Water station equipment life prediction and health management system and method

Abstract

The invention relates to the technical field of information, in particular to a water station equipment life prediction and health management system and method, and the system comprises a data collection module, a data transmission module, a data processing module, and a data storage module. The data collection module is used for collecting state parameters and operation parameters of water station equipment in real time; the data transmission module is connected with the data collection module, and the data transmission module is used for transmitting information collected by the data collection module to the data processing center; the data processing module is used for performing data processing on the information received by the data processing center and predicting the service life of the water station equipment; the data storage module is used for recording the state parameters and the operation parameters, collected by the data collection module in real time, of the water station equipment and data parameters obtained after the data processing module processes the state parameters and the operation parameters, and the data storage module is further used for storing replacement information of the water station equipment; and the service life of the water station is predicted and the health of the water station is evaluated through multi-dimensional data acquisition.

Description

Technical Field

[0001] The present invention relates to the field of information technology, and in particular to a water station equipment life prediction and health management system and method. Background Art

[0002] With the continuous advancement of water resource protection and water pollution control, water station equipment plays a vital role in water quality monitoring, water resource management, and water environment protection. However, stable operation and timely maintenance of water station equipment are crucial to ensuring its effective function. Traditional water station equipment management methods often rely on regular manual inspections and simple maintenance records, which have many limitations. First, equipment lifespan predictions lack scientific and accurate information. Due to the lack of comprehensive analysis of equipment operating data and effective predictive models, equipment managers struggle to predict potential equipment failures and end-of-life dates. Typically, equipment is repaired or replaced only after obvious failures or severe performance degradation. This not only causes unexpected equipment downtime, impacting normal water quality monitoring operations, but also increases costs due to emergency repairs. For example, some key water quality monitoring instruments, such as dissolved oxygen monitors and chemical oxygen demand (COD) monitors, can suddenly fail during use without effective lifespan predictions, preventing water stations from obtaining timely and accurate water quality data and hindering assessments and decision-making regarding water resource conditions. Furthermore, equipment health management is also deficient. Existing management systems often fail to monitor equipment's operating status in real time, making it difficult to identify potential health issues. Equipment health assessments rely primarily on manual experience and simple visual inspections, making it difficult to detect potential internal faults. For example, a water pump is a critical piece of equipment in a water station. Due to long-term continuous operation, its internal mechanical components gradually wear out. However, relying solely on regular manual inspections makes it difficult to detect this wear and tear early and repair it promptly. By the time the problem becomes severe, it can cause the pump to fail, impacting the station's normal water supply or drainage functions. Summary of the Invention

[0003] In view of this, the present invention addresses the deficiencies in the prior art and proposes a water station equipment life prediction and health management system and method, aiming to solve at least one of the problems raised in the above background technology.

[0004] Firstly,

[0005] The present invention provides a water station equipment life prediction and health management system, comprising: a data collection module, the data collection module being arranged inside the water station equipment, the data collection module being used to collect status parameters and operating parameters of the water station equipment in real time;

[0006] A data transmission module, the data transmission module is connected to the data collection module, and the data transmission module is used to transmit the information collected by the data collection module to a data processing center;

[0007] A data processing module, the data processing module is used to process the information received by the data processing center and predict the life of water station equipment;

[0008] A data storage module is used to record the status parameters and operating parameters of the water station equipment collected in real time by the data collection module and the data parameters after the status parameters and operating parameters are processed by the data processing module. The data storage module is also used to store replacement information of the water station equipment.

[0009] In some embodiments, the data collection module includes a first pressure sensor, a second pressure sensor, a flow sensor, a temperature sensor, a vibration sensor, and a water quality sensor. The vibration sensor and the first pressure sensor are provided on the water pump in the water station equipment. The vibration sensor is used to monitor the vibration frequency of the water pump, and the first pressure sensor is used to monitor the first pressure at the water outlet of the water pump.

[0010] The transmission pipeline in the water station equipment is provided with the flow sensor and the second pressure sensor, the flow sensor is used to monitor the water flow in the transmission pipeline, and the second pressure sensor is used to detect the second pressure in the transmission pipeline;

[0011] The temperature sensor is arranged inside the power distribution cabinet of the water station equipment, and the temperature sensor is used to monitor the temperature inside the power distribution cabinet;

[0012] The water quality sensor is arranged on the water storage tank of the water station equipment, and the water quality sensor is used to monitor the water quality of the purified water inside the water storage tank.

[0013] In some embodiments, the state parameters are temperature parameters inside the power distribution cabinet and water quality parameters of purified water inside the water storage tank;

[0014] The operating parameters include: a vibration frequency parameter of the water pump, a first pressure parameter of the water outlet of the water pump, a second pressure parameter in the transmission pipeline, and a water flow parameter in the transmission pipeline.

[0015] In some embodiments, the data transmission module transmits the temperature parameter, water quality parameter, vibration frequency parameter, first pressure parameter, second pressure parameter, and water flow parameter to the data processing center via wireless communication.

[0016] In a second aspect, the present invention provides a method for predicting the lifespan and health management of water station equipment, wherein the data processing comprises the following steps:

[0017] S1. Preprocessing the temperature parameter, water quality parameter, vibration frequency parameter, first pressure parameter, second pressure parameter, and water flow parameter;

[0018] S2. Construct a water station equipment life prediction model based on a machine learning algorithm, with the pre-processed temperature parameter, water quality parameter, vibration frequency parameter, first pressure parameter, second pressure parameter, and water flow parameter as input variables, and the remaining life of the water station equipment as the output variable.

[0019] In some embodiments, step S1 performs data preprocessing on temperature parameters, water quality parameters, vibration frequency parameters, first pressure parameters, second pressure parameters, and water flow parameters, including: smoothing the temperature parameters by a moving average method; standardizing water quality parameters of different magnitudes by a Z-score standardization method; obtaining spectrum information by performing a fast Fourier transform on the vibration frequency parameters, and analyzing the characteristic frequencies and amplitude changes in the spectrum to extract features related to the water pump failure; smoothing the first pressure parameter by a sliding average method; smoothing the second pressure parameter by a spline curve fitting method; and smoothing the water flow parameter by an exponential smoothing method.

[0020] In some embodiments, the machine learning algorithm is a support vector machine model, the pre-threshold is set to A, the output variable is B, when B>A, the corresponding equipment is in a state waiting for maintenance; when B≤A, the corresponding equipment is in a safe state.

[0021] In some embodiments, when water station equipment is replaced, the replacement time and replacement times of the corresponding equipment are recorded in the data storage module, and the service life of the equipment is predicted by calculating the replacement cycle of the corresponding equipment.

[0022] In some embodiments, the replacement information includes the equipment name, model specifications, manufacturer, purchase date, installation location, and using department of the water station equipment.

[0023] In some embodiments, the pre-threshold value A includes: a temperature parameter threshold value, a water quality parameter threshold value, a vibration frequency parameter threshold value, a first pressure parameter threshold value, a second pressure parameter threshold value, and a water flow parameter threshold value.

[0024] Compared with the prior art, the beneficial effect of the present invention is that the system can collect a variety of state parameters (such as temperature, vibration frequency, etc.) and operating parameters (such as pressure, flow, etc.) of water station equipment in real time, covering information on all key links of the water station equipment. For example, by setting a vibration sensor and a first pressure sensor on the water pump, the operating status of the water pump can be accurately monitored; by setting a flow sensor and a second pressure sensor on the transmission pipeline, the actual situation of the water in the pipeline can be grasped. This multi-dimensional data collection lays a solid data foundation for subsequent accurate life prediction and health assessment. The data storage module not only records various parameters collected in real time, but also stores equipment replacement information, including equipment name, model specifications, manufacturer, purchase date, installation location, using department and other details. This enables the system to fully trace the history of the equipment, and combined with information such as replacement cycle, better predict the service life of the equipment, and also facilitates equipment management and operation and maintenance personnel to query and manage equipment information.

[0025] The collected data undergoes various scientific preprocessing techniques, such as smoothing the temperature parameters using the moving average method to reduce interference caused by data fluctuations; standardizing the water quality parameters using the Z-score standardization method to make data of different magnitudes comparable; and performing a fast Fourier transform on the vibration frequency parameters to extract features related to water pump failures. These preprocessing methods improve data quality and provide reliable data support for subsequent accurate life prediction and health assessment. A water station equipment life prediction model is constructed based on machine learning algorithms (such as support vector machine models), using the preprocessed temperature parameters, water quality parameters, vibration frequency parameters, first pressure parameters, second pressure parameters, and water flow parameters as input variables, and the remaining life of the water station equipment as the output variable. This model can learn complex relationships in the data and accurately predict the life of the equipment.

[0026] The foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure.

[0027] Other features and aspects of the present disclosure will become more apparent from the following detailed description of exemplary embodiments with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0029] Figure 1This is a structural block diagram of the water station equipment life prediction and health management system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0030] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0031] In the description of this application, it should be understood that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating the orientation or position relationship, are based on the orientation or position relationship shown in the accompanying drawings, and are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on this application.

[0032] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature specified as "first" or "second" may explicitly or implicitly include one or more of such features. Throughout this application, unless otherwise specified, "plurality" means two or more.

[0033] In the description of this application, it should be noted that, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood in a broad sense. For example, they can refer to fixed, detachable, or integral connections; mechanical or electrical connections; direct or indirect connections through an intermediate medium; and internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in this application based on the specific circumstances.

[0034] See Figure 1 As shown in the first embodiment, a water station equipment life prediction and health management system according to an embodiment of the present application includes:

[0035] Data collection module, the data collection module is set inside the water station equipment, the data collection module is used to collect the status parameters and operating parameters of the water station equipment in real time;

[0036] A data transmission module, the data transmission module is connected to the data collection module, and the data transmission module is used to transmit the information collected by the data collection module to the data processing center;

[0037] Data processing module, which is used to process the information received by the data processing center and predict the life of water station equipment;

[0038] The data storage module is used to record the status parameters and operating parameters of the water station equipment collected in real time by the data collection module, as well as the data parameters processed by the data processing module. The data storage module is also used to store replacement information of the water station equipment.

[0039] In some specific embodiments, the data collection module includes a first pressure sensor, a second pressure sensor, a flow sensor, a temperature sensor, a vibration sensor, and a water quality sensor. The water pump in the water station equipment is provided with a vibration sensor and a first pressure sensor. The vibration sensor is used to monitor the vibration frequency of the water pump, and the first pressure sensor is used to monitor the first pressure at the water outlet of the water pump.

[0040] It should be understood that various types of sensors, including but not limited to pressure sensors, flow sensors, temperature sensors, vibration sensors, and water quality sensors, are installed on key water station equipment to collect real-time operating parameters and environmental information. Vibration sensors and pressure sensors are installed on water pumps to monitor their vibration frequency and outlet pressure; flow sensors and pressure sensors are installed on pipelines to monitor changes in water flow and pressure. Temperature sensors and current sensors are installed on important electrical equipment, such as transformers and distribution cabinets, to monitor operating temperature and current.

[0041] A flow sensor and a second pressure sensor are provided on the transmission pipeline in the water station equipment. The flow sensor is used to monitor the water flow in the transmission pipeline, and the second pressure sensor is used to detect the second pressure in the transmission pipeline;

[0042] The temperature sensor is installed inside the power distribution cabinet of the water station equipment. The temperature sensor is used to monitor the temperature inside the power distribution cabinet;

[0043] The water quality sensor is installed on the water storage tank of the water station equipment. The water quality sensor is used to monitor the water quality of the purified water inside the water storage tank.

[0044] In some specific embodiments, the state parameters are temperature parameters inside the power distribution cabinet and water quality parameters of purified water inside the water storage tank;

[0045] The operating parameters include: a vibration frequency parameter of the water pump, a first pressure parameter of the water outlet of the water pump, a second pressure parameter in the transmission pipeline, and a water flow parameter in the transmission pipeline.

[0046] In some specific embodiments, the data transmission module transmits the temperature parameter, water quality parameter, vibration frequency parameter, first pressure parameter, second pressure parameter, and water flow parameter to the data processing center via wireless communication.

[0047] It should be understood that the data collected by the sensor is transmitted to the data processing center using wired communication (such as RS485, Ethernet, etc.) or wireless communication (such as GPRS, 4G / 5G, ZigBee, etc.). For water station equipment with more dispersed distribution, wireless communication can be used to reduce wiring costs; this application prefers wireless communication, and for centralized equipment, wired communication can be used to improve the stability and speed of data transmission.

[0048] In a second embodiment, according to a method for predicting the lifespan and health management of water station equipment according to an embodiment of the present application, data processing includes the following steps:

[0049] S1. Preprocessing the temperature parameter, water quality parameter, vibration frequency parameter, first pressure parameter, second pressure parameter, and water flow parameter;

[0050] S2. Build a water station equipment life prediction model based on the machine learning algorithm, with the pre-processed temperature parameters, water quality parameters, vibration frequency parameters, first pressure parameters, second pressure parameters, and water flow parameters as input variables, and the remaining life of the water station equipment as the output variable.

[0051] In some specific embodiments, step S1 performs data preprocessing on temperature parameters, water quality parameters, vibration frequency parameters, first pressure parameters, second pressure parameters, and water flow parameters, including: smoothing the temperature parameters by a moving average method; standardizing water quality parameters of different magnitudes by a Z-score standardization method; obtaining spectrum information by performing a fast Fourier transform on the vibration frequency parameters, analyzing the characteristic frequencies and amplitude changes in the spectrum, and extracting features related to water pump failures; smoothing the first pressure parameter by a sliding average method; smoothing the second pressure parameter by a spline curve fitting method; and smoothing the water flow parameter by an exponential smoothing method.

[0052] It should be understood that due to temperature sensor failure or other interference factors, individual data points may deviate from the normal range. Statistical methods, such as calculating the mean and standard deviation, can be used to treat data outside a certain range (such as the mean ± 3 times the standard deviation) as outliers and eliminate or correct them. For a small amount of missing temperature data, linear interpolation can be performed based on the temperature data of the previous and next moments, or other appropriate interpolation methods can be used to fill in the gaps. Use a moving average method, such as a simple moving average or a weighted moving average, to smooth the temperature data to reduce data fluctuations. For example, take the average of 5 consecutive data points as the smoothed value at the current moment.

[0053] Water quality data that clearly does not conform to actual conditions (such as negative turbidity values) should be corrected or eliminated. A reasonable data range can be set, and data outside the range can be considered abnormal. For small amounts of missing water quality data, estimates and infill can be made based on historical data or correlations with other relevant water quality parameters. For example, if residual chlorine data is missing but it is known to be related to factors such as source water quality and disinfection processes, a regression model can be established based on other relevant parameters to predict the residual chlorine value. Water quality parameters of different magnitudes should be standardized to ensure that each parameter has the same scale. The Z-score standardization method can be used. If the water quality parameter is a categorical variable (such as water quality grades of excellent, good, fair, and poor), it can be one-hot encoded to convert it into numerical form for model processing. For example, the water quality grade "excellent" can be encoded as [1,0,0,0], "good" as [0,1,0,0], and so on.

[0054] Due to interference from the pump's operating environment, the data collected by the vibration sensor may contain noise. Filters (such as low-pass filters and band-pass filters) can be used to filter the data and remove high-frequency noise. For data points that significantly deviate from the normal vibration frequency range, check whether they are caused by sensor failure or special circumstances, and make corrections or eliminate them. In addition to directly using the vibration frequency value, its statistical characteristics, such as mean, variance, peak value, kurtosis, etc., can also be calculated. These characteristics can more comprehensively reflect the characteristics of the vibration frequency. By performing a fast Fourier transform (FFT) on the vibration frequency data, spectral information is obtained, and the characteristic frequencies and amplitude changes in the spectrum are analyzed to extract features related to the pump failure. The vibration frequency data or its characteristics are normalized to a suitable range for comprehensive analysis and model training with other parameters. Methods such as minimum-maximum normalization or Z-score normalization can be used.

[0055] Check whether there are abnormally high or low values ​​in the pressure data, which may be caused by sensor failure, pipe blockage or instantaneous pressure shock. For abnormal values, they can be judged and corrected based on physical principles and actual operating conditions. For a small amount of missing pressure data, linear interpolation or other appropriate interpolation methods can be used to fill in the gaps based on the pressure data at adjacent moments. Use appropriate smoothing algorithms, such as sliding average, exponential smoothing, etc., to smooth the pressure data to reduce the impact of pressure fluctuations. For example, use the sliding average method to average multiple consecutive data points to obtain a smoother pressure curve. Standardize the first pressure parameter data so that it has zero mean and unit variance. This can eliminate the influence between data of different magnitudes, facilitating subsequent data analysis and model training. Commonly used standardization methods include Z-score standardization.

[0056] Check that the pressure data is within a reasonable range. For data points outside this range, analyze the cause and make corrections or eliminate them. For example, if negative pressure in a transmission pipeline persists for a short period of time, it may be caused by a momentary sensor failure, which can be corrected based on the actual situation. For small amounts of missing pressure data, estimate and fill in the gaps based on the pressure trend within the transmission pipeline or other relevant pressure parameters. For example, if the pressure and flow rate at the pipeline inlet and outlet are known, a pressure drop model can be developed to estimate the missing pressure values.

[0057] Check the water flow data for values ​​that clearly exceed the normal range. This may be due to sensor failure, pipe leaks, or sudden changes in water flow. For outliers, make judgments and corrections based on historical data and actual operating conditions. For small amounts of missing water flow data, fill in the gaps by using linear interpolation or other appropriate interpolation methods based on flow data at adjacent moments. If there is a large amount of missing data, consider using a data completion algorithm, such as a time series-based forecasting model, to fill in the missing values. Use appropriate smoothing methods, such as moving averages and exponential smoothing, to smooth the water flow data to reduce the impact of flow fluctuations. For example, use exponential smoothing to smooth the flow data, giving more weight to recent data.

[0058] In some specific embodiments, the machine learning algorithm is a support vector machine model, the pre-threshold is set to A, the output variable is B, when B>A, the corresponding equipment is in a state waiting for maintenance; when B≤A, the corresponding equipment is in a safe state.

[0059] In some specific embodiments, when water station equipment is replaced, the replacement time and replacement frequency of the corresponding equipment are recorded in the data storage module, and the service life of the equipment is predicted by calculating the replacement cycle of the corresponding equipment.

[0060] In some specific embodiments, the replacement information includes the equipment name, model specification, manufacturer, purchase date, installation location, and user department of the water station equipment.

[0061] In some specific embodiments, the pre-threshold value A includes: a temperature parameter threshold value, a water quality parameter threshold value, a vibration frequency parameter threshold value, a first pressure parameter threshold value, a second pressure parameter threshold value, and a water flow parameter threshold value.

[0062] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A water station equipment life prediction and health management system, characterized by: include: A data collection module is provided inside the water station equipment and is used to collect status parameters and operating parameters of the water station equipment in real time; A data transmission module, the data transmission module is connected to the data collection module, and the data transmission module is used to transmit the information collected by the data collection module to a data processing center; A data processing module, the data processing module is used to process the information received by the data processing center and predict the life of water station equipment; A data storage module is used to record the status parameters and operating parameters of the water station equipment collected in real time by the data collection module and the data parameters after the status parameters and operating parameters are processed by the data processing module. The data storage module is also used to store replacement information of the water station equipment.

2. A water station equipment life prediction and health management system according to claim 1, characterized in that: The data collection module includes a first pressure sensor, a second pressure sensor, a flow sensor, a temperature sensor, a vibration sensor, and a water quality sensor. The vibration sensor and the first pressure sensor are provided on the water pump in the water station equipment. The vibration sensor is used to monitor the vibration frequency of the water pump, and the first pressure sensor is used to monitor the first pressure at the water outlet of the water pump; The transmission pipeline in the water station equipment is provided with the flow sensor and the second pressure sensor, the flow sensor is used to monitor the water flow in the transmission pipeline, and the second pressure sensor is used to detect the second pressure in the transmission pipeline; The temperature sensor is arranged inside the power distribution cabinet of the water station equipment, and the temperature sensor is used to monitor the temperature inside the power distribution cabinet; The water quality sensor is arranged on the water storage tank of the water station equipment, and the water quality sensor is used to monitor the water quality of the purified water inside the water storage tank.

3. A water station equipment life prediction and health management system according to claim 2, characterized in that: The state parameters are the temperature parameters inside the power distribution cabinet and the water quality parameters of the purified water inside the water storage tank; The operating parameters include: a vibration frequency parameter of the water pump, a first pressure parameter of the water outlet of the water pump, a second pressure parameter in the transmission pipeline, and a water flow parameter in the transmission pipeline.

4. A water station equipment life prediction and health management system according to claim 3, characterized in that: The data transmission module transmits the temperature parameter, water quality parameter, vibration frequency parameter, first pressure parameter, second pressure parameter, and water flow parameter to the data processing center through wireless communication.

5. A method for predicting the life of water station equipment and managing its health, characterized in that: Applied to a water station equipment life prediction and health management system according to any one of claims 1 to 4, the data processing comprises the following steps: S1. Preprocessing the temperature parameter, water quality parameter, vibration frequency parameter, first pressure parameter, second pressure parameter, and water flow parameter; S2. Construct a water station equipment life prediction model based on a machine learning algorithm, with the pre-processed temperature parameter, water quality parameter, vibration frequency parameter, first pressure parameter, second pressure parameter, and water flow parameter as input variables, and the remaining life of the water station equipment as the output variable.

6. A water station equipment life prediction and health management method according to claim 5, characterized in that: The step S1 performs data preprocessing on the temperature parameter, water quality parameter, vibration frequency parameter, first pressure parameter, second pressure parameter, and water flow parameter, including: smoothing the temperature parameter by a moving average method; standardizing water quality parameters of different magnitudes by a Z-score standardization method; obtaining spectrum information by performing a fast Fourier transform on the vibration frequency parameter, analyzing the characteristic frequency and amplitude changes in the spectrum, and extracting features related to the water pump fault; smoothing the first pressure parameter by a sliding average method; smoothing the second pressure parameter by a spline curve fitting method; and smoothing the water flow parameter by an exponential smoothing method.

7. A water station equipment life prediction and health management method according to claim 6, characterized in that: The machine learning algorithm is a support vector machine model, which sets the pre-threshold value to A and the output variable to B. When B>A, the corresponding equipment is in a state waiting for maintenance; when B≤A, the corresponding equipment is in a safe state.

8. A water station equipment life prediction and health management method according to claim 7, characterized in that: When the water station equipment is replaced, the replacement time and replacement times of the corresponding equipment are recorded in the data storage module, and the service life of the equipment is predicted by calculating the replacement cycle of the corresponding equipment.

9. A water station equipment life prediction and health management method according to claim 8, characterized in that: The replacement information includes the equipment name, model specification, manufacturer, purchase date, installation location, and user department of the water station equipment.

10. A water station equipment life prediction and health management method according to claim 8, characterized in that: The pre-threshold value A includes: a temperature parameter threshold value, a water quality parameter threshold value, a vibration frequency parameter threshold value, a first pressure parameter threshold value, a second pressure parameter threshold value, and a water flow parameter threshold value.

Images