Liquid pump fault detection method, device and equipment, storage medium and program product

Abstract

The invention discloses a liquid pump fault detection method, device and equipment, a storage medium and a program product, and belongs to the technical field of liquid pump detection. The method comprises the following steps: determining a first deviation value according to a frequency control value and a frequency feedback value of the liquid pump in a preset time period; according to the frequency control value in a preset time period and a prediction model corresponding to the at least one evaluation index, determining a prediction value corresponding to the at least one evaluation index; determining at least one second deviation value according to the predicted value corresponding to the at least one evaluation index and the actual value of the liquid pump; and according to the first deviation value and the at least one second deviation value, the fault level of the liquid pump is determined, and the fault level is used for indicating the fault state of the liquid pump. By means of the mode, operation changes of the liquid pump can be captured in time, response lag after faults occur is reduced, and the fault state of the liquid pump can be accurately detected.

Description

Technical Field

[0001] This application relates to the field of liquid pump testing technology, and in particular to a liquid pump fault detection method, apparatus, equipment, storage medium, and program product. Background Technology

[0002] As a core infrastructure of modern information society, the stable operation of data centers directly affects the continuity of critical businesses such as cloud computing, big data, and financial transactions. Water-cooled refrigeration systems are the main source of energy consumption in data centers. Among them, liquid pumps such as chilled pumps and cooling pumps are the core power equipment of water-cooled refrigeration systems, and their reliability directly affects the overall energy efficiency and operational safety.

[0003] Currently, the following methods are commonly used for liquid pump fault detection: (1) Periodic sampling based on human experience. This method has a delayed response, cannot predict sudden faults, and relies on experience judgment, resulting in a high rate of missed detection and high maintenance costs. The annual maintenance expenditure of large data centers can reach tens of millions of yuan; (2) Predicting pump faults by detecting changes in system flow and pressure. Since changes in system characteristics may be caused by a variety of factors, this method is difficult to distinguish between pump faults and faults in other system components; (3) Using machine learning algorithms to analyze multi-source sensor data for fault prediction. Since there is little data on the control conditions of liquid pumps, the prediction accuracy of the model will be affected when encountering uncontrolled parameters, and the interpretability of the model is poor. Summary of the Invention

[0004] This application provides a liquid pump fault detection method, apparatus, equipment, storage medium, and program product to at least solve the problems of slow response and high false detection rate in related liquid pump fault detection methods.

[0005] To solve the above-mentioned technical problems, this application is implemented as follows: In a first aspect, embodiments of this application provide a liquid pump fault detection method, comprising: determining a first deviation value based on a frequency control value and a frequency feedback value of the liquid pump within a preset time period; determining a predicted value corresponding to the at least one evaluation index based on the frequency control value within the preset time period and a prediction model corresponding to at least one evaluation index; determining at least one second deviation value based on the predicted value corresponding to the at least one evaluation index and the actual value of the liquid pump; and determining a fault level of the liquid pump based on the first deviation value and the at least one second deviation value, wherein the fault level is used to indicate the fault state of the liquid pump.

[0006] Secondly, embodiments of this application provide a liquid pump fault detection device, comprising: a first determining module, configured to determine a first deviation value based on a frequency control value and a frequency feedback value of the liquid pump within a preset time period; an index prediction module, configured to determine a predicted value corresponding to the at least one evaluation index based on the frequency control value within the preset time period and a prediction model corresponding to at least one evaluation index; a second determining module, configured to determine at least one second deviation value based on the predicted value corresponding to the at least one evaluation index and the actual value of the liquid pump; and a fault determining module, configured to determine a fault level of the liquid pump based on the first deviation value and at least one second deviation value, wherein the fault level is used to indicate the fault state of the liquid pump.

[0007] Thirdly, embodiments of this application provide an electronic device, which includes a processor and a memory. The memory stores programs or instructions that can run on the processor, and when the programs or instructions are executed by the processor, they implement the steps of the method described in the first aspect above.

[0008] Fourthly, embodiments of this application provide a computer-readable storage medium on which a program or instructions are stored, which, when executed by a processor, implement the steps of the method described in the first aspect above.

[0009] Fifthly, embodiments of this application provide a computer program product, the computer program product including a computer program stored on a non-transitory computer-readable storage medium, the computer program including program instructions, which, when executed by a computer, cause the computer to perform the steps of the method described in the first aspect above.

[0010] In this embodiment, a first deviation value is determined based on the frequency control value and frequency feedback value of the liquid pump within a preset time period; a predicted value corresponding to at least one evaluation index is determined based on the frequency control value within the preset time period and a prediction model corresponding to at least one evaluation index; at least one second deviation value is determined based on the actual value of the liquid pump corresponding to the predicted value of the at least one evaluation index; and the fault level of the liquid pump is determined based on the first deviation value and at least one second deviation value, which indicates the fault state of the liquid pump. Thus, by comprehensively considering the deviation between the frequency control value and the frequency feedback value, as well as the deviation between the predicted value and the actual value corresponding to other evaluation indices, changes in the operation of the liquid pump can be captured in a timely manner, reducing response lag after a fault occurs, and accurately detecting the fault state of the liquid pump.

[0011] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0012] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0013] Figure 1 A flowchart illustrating a liquid pump fault detection method provided in some embodiments of this application is shown; Figure 2 A flowchart illustrating a liquid pump fault detection method provided in other embodiments of this application is shown; Figure 3 This application provides a schematic diagram of the structure of a liquid pump fault detection device according to some embodiments. Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of this application is shown. Detailed Implementation

[0014] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0015] Cooling systems are the primary source of energy consumption in data centers (accounting for approximately 40%). Among them, chilled pumps and cooling pumps are the core power equipment of water-cooled cooling systems, and their reliability directly affects overall energy efficiency and operational safety. Once the pump set fails (such as bearing wear, impeller cavitation, motor insulation aging, etc.), it may lead to a decrease in cooling efficiency of more than 30%, or even cause system paralysis, resulting in server overheating and downtime.

[0016] Currently, data centers primarily rely on manual inspections and regular maintenance to ensure the operation of their cooling systems. This approach has significant drawbacks: first, it suffers from slow response times and cannot predict sudden failures; second, it relies on experience-based judgment, leading to a high rate of missed detections; and third, maintenance costs are exorbitant, with large data centers incurring tens of millions of yuan in annual operating expenses. As data centers expand and Power Usage Effectiveness (PUE) requirements become increasingly stringent (e.g., the EU requires PUE ≤ 1.3), the traditional model is no longer sufficient. Against this backdrop, developing AI-based fault prediction technologies for chilled and cooling pumps has become an industry necessity. By collecting multi-dimensional sensor data in real time, including pump frequency control values, pump frequency feedback values, instantaneous flow rates, and power, and combining this with machine learning to build fault prediction models, it is of great significance for improving data center energy efficiency, reducing operating costs, and ensuring business continuity.

[0017] Among related methods, flow meters and pressure sensors can be installed to detect the flow and pressure of liquid pumps. By analyzing the changes in the flow-pressure characteristic curve and the trend of efficiency decline, liquid pump failures can be detected. However, since these characteristic changes can be caused by a variety of factors, it is difficult to distinguish between pump failures and failures of other system components. Therefore, this method has low real-time performance and slow response speed. Furthermore, fluctuations in flow and pressure data in data centers are often normal, which can easily lead to false alarms. Alternatively, machine learning algorithms can be used to analyze multi-source sensor data for fault prediction. However, there is limited data on the operating conditions of liquid pump equipment. When encountering uncontrolled parameters, the prediction accuracy of the model will be affected, and the interpretability of the model is poor.

[0018] To address the problems existing in the above-mentioned liquid pump fault detection process, this application provides a liquid pump fault detection method. This method, by comprehensively considering the deviation between the frequency control value and the frequency feedback value, as well as the deviation between the predicted value and the actual value corresponding to other evaluation indicators, can timely capture changes in the operation of the liquid pump, reduce response lag after a fault occurs, and accurately detect the fault state of the liquid pump.

[0019] Figure 1 This document illustrates a flowchart of a liquid pump fault detection method provided in some embodiments of this application. The method can be executed by a terminal device or a server. The terminal device can be a personal computer, a mobile device such as a mobile phone or tablet, or a user-operated terminal device. The server can be a standalone server or a server cluster composed of multiple servers. Furthermore, the server can be a backend server for a specific service or a backend server for a platform or application (e.g., a water cooling system, a data center, an IoT platform, etc.). This embodiment uses a server as the executing entity for illustration. For terminal devices, the following related content can be used, and will not be elaborated further here. As shown in the figure, method 100 may include the following steps: Step 101: Determine the first deviation value based on the frequency control value and frequency feedback value of the liquid pump within a preset time period.

[0020] The preset time period in step 101 can be 0.5 hours, 1 hour, 2 hours, 12 hours, etc., and can be set according to actual needs; the liquid pump in step 101 can be a refrigeration pump or a cooling pump.

[0021] In an exemplary embodiment, the operating data of the chilled pump within a preset time period can be acquired periodically. This operating data includes frequency control values ​​and frequency feedback values. For example, a timed task can be set to acquire the operating data of the chilled pump over the past hour every minute. Optionally, after acquiring the operating data, the chilled pump operating data can be preprocessed. Preprocessing includes filtering out abnormal values ​​such as null values ​​and values ​​exceeding the equipment control range; smoothing the operating data; calculating the moving average value of the operating data; and obtaining the frequency control values ​​and frequency feedback values ​​from the preprocessed operating data. Then, based on the frequency control values ​​and frequency feedback values ​​within the preset time period, a first deviation value is determined. For example, the mean absolute error (MAE) between the frequency feedback values ​​and the frequency control values ​​within the preset time period is determined as the first deviation value.

[0022] The aforementioned preset time period can be set to one or multiple. In the case of multiple preset time periods, the deviation value can be determined separately based on the frequency control value and frequency feedback value within each time period, and the first deviation value can be determined based on the deviation value corresponding to each time period. For example, the data bias for the past hour can be determined based on the frequency control value and frequency feedback value of the liquid pump within the past hour, and the historical bias can be determined based on data from the liquid pump after it left the factory or data from a relatively long period. The sum of the data bias for the past hour and the historical bias is determined as the first deviation value.

[0023] In this way, based on the frequency control value and frequency feedback value of the liquid pump within a preset time period, the first deviation value related to the frequency feedback can be obtained, which is helpful for subsequent fault status detection. Furthermore, by setting multiple preset time periods, the systematic errors of the liquid pump during long-term operation, such as the effects of changes in ambient temperature and equipment friction, can be avoided, which helps to improve the accuracy of fault identification.

[0024] Step 102: Determine the predicted value corresponding to at least one evaluation indicator based on the frequency control value within the preset time period and the prediction model corresponding to at least one evaluation indicator.

[0025] The evaluation index in step 102 above can be a flow rate index or a power index; the prediction model in step 102 above can be a flow rate prediction model or a power prediction model.

[0026] In an exemplary embodiment, taking a chilled water pump as an example, a mechanism model related to the chilled water pump can be constructed, including a chilled water pump flow prediction model and a chilled water pump power prediction model, as follows: M_chilled pump flow prediction model = F (chilled pump frequency control value); M_Refrigeration pump power prediction model = F (refrigeration pump frequency control value); in, This is the prediction function.

[0027] By inputting the frequency control value within a preset time period into the above prediction model, the flow prediction value and power prediction value are obtained.

[0028] Step 103: Determine at least one second deviation value based on the predicted value corresponding to at least one evaluation index and the actual value of the liquid pump.

[0029] Continuing with the above embodiments, the operating data of the chilled pump is obtained, which may further include instantaneous flow rate and actual power. A second deviation value is determined based on the predicted flow rate and instantaneous flow rate obtained in step 102 above. For example, the average absolute error between the predicted flow rate and the instantaneous flow rate within a preset time period is determined as the second deviation value. The second deviation value is also determined based on the predicted power and actual power obtained in step 102 above. For example, the average absolute error between the predicted power and the actual power within a preset time period is determined as the second deviation value.

[0030] It should be noted that, for the case of multiple preset time periods, for each evaluation indicator, the deviation value can be determined based on the predicted value and the actual value in each time period, and the second deviation value can be determined based on the deviation value corresponding to each time period.

[0031] Step 104: Determine the fault level of the liquid pump based on the first deviation value and at least one second deviation value. This fault level is used to indicate the fault condition of the liquid pump.

[0032] The fault level in step 104 can include different states such as normal equipment, equipment failure, or reduced equipment efficiency, which are used to indicate the fault status of the liquid pump.

[0033] In an exemplary embodiment, a fault level is determined based on the first deviation value in step 101 and at least one second deviation value in step 103. For example, when the first deviation value and at least one second deviation value are within a first threshold range corresponding to "equipment normal", the state of the liquid pump is determined to be equipment normal; as another example, when the first deviation value and at least one second deviation value are within a second threshold range corresponding to "equipment fault", the state of the liquid pump is determined to be equipment fault.

[0034] In this way, by comprehensively considering the deviation between the frequency control value and the frequency feedback value, as well as the deviation between the predicted value and the actual value corresponding to other evaluation indicators, the changes in the operation of the liquid pump can be captured in a timely manner, the response lag after a fault occurs can be reduced, and the fault status of the liquid pump can be accurately detected.

[0035] In some embodiments, in step 101 above, determining the first deviation value based on the frequency control value and frequency feedback value of the liquid pump within a preset time period includes: The first deviation value is determined based on the average absolute error between the frequency feedback value and the frequency control value of the liquid pump within a preset time period.

[0036] In an exemplary embodiment, the first deviation value can be determined according to the following formula. : b1 = MAE (chilled pump frequency feedback value, chilled pump frequency control value); In some embodiments, the evaluation indicators mentioned above include traffic flow indicators; in step 103, determining the predicted value corresponding to at least one evaluation indicator based on the frequency control value within a preset time period and the prediction model corresponding to at least one evaluation indicator includes: Obtain the traffic prediction model corresponding to the traffic indicators; by inputting the frequency control value within a preset time period into the traffic prediction model, obtain the predicted value corresponding to the traffic indicators.

[0037] In one exemplary embodiment, a pre-built flow prediction model is obtained, and the flow prediction value is obtained by inputting the chilled pump frequency control value into the flow prediction model. The chilled pump flow prediction model can be constructed in the following manner: 1) Construct the flow function of the chilled pump as follows: Construct the chilled pump flow function, L (chilled pump frequency control value) = a1 * function_x[0] * 50 / 519 + b1; 2) Calculate a1 and b1 by optimizing the least squares method under scipy.optimize using different types of optimization. 3) Calculate the regression model evaluation index R using r2_score and mean_absolute_error from sklearn.metrics. 2 And MAE, the specific calculation formula is as follows: ; ; in, For actual value, For predicted values, Here, N represents the average value, and N represents the sample size.

[0038] Using the training set and the test set, calculate R. 2 The two metrics, Ri and MAE, are used to evaluate the goodness of fit and accuracy of the regression model. 2The accuracy of the model was assessed using MAE, and models that met the required accuracy were deployed. The accuracy of the chilled pump flow model is shown in the table below: Table 1. Accuracy of Refrigeration Pump Flow Model

[0039] In some embodiments, the evaluation indicators mentioned above include power indicators; determining the predicted value corresponding to at least one evaluation indicator based on the frequency control value within a preset time period and the prediction model corresponding to at least one evaluation indicator includes: Obtain the power prediction model corresponding to the power index; by inputting the frequency control value within a preset time period into the power prediction model, obtain the predicted value corresponding to the power index.

[0040] In one exemplary embodiment, a pre-built power prediction model is obtained, and a power prediction value is obtained by inputting the chilled pump frequency control value into the power prediction model. The chilled pump power prediction model can be constructed in the following manner: 1) Construct the power function of the chilled pump as follows: Construct the chilled pump power function W, W(chilled pump frequency control value) = a * chilled pump frequency control value * 50 / 747 + b; 2) Calculate a and b using the least_squares method under scipy.optimize; 3) Calculate R using r2_score and mean_absolute_error from sklearn.metrics. 2 and MAE.

[0041] Using the training set and the test set, calculate R. 2 The two metrics, Ri and MAE, are used to evaluate the goodness of fit and accuracy of the regression model. 2 The accuracy of the model was evaluated using MAE, and models that met the required accuracy were deployed. The accuracy of the chilled pump power model is shown in the table below: Table 2. Accuracy of the chilled pump power model

[0042] In some embodiments, step 104 described above, determining the failure level of the liquid pump based on a first deviation value and at least one second deviation value, includes: Obtain the correspondence between multiple fault levels and deviation ranges; determine the target deviation range to which the first deviation value and at least one second deviation value belong among the multiple deviation ranges; determine the target fault level corresponding to the target deviation range based on the correspondence; determine the target fault level as the fault level of the liquid pump.

[0043] In an exemplary embodiment, each fault level can be assigned a corresponding deviation range. For example, the deviation range for "equipment normal" is "first deviation value b1≤1, two second deviation values ​​b2≤10, b3≤1"; the deviation range for "equipment fault" is "first deviation value b1≥2, two second deviation values ​​b2≥20, b3≥2". The system obtains the correspondence between multiple pre-set fault levels and deviation ranges; determines the target deviation range to which the first deviation value and at least one second deviation value belong, for example, b1≤1, b2≤10, b3≤1; and determines the target fault level corresponding to the target deviation range based on the above correspondence, for example, "equipment normal", and identifies this target fault level "equipment normal" as the fault level of the liquid pump. Taking a refrigeration pump as an example, the fault level classification of the refrigeration pump is shown in the table below: Table 3. Correspondence between failure levels and deviation ranges of refrigeration pumps

[0044] In some embodiments, the preset time period mentioned above includes a first time period and a second time period; the first time period includes the current first time point and a first preset number of time points before the first time point, and the second time period includes a second time point and a second preset number of time points after the second time point, wherein the first time point and the second time point are two different time points.

[0045] The second time point in this step can be the manufacturing time of the liquid pump or a historical time point that is older than the current first time point. The specific time point can be set according to actual needs.

[0046] In one exemplary embodiment, such as Figure 2 As shown, the above-mentioned liquid pump fault detection method may include the following steps: Step 201: Design a timed task to periodically acquire the operating data of the liquid pump within a preset time period. This operating data includes frequency control value, frequency feedback value, instantaneous flow rate value, and actual power value. The task timing and preset time period can be set according to actual needs. Step 202: Calculate the deviation between the frequency control value and the frequency feedback value; for example, the first deviation value b1 is related to the frequency feedback. The frequency feedback of the liquid pump can be collected in real time without prediction. Calculate the historical offset between the refrigeration pump frequency feedback value and the refrigeration pump frequency control value using data from after the liquid pump leaves the factory or data from a relatively long period. Then, pull data up to the nearest decimal point to calculate the offset between the refrigeration pump frequency feedback value and the refrigeration pump frequency control value over the past hour, and calculate the first deviation value: b1 = MAE(frequency feedback value, frequency control value) - historical bias + MAE(frequency feedback value, frequency control value) - data bias of the past hour; Step 203: Based on the frequency control value within the preset time period and the prediction model corresponding to at least one evaluation indicator, determine the predicted value corresponding to at least one evaluation indicator; specifically, step 203 includes: Step 2031: Call the traffic prediction model to predict traffic within a preset time period and obtain the traffic prediction value; Step 2032: Call the power prediction model to predict the power within a preset time period and obtain the predicted power value; Step 204: Determine at least one second deviation value based on the predicted value corresponding to at least one evaluation index and the actual value of the liquid pump; specifically, step 204 includes: Step 2041: Calculate the deviation between the actual flow rate and the predicted flow rate; for example, the second deviation value b2 is related to the flow rate; use data from after the liquid pump leaves the factory or data from a relatively long period of time to train the model, record the MAE that matches the accuracy of the model, and then use the deployed model to predict data close to a decimal point, calculate the MAE, and calculate the second deviation value: b2 = MAE(predicted flow rate, instantaneous flow rate) - historical bias + MAE(predicted flow rate, instantaneous flow rate) - bias of data in the last hour; Step 2042: Calculate the deviation between the actual power value and the predicted power value; for example, the second deviation value b3 is related to the power. Using data from after the liquid pump leaves the factory or data from a relatively long period, train the model, record the MAE (Maximum Effectiveness) that matches the accuracy of the model, and then use the deployed model to predict data up to a near-decimal value, calculating the MAE and the following metrics: b2 = MAE(Power Prediction, Power Actual) - Historical Offset + MAE(Power Prediction, Power Actual) - Data Offset for the Last Hour; Step 205: Based on b1, b2 and b3 obtained in the above steps, output the fault level of the liquid pump.

[0047] This application provides a liquid pump fault detection method. Based on the frequency control value and frequency feedback value of the liquid pump within a preset time period, a first deviation value is determined. Based on the frequency control value within the preset time period and a prediction model corresponding to at least one evaluation index, a predicted value corresponding to at least one evaluation index is determined. Based on the actual value of the liquid pump corresponding to the predicted value corresponding to the at least one evaluation index, at least one second deviation value is determined. Based on the first deviation value and at least one second deviation value, the fault level of the liquid pump is determined, and this fault level is used to indicate the fault state of the liquid pump. In this way, by comprehensively considering the deviation between the frequency control value and the frequency feedback value, as well as the deviation between the predicted value and the actual value corresponding to other evaluation indices, changes in the operation of the liquid pump can be captured in a timely manner, reducing response lag after a fault occurs, and accurately detecting the fault state of the liquid pump.

[0048] Figure 3 This application shows a schematic diagram of the structure of a liquid pump fault detection device according to some embodiments, which can achieve the following: Figure 1 or Figure 2 The liquid pump fault detection device 300, as shown in all or part of the embodiments illustrated, includes: The first determining module 310 is used to determine the first deviation value based on the frequency control value and frequency feedback value of the liquid pump within a preset time period; The indicator prediction module 320 is used to determine the predicted value corresponding to the at least one evaluation indicator based on the frequency control value within the preset time period and the prediction model corresponding to the at least one evaluation indicator. The second determining module 330 is used to determine at least one second deviation value based on the predicted value corresponding to the at least one evaluation index and the actual value of the liquid pump. The fault determination module 340 is used to determine the fault level of the liquid pump based on the first deviation value and at least one second deviation value, the fault level being used to indicate the fault state of the liquid pump.

[0049] In some embodiments, the first determining module 310, when determining the first deviation value based on the frequency control value and frequency feedback value of the liquid pump within a preset time period, is specifically used for: The first deviation value is determined based on the average absolute error between the frequency feedback value and the frequency control value of the liquid pump within a preset time period.

[0050] In some embodiments, the aforementioned evaluation indicators include traffic flow indicators; the indicator prediction module 320, when determining the predicted value corresponding to the at least one evaluation indicator based on the frequency control value within the preset time period and the prediction model corresponding to the at least one evaluation indicator, is specifically used for: Obtain the traffic prediction model corresponding to the traffic metric; By inputting the frequency control value within the preset time period into the traffic prediction model, the predicted value corresponding to the traffic index is obtained.

[0051] In some embodiments, the aforementioned evaluation indicators include power indicators; the indicator prediction module 320, when determining the predicted value corresponding to the at least one evaluation indicator based on the frequency control value within the preset time period and the prediction model corresponding to the at least one evaluation indicator, is specifically used for: Obtain the power prediction model corresponding to the power index; By inputting the frequency control value within the preset time period into the power prediction model, the predicted value corresponding to the power index is obtained.

[0052] In some embodiments, the fault determination module 340, when determining the fault level of the liquid pump based on the first deviation value and at least one second deviation value, is specifically configured to: Obtain the correspondence between multiple fault levels and deviation ranges; Determine the target deviation range to which the first deviation value and at least one second deviation value belong among the plurality of said deviation ranges; Based on the correspondence, determine the target fault level corresponding to the target deviation range; The target fault level is determined as the fault level of the liquid pump.

[0053] In some embodiments, the preset time period mentioned above includes a first time period and a second time period; the first time period includes the current first time point and a first preset number of time points before the first time point, the second time period includes a second time point and a second preset number of time points after the second time point, and the first time point and the second time point are two different time points.

[0054] This application provides a liquid pump fault detection device, including a first determination module, an index prediction module, a second determination module, and a fault determination module. The first determination module determines a first deviation value based on the frequency control value and frequency feedback value of the liquid pump within a preset time period. The index prediction module determines a predicted value corresponding to the at least one evaluation index based on the frequency control value within the preset time period and a prediction model corresponding to at least one evaluation index. The second determination module determines at least one second deviation value based on the predicted value corresponding to the at least one evaluation index and the actual value of the liquid pump. The fault determination module determines the fault level of the liquid pump based on the first deviation value and the at least one second deviation value, whereby the fault level indicates the fault state of the liquid pump. Thus, by comprehensively considering the deviation between the frequency control value and the frequency feedback value, as well as the deviation between the predicted value and the actual value corresponding to other evaluation indices, the device can promptly capture changes in the operation of the liquid pump, reduce response lag after a fault occurs, and accurately detect the fault state of the liquid pump.

[0055] Figure 4 This diagram illustrates the hardware structure of an electronic device implementing the embodiments of this application. Referring to the diagram, at the hardware level, the electronic device 400 includes a processor 410, and optionally includes an internal bus 420, a network interface 430, and a memory. The memory may include main memory 441, such as high-speed random-access memory (RAM), and may also include non-volatile memory 442, such as at least one disk storage device. Of course, the electronic device may also include other hardware required for other services.

[0056] The processor 410, network interface 430, and memory can be interconnected via an internal bus 420. This internal bus 420 can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be categorized as an address bus, data bus, control bus, etc. For ease of illustration, only a single bidirectional arrow is used in this diagram, but this does not imply that there is only one bus or one type of bus.

[0057] The memory stores programs. Specifically, the program may include program code, which includes computer operation instructions. The memory may include main memory 441 and non-volatile memory 442, and provides instructions and data to the processor 410.

[0058] Processor 410 reads the corresponding computer program from non-volatile memory 442 into memory and then runs it, forming a device for locating the target user at the logical level. Processor 410 executes the program stored in memory and specifically performs the following: Figure 1 or Figure 2 The methods disclosed in the embodiments shown achieve the functions and beneficial effects of the methods described in the preceding method embodiments, and will not be repeated here.

[0059] The above is as stated in this application. Figure 1 or Figure 2 The methods disclosed in the illustrated embodiments can be applied to or implemented by processor 410. Processor 410 may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by integrated logic circuits in the hardware or by instructions in software form within processor 410. Processor 410 can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software module can reside in a mature storage medium in the field, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method.

[0060] The computer device can also execute the methods described in the preceding method embodiments and achieve the functions and beneficial effects of the methods described in the preceding method embodiments, which will not be repeated here.

[0061] Of course, in addition to software implementation, the electronic device of this application does not exclude other implementation methods, such as logic devices or a combination of hardware and software, etc. In other words, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0062] This application also proposes a computer-readable storage medium that stores one or more programs, which, when executed by an electronic device including multiple applications, cause the electronic device to perform... Figure 1 or Figure 2 The methods disclosed in the embodiments shown achieve the functions and beneficial effects of the methods described in the preceding method embodiments, and will not be repeated here.

[0063] The computer-readable storage medium mentioned above includes read-only memory (ROM), random access memory (RAM), magnetic disk or optical disk, etc.

[0064] Furthermore, embodiments of this application also provide a computer program product, the computer program product including a computer program stored on a non-transitory computer-readable storage medium, the computer program including program instructions, which, when executed by a computer, implement the following process: Figure 1 or Figure 2 The methods disclosed in the embodiments shown achieve the functions and beneficial effects of the methods described in the preceding method embodiments, and will not be repeated here.

[0065] The embodiments of this application can be applied to various scenarios of electronic device collaboration or interconnection, including: collaboration and interconnection between mobile phones and laptops / tablets; collaboration and interconnection between mobile terminals and smart TVs / monitors; collaboration and interconnection between mobile phones or tablets and in-vehicle entertainment systems; collaboration and interconnection between mobile terminals and smart conferencing systems, etc. This satisfies users' diverse needs in smart home, smart office, and smart travel scenarios.

[0066] In summary, the above description is merely a preferred embodiment of this application and does not limit the scope of protection of this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

[0067] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0068] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can store information accessible to a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0069] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0070] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

Claims

1. A method for detecting faults in a liquid pump, characterized in that, include: The first deviation value is determined based on the frequency control value and frequency feedback value of the liquid pump within a preset time period; Based on the frequency control value within the preset time period and the prediction model corresponding to at least one evaluation indicator, determine the predicted value corresponding to the at least one evaluation indicator; Based on the predicted value corresponding to the at least one evaluation index and the actual value of the liquid pump, at least one second deviation value is determined; The fault level of the liquid pump is determined based on the first deviation value and at least one second deviation value, the fault level indicating the fault state of the liquid pump.

2. The method according to claim 1, characterized in that, The step of determining the first deviation value based on the frequency control value and frequency feedback value of the liquid pump within a preset time period includes: The first deviation value is determined based on the average absolute error between the frequency feedback value and the frequency control value of the liquid pump within a preset time period.

3. The method according to claim 1, characterized in that, The evaluation indicators include traffic flow indicators; determining the predicted value corresponding to the at least one evaluation indicator based on the frequency control value within the preset time period and the prediction model corresponding to the at least one evaluation indicator includes: Obtain the traffic prediction model corresponding to the traffic metric; By inputting the frequency control value within the preset time period into the traffic prediction model, the predicted value corresponding to the traffic index is obtained.

4. The method according to claim 1, characterized in that, The evaluation indicators include power indicators; determining the predicted value corresponding to the at least one evaluation indicator based on the frequency control value within the preset time period and the prediction model corresponding to the at least one evaluation indicator includes: Obtain the power prediction model corresponding to the power index; By inputting the frequency control value within the preset time period into the power prediction model, the predicted value corresponding to the power index is obtained.

5. The method according to claim 1, characterized in that, Determining the fault level of the liquid pump based on the first deviation value and at least one second deviation value includes: Obtain the correspondence between multiple fault levels and deviation ranges; Determine the target deviation range to which the first deviation value and at least one second deviation value belong among the plurality of said deviation ranges; Based on the correspondence, determine the target fault level corresponding to the target deviation range; The target fault level is determined as the fault level of the liquid pump.

6. The method according to any one of claims 1 to 5, characterized in that, The preset time period includes a first time period and a second time period; the first time period includes the current first time point and a first preset number of time points before the first time point, and the second time period includes a second time point and a second preset number of time points after the second time point, wherein the first time point and the second time point are two different time points.

7. A liquid pump fault detection device, characterized in that, include: The first determining module is used to determine the first deviation value based on the frequency control value and frequency feedback value of the liquid pump within a preset time period; The indicator prediction module is used to determine the predicted value corresponding to the at least one evaluation indicator based on the frequency control value within the preset time period and the prediction model corresponding to at least one evaluation indicator. The second determining module is used to determine at least one second deviation value based on the predicted value corresponding to the at least one evaluation index and the actual value of the liquid pump; The fault determination module is used to determine the fault level of the liquid pump based on the first deviation value and at least one second deviation value, the fault level being used to indicate the fault state of the liquid pump.

8. An electronic device, characterized in that, The electronic device includes a processor and a memory, the memory storing programs or instructions that can run on the processor, the programs or instructions being executed by the processor to implement the steps of the method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a program or instructions that, when executed by a processor, implement the steps of the method as described in any one of claims 1 to 6.

10. A computer program product, characterized in that, The computer program product includes a computer program stored on a non-transitory computer-readable storage medium, the computer program including program instructions that, when executed by a computer, cause the computer to perform the steps of the method as described in any one of claims 1 to 6.

Images