed to determine whether the pump operation status is normal. If there is a strong positive correlation between the speed and current consumption of the pump, a normal signal is generated, otherwise an abnormal signal is generated. Finally, in the comprehensive judgment of causal relationships, the abnormal water flow period is compared with the abnormal pump period to find out whether there is an overlapping time period. If most of the abnormal conditions occur during the pump failure, the water flow abnormality is determined to be caused by the pump and an impact signal is generated. Otherwise, a non-impact signal is generated, and corresponding measures are taken according to the specific situation.In summary, the present invention not only realizes the accurate monitoring of the operating status of the water system of the marine integrated sanitary unit, but also provides a scientific and reasonable fault diagnosis method, which helps to significantly improve the stability and reliability of the system.

[0135] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A process for assembling a marine integrated sanitary unit, characterized in that: The following steps are involved: Collect water flow data in the waterways within the sanitary unit; Based on water flow data, a prediction model is constructed to predict the trend of water flow changes; Compare the predicted result of water flow with the actual water flow value to obtain the error between the two; Compare the error with a preset error threshold and generate a waterway status signal; The pump speed and current consumption data were recorded synchronously on the same time scale as the water flow data acquisition; Based on the water circuit status signal, the strength of the relationship between the rotational speed and the current consumption of the pump is evaluated to generate a pump status signal; The causal relationship between the waterway status signal and the pump status signal is comprehensively analyzed to generate the pump impact signal and the pump non-influence signal.

2. A marine integrated sanitary unit assembly process according to claim 1, characterized in that: Define the monitoring period, subdivide the monitoring period into multiple time sub-units of equal length, and further divide them into smaller time sub-units; Collect water flow data at the middle point of each time unit; The water flow data collected at the middle time point of each time sub-unit are integrated and processed to obtain a water flow unit group within the time sub-unit; The water flow unit group is processed according to the mean calculation formula to obtain the water flow unit mean in the time subunit, which is recorded as the unit water flow value.

3. A marine integrated sanitary unit assembly process according to claim 2, characterized in that: Based on all unit water flow values ​​obtained during the monitoring period, the sliding window technology is used to extract time series features, and a water flow prediction model is built based on this; Use the constructed water flow prediction model to predict the water flow in the future and obtain the predicted value of the water flow; Based on the predicted value of the water flow, actual water flow data at a time corresponding to the predicted value of the water flow is obtained.

4. A marine integrated sanitary unit assembly process according to claim 3, characterized in that: According to the predicted value and the actual value of the water flow, the difference between the predicted value and the actual value of the water flow is calculated and recorded as the water flow prediction error; All the obtained prediction errors are integrated to obtain a water flow prediction error group; The water flow prediction error group is calculated according to the standard deviation calculation formula to obtain the standard deviation of the water flow prediction error; Using the standard deviation multiple method, the error threshold is set to twice the standard deviation of the water flow prediction error.

5. A marine integrated sanitary unit assembly process according to claim 4, characterized in that: comparing the prediction error to an error threshold; If the prediction error is greater than the error threshold, a waterway abnormality signal is generated; If the prediction error is less than or equal to the error threshold, a normal waterway signal is generated.

6. A marine integrated sanitary unit assembly process according to claim 5, characterized in that: Synchronously record the pump speed and current consumption at the middle moment of each time unit; All the speeds and currents collected in the time sub-unit are integrated and averaged to obtain the average values ​​of the speed and current in the time sub-unit, which are recorded as the unit speed value and the unit current value respectively; All unit speed values ​​and unit current values ​​collected during the monitoring period are integrated and averaged to obtain the average speed and current of the pump during the monitoring period; By formula The difference between the speed and the current is calculated C(Z,D); Among them, Z is the speed value, ZJ is the average speed value, D is the current value, DJ is the average current value, and i is the number of time subunits, i=1,2,...,n.

7. A marine integrated sanitary unit assembly process according to claim 6, characterized in that: Based on the difference between the speed and the current, the speed value group and the current value group are processed according to the standard deviation calculation formula to obtain the speed standard deviation and the current standard deviation; The difference between the speed and the current is multiplied by the product of the standard deviation between the speed and the current to calculate the correlation coefficient between the speed and the current; Compare the correlation coefficient r between the rotation speed and the current with a correlation threshold; If the correlation coefficient is greater than or equal to the correlation threshold, a pump normal signal is generated; If the correlation coefficient is less than the correlation threshold, a pump abnormality signal is generated.

8. The assembly process of a marine integrated sanitary unit according to claim 7, characterized in that: Based on the abnormal waterway signal and the abnormal pump signal, all unit water flow values ​​collected during the monitoring period are integrated and processed to obtain a water flow group; Each value in the speed value group is matched with each value in the current value group in a one-to-one manner according to a time series to obtain a pump state group; The water flow group and the pump status group are analyzed and judged, all data points with abnormal water flow and pump conditions are identified, and all data points in the water flow group and the pump status group are divided into normal data points and abnormal data points.

9. A marine integrated sanitary unit assembly process according to claim 8, characterized in that: Based on all normal data points and abnormal data points in the water flow group and the pump status group, a label is added to each data point in the water flow group, and the data point of the abnormal water flow is marked as -1, and the data point of the normal water flow is marked as 1; Based on the label of each data point in the water flow group, a positive and negative scatter plot of water flow is drawn with time as the horizontal axis and the label of each data point in the water flow group as the vertical axis; Based on the data points of the pump abnormality, a label is added to the working status of the pump at each moment in the pump status group, and the data points of the pump normal condition are recorded as 1, and the data points of the pump abnormal condition are recorded as -1; With time as the horizontal axis and the label of each data point in the pump state group as the vertical axis, draw a positive and negative scatter plot of the pump state.

10. A marine integrated sanitary unit assembly process according to claim 9, characterized in that: The positive and negative scatter plots of water flow and the positive and negative scatter plots of pump status are merged according to time to obtain a water pump relationship diagram; Extract the time period of abnormal water flow and the time period of pump abnormality in the water pump relationship diagram, and obtain the time period in which the abnormal water flow time period overlaps with the abnormal pump time period, which is recorded as the overlapping time period; Integrate all the overlapping time periods in the pump relationship diagram to obtain the total overlapping time; comparing the total coincidence time to a time threshold; If the total overlap time is greater than or equal to the time threshold, a water pump impact signal is generated; If the total coincidence time is less than the time threshold, a pump non-impact signal is generated.

Images