Cooling water system flow switch verification method and system

Abstract

The invention discloses a cooling water system flow switch verification method and system, and relates to the technical field of flow switch verification, and the method comprises the steps: detecting the current flow in real time through a flow adjusting device, comparing the current flow with a preset standard flow value, and adjusting the current flow to a preset reference state; according to the working condition of a cooling water system and the characteristics of a flow switch, the cooling water flow is adjusted through a self-adaptive flow adjusting algorithm, and data collection is conducted at multiple flow points; monitoring the triggering time and the response state of the flow switch at each flow point; analyzing historical response data of the flow switch through a machine learning algorithm, and identifying a potential fault trend of the flow switch; a report is generated based on the collected data and analysis results. According to the cooling water system flow switch calibration method provided by the invention, the downtime of the cooling water system is reduced, the operation efficiency of the system is improved, and the requirement for real-time calibration in an industrial process is met. And data deviation caused by temperature and pressure fluctuation is reduced.

Description

Technical Field

[0001] The invention relates to the technical field of flow switch calibration, and in particular to a cooling water system flow switch calibration method and system. Background Art

[0002] Cooling water systems are widely used in industrial applications for heat dissipation and temperature control of equipment. Flow switches are key monitoring and protection devices in this system, ensuring the safety and stable operation of equipment through real-time monitoring of flow. The flow switch calibration in the prior art mainly relies on laboratory equipment, and usually requires the flow switch to be disassembled and sent to a specific laboratory for calibration, which has the following shortcomings and limitations:

[0003] Since the flow switch is often located in the cooling water system and cannot be moved, the traditional method usually requires shutting down and disassembling the flow switch for laboratory calibration, resulting in long downtime of the cooling water system and low calibration efficiency, which increases the inconvenience and cost of industrial production.

[0004] Traditional calibration methods mainly rely on manual or semi-automatic detection, and fail to make adaptive adjustments to the real-time fluctuations in operating conditions in the cooling water system. This can easily lead to deviations in measurement results due to environmental factors, affecting the reliability and accuracy of the calibration.

[0005] Existing flow switch calibration methods are mostly based on static calibration methods, which fail to effectively identify potential failure trends and cannot achieve early prediction and maintenance reminders for flow switches, which can easily cause system failure hazards to be difficult to detect in time, thereby affecting the long-term stable operation of the cooling water system.

[0006] To sum up, the existing technology has defects in the calibration and fault prediction of flow switches, such as poor real-time performance, low sensitivity, and lack of fault prediction. There is an urgent need for a technical solution that can realize real-time and efficient calibration in the operating environment of the cooling water system and has fault prediction capabilities, so as to improve the reliability and work efficiency of flow switch calibration. Summary of the invention

[0007] In view of the above-mentioned problems, the present invention is proposed.

[0008] Therefore, the technical problem solved by the present invention is that the existing flow switch calibration usually requires the flow switch to be removed from the cooling water system and sent to the laboratory for testing. This offline calibration method not only increases the complexity of the operation, but also leads to a long system downtime, and cannot meet the demand for real-time monitoring in industrial processes.

[0009] Traditional flow switch calibration is mainly based on laboratory environment, which fails to fully consider the flow, temperature, pressure and other operating factors of the cooling water system in the operating environment. As a result, data collection is easily affected by fluctuations and the accuracy and sensitivity of the measurement results are low.

[0010] Traditional calibration methods mainly rely on static measurements, which fail to provide analysis of the response of the flow switch under dynamic conditions. Therefore, it is difficult to identify potential failure trends in a timely manner, and fail to meet the fault warning needs of the flow switch during long-term operation, increasing system risks.

[0011] In order to solve the above technical problems, the present invention provides the following technical solutions: a method for calibrating a flow switch of a cooling water system, comprising:

[0012] The current flow rate is detected in real time by the flow regulating device, and compared with the preset standard flow rate value, and adjusted to the predetermined reference state;

[0013] According to the working conditions of the cooling water system and the characteristics of the flow switch, an adaptive flow regulation algorithm is used to adjust the cooling water flow, and data is collected at multiple flow points;

[0014] Monitor the triggering time and response status of the flow switch at each flow point;

[0015] Analyze the historical response data of the flow switch through machine learning algorithms to identify potential failure trends of the flow switch;

[0016] Generate flow switch sensitivity, response time and fault prediction reports based on the collected data and analysis results.

[0017] As a preferred solution of the cooling water system flow switch calibration method of the present invention, wherein: the adjustment to the predetermined reference state includes using an ultrasonic flow sensor to measure the instantaneous flow velocity in the cooling water pipeline based on an ultrasonic time difference method;

[0018] Compare the measured instantaneous flow rate with the preset standard flow value in real time;

[0019] When the flow deviation exceeds the set allowable range, the flow is gradually adjusted to the predetermined reference state by controlling the valve opening and adjusting the pump speed.

[0020] As a preferred solution of the cooling water system flow switch calibration method of the present invention, wherein: the adjusting the cooling water flow includes real-time collection of operating parameters, and the operating parameters include water temperature, pipeline pressure and flow rate;

[0021] The operating condition parameters are used as input parameters of the flow rate change rate and flow rate fluctuation rate, and the current flow rate change rate is calculated in combination with the instantaneous flow rate;

[0022] When the flow rate change rate is lower than the threshold, it is determined that the flow point has reached a stable state and the calculation of the stable time begins.

[0023] As a preferred solution of the cooling water system flow switch calibration method described in the present invention, wherein: the calculation of the stabilization time is evaluated by using the difference factor method, comparing the relationship between the operating parameters and the flow fluctuation rate at the same flow point, and confirming whether the flow point is in a stable working condition by judging whether the operating parameters are within the normal range and the flow fluctuation rate is lower than the preset fluctuation threshold;

[0024] The flow points whose stable time is lower than the set threshold are marked as flow points that need to be repeatedly collected.

[0025] As a preferred solution of the cooling water system flow switch calibration method of the present invention, wherein: the monitoring of the triggering time and response state of the flow switch at each flow point includes collecting the electrical signal triggered by the flow switch, and the triggering of the electrical signal indicates the switching action of the flow switch when the preset flow value is reached;

[0026] The electrical signal is processed by a low-pass filter to remove high-frequency noise and environmental interference in the signal;

[0027] Comprehensively judging three response states of the flow switch based on the electrical signal amplitude, flow fluctuation rate and operating parameters, the three response states including open or closed state, trigger time and trigger delay time;

[0028] The open or closed state refers to analyzing the opening or closing action of the flow switch according to the amplitude of the electrical signal;

[0029] The trigger time refers to the time interval from the flow switch being detected to the action, and this time is recorded as the trigger time.

[0030] The trigger delay time refers to comparing the trigger time with the preset response time based on the current flow fluctuation rate and the operating parameters of the previous flow point, and calculating the trigger delay time. If the trigger delay time exceeds the preset threshold, the data is marked as a response abnormality;

[0031] The recorded response status data is used as input data for the machine learning algorithm to analyze the differences in the response characteristics of the flow switches.

[0032] As a preferred solution of the cooling water system flow switch calibration method of the present invention, wherein: the potential failure trend of the flow switch is identified including:

[0033] The data points marked as response anomalies, trigger time delay data and traffic fluctuation rate are input into the long short-term memory neural network model for training, and a multi-factor prediction model is established in combination with historical data;

[0034] Comparing the real-time collected flow switch response time with the calculated value of the prediction model, and calculating the difference between the predicted value and the actual value;

[0035] Compare real-time data with historical data. When the difference between the real-time response time and the model prediction value exceeds the 95% confidence interval of the model, mark the traffic point as a potential failure point.

[0036] The adjusted operating parameter data is used as error compensation data and input into the multi-factor prediction model, so that the prediction model can adapt to the changes in response characteristics under different operating conditions;

[0037] Multi-level acquisition frequency control is performed based on the actual difference of the potential fault point.

[0038] As a preferred solution of the cooling water system flow switch calibration method of the present invention, wherein: the generating of the flow switch sensitivity, response time and fault prediction report includes generating a response time curve based on the response data marked as abnormal, and the response time curve shows the response time change of the flow switch at different flow points;

[0039] Generate a sensitivity change trend graph, which shows the sensitivity fluctuation of the flow switch at different flow points;

[0040] Compare the response time curve and sensitivity change trend chart with the historical failure mode data. When the failure probability is between 0% and 30%, the flow switch is judged to be fault-free; when the failure probability is between 30% and 50%, it is recommended that the user conduct routine inspections; when the failure probability is between 50% and 70%, it is recommended that the user regularly maintain the flow switch; when the failure probability is between 70% and 80%, it is recommended that the user conduct a comprehensive inspection; when the failure probability is between 80% and 100%, it is recommended that the user immediately replace the flow switch;

[0041] The generated fault prediction report includes response time curve, sensitivity change trend graph and fault probability analysis.

[0042] Another object of the present invention is to provide a cooling water system flow switch calibration system, which can solve the problems of insufficient real-time performance, poor environmental adaptability and delayed fault identification in the existing cooling water system flow switch calibration by constructing a cooling water system flow switch calibration system.

[0043] To solve the above technical problems, the present invention provides the following technical solutions: a cooling water system flow switch calibration system, comprising: an operating condition monitoring module, a flow control module, a data analysis module, an anomaly detection module and a report generation module; the operating condition monitoring module is used to detect the current flow in real time through a flow regulating device, and compare it with a preset standard flow value, and adjust it to a predetermined reference state; the flow control module is used to adjust the cooling water flow according to the operating conditions of the cooling water system and the characteristics of the flow switch, using an adaptive flow regulation algorithm, and perform data collection at multiple flow points; the data analysis module is used to monitor the trigger time and response status of the flow switch at each flow point; the anomaly detection module is used to analyze the historical response data of the flow switch through a machine learning algorithm to identify potential failure trends of the flow switch; the report generation module is used to generate a flow switch sensitivity, response time and failure prediction report based on the collected data and analysis results.

[0044] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the cooling water system flow switch calibration method as described above when executing the computer program.

[0045] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the cooling water system flow switch calibration method as described above.

[0046] Beneficial effects of the present invention: The cooling water system flow switch calibration method provided by the present invention adopts real-time flow regulation and online monitoring. The flow switch does not need to be disassembled during the calibration process, which reduces the downtime of the cooling water system, improves the operating efficiency of the system, and adapts to the needs of real-time calibration in industrial processes.

[0047] Ultrasonic sensors and adaptive adjustment algorithms can accurately measure flow data, and use the difference factor method to determine stability under multiple working conditions, reducing data deviations caused by temperature and pressure fluctuations. Compared with traditional methods, the calibration accuracy is higher and the data is more reliable.

[0048] By building a multi-factor fault prediction model through machine learning algorithms, it is possible to identify potential fault trends based on the historical response data of the flow switch. This method improves the accuracy of fault prediction, effectively avoids sudden system downtime, and extends the service life of the flow switch.

[0049] The generated response time curve, sensitivity trend chart and fault probability analysis report can help users intuitively understand the health status of the flow switch. Compared with traditional calibration methods, users can detect abnormalities earlier and take maintenance measures, reducing the risk of equipment downtime due to failure. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0051] Figure 1 An overall flow chart of a cooling water system flow switch calibration method provided by one embodiment of the present invention.

[0052] Figure 2 The overall structure diagram of a cooling water system flow switch calibration system provided by the second embodiment of the present invention DETAILED DESCRIPTION

[0053] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0054] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0055] Example 1

[0056] Reference Figure 1 , as an embodiment of the present invention, provides a cooling water system flow switch calibration method, comprising:

[0057] S1 detects the current flow rate in real time through the flow regulating device, compares it with the preset standard flow rate value, and adjusts it to the predetermined reference state;

[0058] S2 uses an adaptive flow control algorithm to adjust the cooling water flow according to the operating conditions of the cooling water system and the characteristics of the flow switch, and collects data at multiple flow points;

[0059] S3 monitors the triggering time and response status of the flow switch at each flow point;

[0060] S4 uses machine learning algorithms to analyze historical response data of flow switches and identify potential failure trends of flow switches;

[0061] S5 generates flow switch sensitivity, response time and fault prediction reports based on the collected data and analysis results.

[0062] The adjusting to the predetermined reference state includes using an ultrasonic flow sensor to measure the instantaneous flow velocity in the cooling water pipeline based on an ultrasonic time difference method;

[0063] Compare the measured instantaneous flow rate with the preset standard flow value in real time;

[0064] When the flow deviation exceeds the set allowable range, the flow is gradually adjusted to the predetermined reference state by controlling the valve opening and adjusting the pump speed.

[0065] After each adjustment, the flow feedback data is associated with the operating parameters such as water temperature, pipeline pressure, flow rate, etc. before adjustment, and these operating parameters are referenced during the next adjustment to achieve operating condition adaptation.

[0066] It should be noted that the instantaneous flow rate is measured by the time difference method of the ultrasonic flow sensor, and it is compared with the standard flow value in real time, combined with the automatic adjustment of the valve opening and the speed of the water pump to ensure that the flow can be quickly and accurately adjusted to the predetermined reference state. This method can significantly improve the response speed and accuracy of flow regulation, reduce the error accumulation of manual adjustment, and ensure the stability of the calibration system and the reliability of data acquisition. Through this step, it is possible to quickly adapt to different flow deviations, ensure that the cooling water flow reaches the optimal reference state, provide a stable fluid environment for subsequent flow switch detection, reduce data deviations caused by flow fluctuations, and improve the accuracy of calibration data.

[0067] The regulating cooling water flow comprises collecting operating parameters in real time, wherein the operating parameters include water temperature, pipeline pressure and flow rate;

[0068] The operating condition parameters are used as input parameters of the flow rate change rate and flow rate fluctuation rate, and the current flow rate change rate is calculated in combination with the instantaneous flow rate;

[0069] When the flow rate change rate is lower than the threshold, it is determined that the flow point has reached a stable state and the calculation of the stable time begins.

[0070] It should be noted that the operating parameters collected in real time are used to calculate the flow fluctuation rate and flow change rate to determine whether the current flow point is in a stable state. This design can achieve comprehensive monitoring of the operating conditions of the cooling water system and ensure that the system stability is mastered at any time during the flow adjustment process. By judging whether the flow fluctuation rate is less than the set threshold, the stable state of the flow point can be automatically judged, reducing the interference of manual operation and ensuring the stability and continuity of data collection. In addition, dynamic adjustment based on real-time operating parameters further enhances the ability of the cooling water system to adapt to different operating conditions and provides more stable data input conditions for flow switch detection.

[0071] The calculation of the stabilization time is evaluated by using the difference factor method, comparing the relationship between the operating parameters and the flow fluctuation rate at the same flow point, and confirming whether the flow point is in a stable working condition by judging whether the operating parameters are within the normal range and the flow fluctuation rate is lower than the preset fluctuation threshold;

[0072] The flow points whose stable time is lower than the set threshold are marked as flow points that need to be repeatedly collected.

[0073] It should be noted that the difference factor method is used to calculate the stabilization time to determine the correlation between the flow fluctuation rate and the operating parameters, ensuring that the flow point is in a stable operating condition under the conditions. By marking the flow points with short stabilization time as data points that need to be repeatedly collected, the impact of abnormal fluctuations on data quality is further reduced. This method uses the difference factor method to accurately evaluate the stable state, which not only increases the accuracy of the flow switch calibration process, but also ensures the quality and accuracy of the collected data by automatically screening unstable data points. This design can effectively improve the reliability of cooling water flow calibration and provide a stable foundation for subsequent data analysis and fault detection.

[0074] The monitoring of the triggering time and response state of the flow switch at each flow point includes collecting an electrical signal triggered by the flow switch, wherein the triggering of the electrical signal indicates the switching action of the flow switch when the preset flow value is reached;

[0075] The electrical signal is processed by a low-pass filter to remove high-frequency noise and environmental interference in the signal;

[0076] Comprehensively judging three response states of the flow switch based on the electrical signal amplitude, flow fluctuation rate and operating parameters, the three response states including open or closed state, trigger time and trigger delay time;

[0077] The open or closed state refers to analyzing the opening or closing action of the flow switch according to the amplitude of the electrical signal;

[0078] The trigger time refers to the time interval from the flow switch being detected to the action, and this time is recorded as the trigger time.

[0079] The trigger delay time refers to comparing the trigger time with the preset response time based on the current flow fluctuation rate and the operating parameters of the previous flow point, and calculating the trigger delay time. If the trigger delay time exceeds the preset threshold, the data is marked as a response abnormality;

[0080] The recorded response status data is used as input data for the machine learning algorithm to analyze the differences in the response characteristics of the flow switches.

[0081] It should be noted that through low-pass filter processing and multiple judgments of signal amplitude, volatility and operating parameters, the three response states of the flow switch are clarified, including open or closed state, trigger time and trigger delay time. This method can effectively filter signal noise and environmental interference to ensure the accuracy of the collected signal. The system marks the abnormal response data based on the delay time exceeding the preset threshold, thereby enhancing the sensitivity of fault detection and the validity of the data. This step can timely identify the response characteristic deviation of the flow switch, ensure the real-time nature of fault detection, and at the same time improve the accuracy of the analysis through detailed response state classification, providing high-quality data input for the machine learning model.

[0082] The potential failure trends of the flow switch are identified as follows:

[0083] The data points marked as response anomalies, trigger time delay data and traffic fluctuation rate are input into the long short-term memory neural network model for training, and a multi-factor prediction model is established in combination with historical data;

[0084] Comparing the real-time collected flow switch response time with the calculated value of the prediction model, and calculating the difference between the predicted value and the actual value;

[0085] Compare real-time data with historical data. When the difference between the real-time response time and the model prediction value exceeds the 95% confidence interval of the model, mark the traffic point as a potential failure point.

[0086] The adjusted operating parameter data is used as error compensation data and input into the multi-factor prediction model, so that the prediction model can adapt to the changes in response characteristics under different operating conditions;

[0087] Multi-level acquisition frequency control is performed based on the actual difference of the potential fault point.

[0088] When the difference is within the range of 0% to 5%, the existing acquisition frequency is maintained; when the difference is within the range of 5% to 10%, the acquisition frequency is increased to 5 times per second; when the difference is greater than 10%, the acquisition frequency is increased to 10 times per second, and the detailed acquisition data near the fault point is used to further update the fault model

[0089] It should be noted that the data points marked as abnormal responses, trigger time delay data, and flow fluctuation rate are input into the long short-term memory neural network model (LSTM) for training, which can generate a multi-factor prediction model and improve the accuracy of fault trend identification. After the model is trained, the collected real-time data is compared with the output of the prediction model. When the difference exceeds the set 95% confidence interval, the point is marked as a potential fault point. This design ensures detailed data collection near the fault trend point through multi-level acquisition frequency control, which helps to obtain more detailed characteristic information about the flow switch failure. This step improves the system's ability to identify and handle potential faults of the flow switch early, effectively reduces the probability of system failures, and ensures the long-term stable operation of the cooling water system.

[0090] The generating of the flow switch sensitivity, response time and fault prediction report includes generating a response time curve based on the response data marked as abnormal, the response time curve showing the response time change of the flow switch at different flow points;

[0091] Generate a sensitivity change trend graph, which shows the sensitivity fluctuation of the flow switch at different flow points;

[0092] Compare the response time curve and sensitivity change trend chart with the historical failure mode data. When the failure probability is between 0% and 30%, the flow switch is judged to be fault-free; when the failure probability is between 30% and 50%, it is recommended that the user conduct routine inspections; when the failure probability is between 50% and 70%, it is recommended that the user regularly maintain the flow switch; when the failure probability is between 70% and 80%, it is recommended that the user conduct a comprehensive inspection; when the failure probability is between 80% and 100%, it is recommended that the user immediately replace the flow switch;

[0093] The generated fault prediction report includes response time curve, sensitivity change trend graph and fault probability analysis.

[0094] It should be noted that the response time curve and sensitivity change trend chart are generated based on the response data marked as abnormal, and the fault probability analysis is performed in combination with historical data. The system performs detailed classification processing on the fault probability, providing users with clearer status feedback and corresponding maintenance or replacement suggestions. This design can timely reflect the health status of the flow switch and improve the visualization effect of the flow switch calibration. Through the classification prompts of the fault probability, users can prevent potential problems earlier and reduce unexpected downtime or flow control failure caused by faults. This method provides highly operational diagnostic and maintenance information, greatly enhancing the intelligence and automation level of cooling water system calibration.

[0095] Example 2

[0096] Reference Figure 2, as one embodiment of the present invention, provides a cooling water system flow switch calibration system, comprising:

[0097] Working condition monitoring module 100, flow control module 200, data analysis module 300, abnormality detection module 400 and report generation module 500;

[0098] The working condition monitoring module 100 is used to detect the current flow rate in real time through the flow regulating device, and compare it with the preset standard flow rate value to adjust it to a predetermined reference state;

[0099] The flow control module 200 is used to adjust the cooling water flow rate using an adaptive flow regulation algorithm according to the working conditions of the cooling water system and the characteristics of the flow switch, and to collect data at multiple flow points;

[0100] The data analysis module 300 is used to monitor the triggering time and response status of the flow switch at each flow point;

[0101] The anomaly detection module 400 is used to analyze the historical response data of the flow switch through a machine learning algorithm to identify potential failure trends of the flow switch;

[0102] The report generation module 500 is used to generate a flow switch sensitivity, response time and fault prediction report based on the collected data and analysis results.

[0103] Example 3

[0104] An embodiment of the present invention is different from the first two embodiments in that:

[0105] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0106] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0107] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0108] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0109] Example 4

[0110] As an embodiment of the present invention, a method for calibrating a flow switch in a cooling water system is provided. In order to verify the beneficial effects of the present invention, a scientific demonstration is carried out through simulation experiments.

[0111] Equipped with a standard industrial cooling water system, including water pumps, flow switches, cooling pipes and water tanks.

[0112] The traditional method is to shut down the machine, disassemble the flow switch, and send it to the laboratory for offline calibration, which includes flow regulation and measurement, but without real-time monitoring and fault prediction.

[0113] The method of the present invention uses online real-time verification, ultrasonic flow sensor, adaptive flow regulation algorithm, LSTM fault prediction model, and multi-operating condition data collection and analysis.

[0114] Data acquisition tools include ultrasonic flow sensor, standard flow meter, and low-pass filter.

[0115] After starting the cooling water system, the flow switch was calibrated using the invented method and the traditional method, and the downtime, number of adjustments, and adjustment time were recorded. At different flow points, the operating parameters of water temperature, pressure, and flow were collected, and the data fluctuation amplitude and stability were compared. The flow switch was set to a chronic fault state (increased trigger delay), and the response time of the traditional method and the invented method to potential faults and the accuracy of fault trend recognition were recorded. The experimental results are shown in Table 1.

[0116] Table 1 Comparison of experimental results

[0117]

[0118]

[0119] The method of the present invention realizes real-time monitoring and regulation of the flow switch of the cooling water system through online real-time verification and adaptive flow regulation algorithm. The traditional method requires the flow switch to be disassembled and sent to the laboratory for offline testing, which is a complicated and time-consuming process and causes system downtime. The present invention uses ultrasonic sensors and adaptive regulation technology to enable real-time verification without disassembling the equipment, significantly improving verification efficiency and operational convenience. This technical improvement makes online verification possible and eliminates the need for downtime. Traditional technical methods have failed to foresee or achieve the flexibility and efficiency of such online detection.

[0120] In terms of the accuracy and sensitivity of data collection, the method of the present invention introduces the difference factor method and dynamic monitoring of multiple operating parameters, providing accurate control and judgment basis for the collection of flow and operating parameters. Traditional calibration schemes are limited to static calibration in the laboratory, and cannot make real-time adjustments to the dynamic fluctuations of factors such as water temperature, flow, and pressure in the actual operating environment. The present invention uses the difference factor method to evaluate the stability of flow points in real time. This method ensures the accuracy of flow data and can always maintain stable measurement results under different environmental conditions.

[0121] In terms of fault prediction capability, the present invention adopts a long short-term memory neural network model and establishes a multi-factor fault prediction model by analyzing the historical response data and real-time operating parameters of the flow switch. Traditional methods rely on periodic manual detection and cannot predict the potential fault trends of the flow switch in advance. The introduction of the LSTM model enables the system to accurately capture subtle anomalies of the flow switch in the early stages of the fault, achieving real-time prediction and fault warning.

[0122] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for calibrating a flow switch in a cooling water system, characterized in that: include: The current flow rate is detected in real time by the flow regulating device, and compared with the preset standard flow rate value, and adjusted to the predetermined reference state; According to the working conditions of the cooling water system and the characteristics of the flow switch, an adaptive flow regulation algorithm is used to adjust the cooling water flow, and data is collected at multiple flow points; Monitor the triggering time and response status of the flow switch at each flow point; Analyze the historical response data of the flow switch through machine learning algorithms to identify potential failure trends of the flow switch; Generate flow switch sensitivity, response time and fault prediction reports based on the collected data and analysis results.

2. The cooling water system flow switch calibration method according to claim 1, characterized in that: The adjusting to the predetermined reference state includes using an ultrasonic flow sensor to measure the instantaneous flow velocity in the cooling water pipeline based on an ultrasonic time difference method; Compare the measured instantaneous flow rate with the preset standard flow value in real time; When the flow deviation exceeds the set allowable range, the flow is gradually adjusted to the predetermined reference state by controlling the valve opening and adjusting the pump speed.

3. The cooling water system flow switch calibration method according to claim 2, characterized in that: The regulating cooling water flow comprises collecting operating parameters in real time, wherein the operating parameters include water temperature, pipeline pressure and flow rate; The operating condition parameters are used as input parameters of the flow rate change rate and flow rate fluctuation rate, and the current flow rate change rate is calculated in combination with the instantaneous flow rate; When the flow rate change rate is lower than the threshold, it is determined that the flow point has reached a stable state and the calculation of the stable time begins.

4. The cooling water system flow switch calibration method according to claim 3, characterized in that: The calculation of the stabilization time is evaluated by using the difference factor method, comparing the relationship between the operating parameters and the flow fluctuation rate at the same flow point, and confirming whether the flow point is in a stable working condition by judging whether the operating parameters are within the normal range and the flow fluctuation rate is lower than the preset fluctuation threshold; The flow points whose stable time is lower than the set threshold are marked as flow points that need to be repeatedly collected.

5. The cooling water system flow switch calibration method according to claim 4, characterized in that: The monitoring of the triggering time and response state of the flow switch at each flow point includes collecting an electrical signal triggered by the flow switch, wherein the triggering of the electrical signal indicates the switching action of the flow switch when the preset flow value is reached; The electrical signal is processed by a low-pass filter to remove high-frequency noise and environmental interference in the signal; Comprehensively judging three response states of the flow switch based on the electrical signal amplitude, flow fluctuation rate and operating parameters, the three response states including open or closed state, trigger time and trigger delay time; The open or closed state refers to analyzing the opening or closing action of the flow switch according to the amplitude of the electrical signal; The trigger time refers to the time interval from the flow switch being detected to the action, and this time is recorded as the trigger time. The trigger delay time refers to comparing the trigger time with the preset response time based on the current flow fluctuation rate and the operating parameters of the previous flow point, and calculating the trigger delay time. If the trigger delay time exceeds the preset threshold, the data is marked as a response abnormality; The recorded response status data is used as input data for the machine learning algorithm to analyze the differences in the response characteristics of the flow switches.

6. The cooling water system flow switch calibration method according to claim 5, characterized in that: The potential failure trends of the flow switch are identified as follows: The data points marked as abnormal responses, trigger time delay data, and traffic fluctuation rate are input into the long short-term memory neural network model for training, and a multi-factor prediction model is established in combination with historical data; Comparing the real-time collected flow switch response time with the calculated value of the prediction model, and calculating the difference between the predicted value and the actual value; Compare real-time data with historical data. When the difference between the real-time response time and the model prediction value exceeds the 95% confidence interval of the model, mark the traffic point as a potential failure point. The adjusted operating parameter data is used as error compensation data and input into the multi-factor prediction model, so that the prediction model can adapt to the changes in response characteristics under different operating conditions; Multi-level acquisition frequency control is performed based on the actual difference of the potential fault point.

7. The cooling water system flow switch calibration method according to claim 6, characterized in that: The generating of the flow switch sensitivity, response time and fault prediction report includes generating a response time curve based on the response data marked as abnormal, the response time curve showing the response time change of the flow switch at different flow points; Generate a sensitivity change trend graph, which shows the sensitivity fluctuation of the flow switch at different flow points; Compare the response time curve and sensitivity change trend chart with the historical failure mode data. When the failure probability is between 0% and 30%, it is determined that the flow switch is fault-free. When the probability of failure is within the range of 30% to 50%, it is recommended that users conduct routine inspections; when the probability of failure is within the range of 50% to 70%, it is recommended that users regularly maintain the flow switch; when the probability of failure is within the range of 70% to 80%, it is recommended that users conduct a comprehensive inspection; when the probability of failure is within the range of 80% to 100%, it is recommended that users immediately replace the flow switch; The generated fault prediction report includes response time curve, sensitivity change trend graph and fault probability analysis.

8. A system using the cooling water system flow switch calibration method according to any one of claims 1 to 7, characterized in that: include: A working condition monitoring module (100), a flow control module (200), a data analysis module (300), an anomaly detection module (400), and a report generation module (500); The working condition monitoring module (100) is used to detect the current flow rate in real time through the flow regulating device, and compare it with the preset standard flow rate value to adjust it to a predetermined reference state; The flow control module (200) is used to adjust the cooling water flow rate using an adaptive flow adjustment algorithm according to the working conditions of the cooling water system and the characteristics of the flow switch, and to collect data at multiple flow points; The data analysis module (300) is used to monitor the triggering time and response state of the flow switch at each flow point; The anomaly detection module (400) is used to analyze historical response data of the flow switch through a machine learning algorithm to identify potential failure trends of the flow switch; The report generation module (500) is used to generate a flow switch sensitivity, response time and fault prediction report based on the collected data and analysis results.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the cooling water system flow switch calibration method described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the cooling water system flow switch calibration method described in any one of claims 1 to 7 are implemented.

Images