Data processing method and system

Abstract

The invention provides a data processing method and system, and belongs to the technical field of data processing.The method comprises the steps that the operating environment variable quantity of target equipment is determined based on operating environment data of the target equipment; determining the operation data variation of the target equipment based on the operation test data of the target equipment; determining a first period based on the operating environment variable quantity of the target equipment and the operating data variable quantity of the target equipment; and updating the evaluation model based on the first period, and evaluating the operation state of the target equipment based on the updated evaluation model. According to the data processing method and system provided by the invention, accurate evaluation of the equipment operation state is realized.

Description

Technical Field

[0001] The present disclosure belongs to the field of data processing technology, and more specifically, to a data processing method and system. Background Art

[0002] With the continuous development of science and technology, various equipment are widely used in different fields, such as infrastructure, industrial manufacturing, energy production, etc., and the testing of equipment performance is also very important. During the trial operation, acceptance and formal use of the equipment, it is necessary to measure the operating parameters of the equipment under different conditions, such as flow, speed, temperature, pressure, etc., to determine whether it can meet the performance indicators required by the design. For example, for a water pump station unit, its flow, head and efficiency during operation can be monitored during the performance test to determine whether it can meet the design performance index requirements. For another example, for a water disinfection device, by monitoring parameters such as flow, pressure, and dosage, the stability and accuracy of the equipment under different operating conditions can be confirmed.

[0003] By training the status evaluation model, the health status of the equipment can be automatically predicted based on the equipment's operating data, thereby determining whether the performance indicators required by the design can be achieved. However, since the equipment operating data is constantly changing, the evaluation model with fixed parameters may not be able to adapt to the new data, making it impossible to accurately evaluate the operating status. Summary of the invention

[0004] The purpose of the present disclosure is to provide a data processing method and system to achieve accurate evaluation of the operating status of a device.

[0005] A first aspect of an embodiment of the present disclosure provides a data processing method, including: Determine an amount of change in the operating environment of the target device based on the operating environment data of the target device; Determine the change amount of the operation data of the target device based on the operation test data of the target device; Determining a first period based on a change in the operating environment of the target device and a change in the operating data of the target device; The evaluation model is updated based on the first cycle, and the operating status of the target device is evaluated based on the updated evaluation model.

[0006] A second aspect of the embodiments of the present disclosure provides a data processing system, including: A first calculation module, used to determine the change amount of the operating environment of the target device based on the operating environment data of the target device; A second calculation module, used to determine the change amount of the operation data of the target device based on the operation test data of the target device; A third calculation module determines a first period based on a change in the operating environment of the target device and a change in the operating data of the target device; The model updating module is used to update the evaluation model based on the first cycle, and evaluate the operating status of the target device based on the updated evaluation model.

[0007] According to a third aspect of an embodiment of the present disclosure, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of the above-mentioned data processing method when executing the computer program.

[0008] According to a fourth aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned data processing method are implemented.

[0009] The data processing method and system provided by the embodiments of the present disclosure have the following beneficial effects: The disclosed embodiment takes into account that changes in the target device's operating test data come not only from changes in its own performance, but also from changes in the operating environment. Therefore, the update cycle (i.e., the first cycle) of the evaluation model is determined based on the operating environment of the target device and the amount of change in the operating data. When the operating environment and operating data of the target device change relatively small, there is no need to frequently update the parameters of the evaluation model, and a larger update cycle can be set. Conversely, when the operating environment and operating data of the target device change relatively large, the parameters of the evaluation model need to be updated in a timely manner, and a smaller update cycle can be set.

[0010] The embodiment of the present disclosure determines the update cycle of the evaluation model based on the operating environment of the target device and the change in the operating data, and reduces the number of model updates as much as possible while ensuring the accuracy of the evaluation model, thereby reducing the amount of calculation. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0012] Figure 1 A flowchart of a data processing method provided by an embodiment of the present disclosure; Figure 2 A structural block diagram of a data processing system provided by an embodiment of the present disclosure; Figure 3A schematic block diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0013] In the following description, specific details such as specific system structures and technologies are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present disclosure. However, it should be clear to those skilled in the art that the present disclosure may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obstructing the description of the present disclosure with unnecessary details.

[0014] In order to make the purpose, technical solutions and advantages of the present disclosure more clear, specific embodiments will be described below in conjunction with the accompanying drawings.

[0015] Please refer to Figure 1 , Figure 1 A flowchart of a data processing method provided by an embodiment of the present disclosure, the method comprising: S101: Determine a change amount of an operating environment of a target device based on operating environment data of the target device.

[0016] In this embodiment, the target equipment may include various equipment in the fields of infrastructure, industrial manufacturing, energy production, etc., such as pump groups in water pumping stations, water treatment equipment in water pumping stations (including disinfection equipment, mixing equipment), working robots, photovoltaic equipment, wind power generation equipment, etc.

[0017] The target device's operating environment data is the target device's environment data, including temperature, humidity, electromagnetic interference and other external environmental factors. Changes in these data will affect the target device's operating status. By counting the operating environment data within a set time, the change in the operating environment data can be obtained.

[0018] Taking the target device as a pump unit in a water pump station as an example, the operating environment data of the target device may include air temperature, water level, and water quality. Among them, the temperature difference in different seasons will affect the operating temperature of the equipment in the pump station. For example, in the high temperature in summer, the pump unit and motor may face the risk of overheating, while in the low temperature in winter, some components may experience performance degradation or damage due to the low temperature. For water pump stations that rely on natural water sources, changes in the water level of the water source will also affect the operating status of the pump unit. For example, in the rainy season, the water level may rise, and in the dry season, the water level may drop, which will affect the suction conditions and working efficiency of the pump. In addition, in the rainy season, the water may contain more silt and impurities, which will affect the operation of the pump unit.

[0019] Taking the target device as a water disinfection device as an example, the operating environment data of the target device may include water temperature, water hardness, pH value, impurity content in water (including suspended matter, organic matter), etc. For example, different disinfection methods have different adaptability ranges to water temperature. For example, ultraviolet disinfection works better within a certain water temperature range, while too high or too low water temperature may reduce its efficiency. For another example, water with high hardness may form scale on the surface of the equipment, affecting the heat transfer, mass transfer and other performance of the equipment.

[0020] S102: Determine the change amount of the operation data of the target device based on the operation test data of the target device.

[0021] In this embodiment, the operation test data of the target device is the performance test data of the target device itself, including power, rotation speed, vibration, noise, etc. By counting the operation test data within a set time, the change amount of the operation data can be obtained.

[0022] Taking the target equipment as a water pump station pump group as an example, the operation test data of the target equipment may include performance parameters such as flow, efficiency, and head, temperature data such as pump body temperature and bearing temperature, frequency data such as vibration amplitude and vibration frequency, electrical parameters such as current and voltage, and noise data such as noise level and noise frequency.

[0023] Taking the target device as a water disinfection device as an example, the operation test data of the target device may include disinfection dosage, ultraviolet intensity, energy consumption, etc.

[0024] S103: Determine a first period based on the change amount of the operating environment of the target device and the change amount of the operating data of the target device.

[0025] In this embodiment, the update cycle (i.e., the first cycle) of the evaluation model can be determined based on the change in the operating environment and operating data of the target device to achieve dynamic adjustment of the update cycle. When the change in the operating environment and operating data of the target device is small, there is no need to frequently update the parameters of the evaluation model, and a larger update cycle can be set. On the contrary, when the change in the operating environment and operating data of the target device is large, the parameters of the evaluation model need to be updated in a timely manner, and a smaller update cycle can be set.

[0026] S104: updating the evaluation model based on the first cycle, and evaluating the operating status of the target device based on the updated evaluation model.

[0027] In this embodiment, when the first cycle arrives, the evaluation model can be retrained based on the most recent historical running test data, so as to update the evaluation model parameters to adapt to the changes in the new running state.

[0028] Specifically, the evaluation model can be obtained based on a machine learning or deep learning model. By inputting the most recent historical operating test data and the corresponding health status data (such as healthy, warning, dangerous, etc.) into the evaluation model for retraining, an updated model can be obtained. Before the most recent historical operating test data is input into the evaluation model, feature extraction can be performed on the historical operating test data, such as calculating the statistical features of the data (including mean, variance, standard deviation, etc.), or extracting specific feature parameters, such as the peak value and frequency component of vibration. Feature extraction can remove irrelevant or unimportant features, reduce the amount of calculation, and improve the running speed of the model.

[0029] From the above, it can be concluded that the embodiment of the present disclosure takes into account that changes in the target device's operating test data come not only from changes in its own performance, but also from changes in the operating environment. Therefore, the update cycle (i.e., the first cycle) of the evaluation model is determined based on the operating environment of the target device and the amount of change in the operating data. When the operating environment and operating data of the target device change in a small amount, there is no need to frequently update the parameters of the evaluation model, and a larger update cycle can be set. Conversely, when the operating environment and operating data of the target device change in a large amount, the parameters of the evaluation model need to be updated in a timely manner, and a smaller update cycle can be set.

[0030] The embodiment of the present disclosure determines the update cycle of the evaluation model based on the operating environment of the target device and the change in the operating data, and minimizes the number of model updates while ensuring the accuracy of the evaluation model, thereby reducing the amount of calculation.

[0031] In one embodiment of the present disclosure, determining the first period based on the change amount of the operating environment of the target device and the change amount of the operating data of the target device includes: A first proportional parameter is determined based on the amount of change in the operating environment.

[0032] A second proportional parameter is determined based on the amount of change in the operating data.

[0033] The set reference period is adjusted based on the first proportional parameter and the second proportional parameter to obtain a first period.

[0034] In this embodiment, a specific implementation method for determining the first period based on the change in the operating environment of the target device and the change in the operating data of the target device is provided. First, the change in the operating environment of the target device can be quantitatively evaluated in a variety of ways, such as calculating statistical indicators such as the standard deviation, variance or change rate of the operating environment data over a period of time, which can reflect the degree of fluctuation and stability of the operating environment data. Then, a first mapping relationship between the change in the operating environment and the first proportional parameter is established. The larger the change in the operating environment, the smaller the value of the first proportional parameter. Based on the above first mapping relationship and the change in the operating environment, the first proportional parameter corresponding to the change in the operating environment can be obtained.

[0035] Similarly, the change in the operating data of the target device can be quantitatively evaluated in a variety of ways, such as calculating statistical indicators such as the standard deviation, variance or change rate of the operating test data over a period of time, which can reflect the degree of fluctuation and stability of the operating test data. Then, a second mapping relationship between the change in the operating data and the second proportional parameter is established. The larger the change in the operating data, the smaller the value of the second proportional parameter. Based on the above second mapping relationship and the change in the operating data, the second proportional parameter corresponding to the change in the operating data can be obtained.

[0036] On the basis of obtaining the first proportional parameter and the second proportional parameter, the first proportional parameter and the second proportional parameter may be weighted and summed to obtain a fourth proportional parameter, and then the fourth proportional parameter may be multiplied by a set reference period to obtain the first period. The set reference period is a preset constant, and those skilled in the art may set a specific value of the reference period according to actual needs, which is not limited here.

[0037] It can be concluded from the above that this embodiment quantifies the change in the operating environment and the change in the operating data, and realizes dynamic adjustment of the first cycle according to the quantification result, which is beneficial to improving the accuracy and timeliness of the evaluation of the operating status of the target device.

[0038] In one embodiment of the present disclosure, the operating environment change amount includes change rates of multiple operating environment parameters, and determining the first proportional parameter based on the operating environment change amount includes: Determine the proportion of operating environment parameters whose corresponding change rates exceed a first threshold among the multiple operating environment parameters to obtain a first proportion. A first proportion parameter is determined based on the first proportion; the first proportion and the first proportion parameter are negatively correlated.

[0039] In this embodiment, a specific implementation method for determining the first proportional parameter based on the change in the operating environment is provided. First, the change rates of multiple operating environment parameters (such as temperature, humidity, electromagnetic interference, etc.) can be calculated respectively, and the proportion of operating environment parameters whose corresponding change rates exceed the first threshold value among the multiple operating environment parameters can be counted to obtain the first proportion. Then, the first proportional parameter is determined based on the size of the first proportion, wherein the larger the first proportion, the larger the change in the operating environment parameter, and the smaller the first proportional parameter. The change rate of any operating environment parameter is used to indicate the degree of change between the measured value of the operating environment parameter and the reference value, and the calculation process may include: first, calculating the difference between the measured value of any operating environment parameter and the corresponding reference value, and then calculating the ratio of the difference to the reference value to obtain the change rate of any operating environment parameter.

[0040] Taking the pump group of a water pump station as an example, the operating environment parameters of the pump group include air temperature, water level and water quality, among which the air temperature change rate is used to indicate the degree of change of the ambient air temperature, and its calculation process may include: calculating the first difference between the actual air temperature value (which may be the average air temperature value over a period of time) and the air temperature reference value, and then calculating the first ratio of the first difference to the air temperature reference value, and determining the first ratio as the air temperature change rate. The water level change rate is used to indicate the degree of change of the water level, and its calculation process may include: calculating the second difference between the actual water level value (which may be the average water level value over a period of time) and the water level reference value, and then calculating the second ratio between the second difference and the water level reference value, and determining the second ratio as the water level change rate. The water quality change rate is used to indicate the degree of change of the water quality, and its calculation process may include: calculating the third difference between the actual water quality parameter value (specifically turbidity) and the water quality reference value, and then calculating the third ratio between the third difference and the water quality reference value, and determining the third ratio as the water quality change rate. Among them, the air temperature reference value, water level reference value and water quality reference value are all preset constants. Under normal circumstances, the pump group operates in the operating environment determined by the above reference values.

[0041] On this basis, the number of data exceeding the first threshold value among the three data of temperature change rate, water level change rate and water quality change rate can be calculated, and then the ratio of the number of data exceeding the first threshold value to the total number of data can be calculated to obtain the first proportion. For example, among the three data of temperature change rate, water level change rate and water quality change rate, if the temperature change rate and water level change rate are both greater than the first threshold value, the first proportion is 2 / 3. The larger the first proportion, the greater the environmental change.

[0042] On the basis of obtaining the first proportion, the first proportion parameter may be determined based on the negative correlation between the first proportion and the first proportion parameter. For example, the first proportion parameter may be calculated using the following formula: ;in, represents the first scale parameter, Indicates the first proportion.

[0043] Taking the target equipment as water disinfection equipment as an example, the operating environment parameters of the water disinfection equipment include water temperature, water hardness, pH value, impurity content in water, etc. The same method can be used to calculate the water temperature change rate, water hardness change rate, pH value change rate and impurity content change rate in water (including suspended matter change rate and organic matter change rate) respectively, and then count the number of data exceeding the first threshold among the five data of water temperature change rate, water hardness change rate, pH value change rate, suspended matter change rate and organic matter change rate, and then obtain the first proportion, and then calculate the first proportion parameter based on the first proportion.

[0044] It can be concluded from the above that this embodiment quantifies the first proportional parameter based on comprehensive consideration of the operating environment changes in multiple dimensions, and can more accurately capture the potential impact of environmental changes on the operating status of the device.

[0045] In one embodiment of the present disclosure, the operation data change amount includes the change rates of multiple operation parameters, and determining the second proportional parameter based on the operation data change amount includes: Determine the proportion of operating parameters whose corresponding change rates exceed the second threshold among the multiple operating parameters to obtain a second proportion. A second proportion parameter is determined based on the second proportion; the second proportion and the second proportion parameter are negatively correlated.

[0046] In this embodiment, a specific implementation method for determining the second proportional parameter based on the change in operating data is provided. First, the change rates of multiple operating parameters (such as power, speed, vibration, noise, etc.) can be calculated respectively, and the proportion of operating parameters whose corresponding change rates exceed the second threshold value among the multiple operating parameters is counted to obtain the second proportion. Then, the second proportional parameter is determined based on the size of the second proportion, wherein the larger the second proportion, the larger the change in the operating parameter, and the smaller the second proportional parameter. The change rate of any operating parameter is used to indicate the degree of change between the measured value of the operating parameter and the reference value, and the calculation process may include: first, calculating the difference between the measured value of any operating parameter and the corresponding reference value, and then calculating the ratio of the difference to the reference value to obtain the change rate of any operating parameter.

[0047] Taking the pump group of a water pump station as an example, the operating parameters of the pump group include performance parameters, temperature, vibration, electrical parameters and noise, etc. Among them, the performance parameter change rate is used to indicate the degree of change of the performance parameter. The performance parameter change rate can include the flow change rate, efficiency change rate and head change rate. Taking the flow change rate as an example, its calculation process can include: calculating the fourth difference between the measured flow value (which can be the average flow value over a period of time) and the flow reference value, and then calculating the fourth ratio of the fourth difference to the flow reference value, and determining the fourth ratio as the flow change rate. The temperature change rate is used to indicate the degree of change of the temperature. The calculation process can include: calculating the fifth difference between the measured temperature value (which can be the average temperature value over a period of time) and the temperature reference value, and then calculating the fifth ratio between the fifth difference and the temperature reference value, and determining the fifth ratio as the temperature change rate. The vibration change rate is used to indicate the degree of change of the vibration. The calculation process can include: calculating the sixth difference between the measured vibration amplitude value (which can be the average vibration amplitude value over a period of time) and the vibration reference value, and then calculating the sixth ratio between the sixth difference and the vibration reference value, and determining the sixth ratio as the vibration change rate. The electrical parameter change rate is used to indicate the degree of change of the electrical parameters. The electrical parameter change rate can include the current parameter change rate and the voltage parameter change rate. Taking the current parameter change rate as an example, its calculation process can include: calculating the seventh difference between the actual current value (which can be the average current value over a period of time) and the current reference value, and then calculating the seventh ratio of the seventh difference to the current reference value, and determining the seventh ratio as the current change rate. The noise change rate is used to indicate the degree of change of the noise. Its calculation process can include: calculating the eighth difference between the actual noise amplitude value (which can be the average noise amplitude value over a period of time) and the noise reference value, and then calculating the eighth ratio of the eighth difference to the noise reference value, and determining the eighth ratio as the noise change rate. Among them, the flow reference value, temperature reference value, vibration amplitude reference value, current reference value and noise reference value are all preset constants, which can be obtained by statistically averaging the running test data of the pump group during normal operation.

[0048] On this basis, the number of data exceeding the second threshold value among the eight data including performance parameter change rate (including flow change rate, efficiency change rate and head change rate), temperature change rate, vibration change rate, electrical parameter change rate (including current change rate and voltage change rate) and noise change rate can be calculated, and then the ratio of the number of data exceeding the second threshold value to the total number of data can be calculated to obtain the second proportion. For example, among the above eight data, if the current change rate and voltage change rate are both greater than the second threshold value, the second proportion is 2 / 8. The larger the first proportion, the greater the change in the operating data.

[0049] On the basis of obtaining the second proportion, the second proportion parameter may be determined based on the negative correlation between the second proportion and the second proportion parameter. For example, the second proportion parameter may be calculated using the following formula: ;in, represents the second scale parameter, Indicates the second proportion.

[0050] Taking the target device as a water disinfection device as an example, the operating parameters of the water disinfection device include disinfection dose, ultraviolet intensity, energy consumption, etc. The same method can be used to calculate the disinfection dose change rate, ultraviolet intensity change rate and energy consumption change rate respectively, and then count the number of data exceeding the second threshold value among the three data of disinfection dose change rate, ultraviolet intensity change rate and energy consumption change rate, and then obtain the second proportion, and then calculate the second proportion parameter based on the second proportion. Among them, the first threshold and the second threshold are both preset constants, and those skilled in the art can flexibly set them according to actual needs.

[0051] It can be concluded from the above that this embodiment quantifies the second proportional parameter based on comprehensive consideration of the operating data changes in multiple dimensions, and can more accurately capture the impact of the operating data on the operating status of the device.

[0052] In one embodiment of the present disclosure, the data processing method further includes: In response to the first time interval being less than the first duration, the first period is adjusted based on a set third proportional parameter; the first time interval is the time interval between the current time point and the time point when the fault occurs.

[0053] In this embodiment, considering that after each failure occurs, the operating state of the target device may be unstable and the failure may further deteriorate, it is necessary to shorten the update cycle of the evaluation model to accurately evaluate the operating state of the target device.

[0054] Specifically, the first time interval between the fault occurrence time point and the current time point can be calculated. If the first time interval is shorter (less than the first duration), the first period is multiplied by a set third proportional parameter (for example, 0.8) to further reduce the first period. The first duration is a preset constant, and those skilled in the art can set the specific value of the first duration according to actual needs.

[0055] It can be concluded from the above that this embodiment shortens the update cycle of the evaluation model within the first period after the fault occurs, which is conducive to timely discovering whether the fault is effectively controlled or whether new fault signs appear.

[0056] In one embodiment of the present disclosure, the evaluation model is a support vector machine model, and the evaluation model is updated based on the first cycle, including: An update time of the evaluation model is determined based on the first cycle.

[0057] The evaluation model is updated at the update time.

[0058] The update process includes: A first evaluation value is determined based on the operating environment data of the target device; the first evaluation value is used to indicate the degree of degradation of the operating environment data.

[0059] A second evaluation value is determined based on the operation test data of the target device; the second evaluation value is used to indicate the degree of degradation of the operation test data.

[0060] In response to the first evaluation value being greater than the third threshold, or the second evaluation value being greater than the fourth threshold, the gamma parameter of the support vector machine model is increased by the first step length to obtain the first gamma parameter, the first gamma parameter is determined as the initial parameter of the support vector machine model, and the support vector machine model is retrained.

[0061] In this embodiment, a support vector machine model is used to evaluate the state of the target device. It classifies or regresses data by finding an optimal hyperplane. In the state evaluation of the target device, different operating test data can be classified as different categories to achieve regression prediction.

[0062] Exemplarily, the first evaluation value may be calculated by comparing the difference between the operating environment data of the target device and the reference value of the operating environment data, thereby quantifying the degree of deterioration of the operating environment data. Specifically, the difference between the measured value of each operating environment parameter and the corresponding reference value may be calculated to obtain the deterioration degree value corresponding to each operating environment parameter, and then the first evaluation value may be obtained by weighted average of the deterioration degree values ​​corresponding to each operating environment parameter.

[0063] Taking the target equipment as a pump station pump group as an example, the deterioration degree of the air temperature can be calculated first. The specific process may include: when the measured air temperature value is greater than the upper limit of the air temperature, the deterioration degree of the air temperature can be quantified by calculating the difference between the measured air temperature value and the upper limit of the air temperature; when the measured air temperature value is less than the lower limit of the air temperature, the deterioration degree of the air temperature can be quantified by calculating the difference between the measured air temperature value and the lower limit of the air temperature. Specifically, the deterioration degree of the air temperature can be calculated using the following formula:

[0064] in, Indicates the degree of deterioration of the temperature. represents the measured value of temperature, Indicates the upper limit of temperature. Indicates the lower limit of temperature.

[0065] The same method can be used to calculate the deterioration degree values ​​of other operating environment parameters (such as water level and water quality), and the first evaluation value can be obtained by weighted summing the deterioration degree values ​​of various operating environment parameters.

[0066] Taking the target equipment as water disinfection equipment as an example, the deterioration degree values ​​of water temperature, pH value, suspended solids and organic matter can be calculated respectively, and then the deterioration degree values ​​of the above operating environment parameters corresponding to the water disinfection equipment are weightedly summed to obtain the first evaluation value of the water disinfection equipment.

[0067] Similarly, the second evaluation value can be calculated by comparing the difference between the operation test data of the target device and the reference value of the operation test data, so as to quantify the degree of deterioration of the operation test data. Specifically, the difference between the data of each operation parameter and the corresponding reference value can be calculated respectively to obtain the deterioration degree value corresponding to each operation parameter, and then the deterioration degree value corresponding to each operation parameter is weighted averaged to obtain the second evaluation value.

[0068] Taking the target device as a pump station pump group as an example, the flow rate deterioration value can be calculated first. The specific process may include: when the measured flow rate value is greater than the upper limit of the flow rate, the flow rate deterioration value can be quantified by calculating the difference between the measured flow rate value and the upper limit of the flow rate; when the measured flow rate value is less than the lower limit of the flow rate, the flow rate deterioration value can be quantified by calculating the difference between the measured flow rate value and the lower limit of the flow rate. Specifically, the flow rate deterioration value can be calculated using the following formula:

[0069] in, Indicates the deterioration degree of the flow rate. represents the measured value of temperature, Indicates the upper limit of temperature. Indicates the lower limit of temperature.

[0070] The same method can be used to calculate the deterioration degree values ​​of other operating test data (such as efficiency, head, and electrical parameters), and the second evaluation value can be obtained by weighted summing up the deterioration degree values ​​of each operating test data.

[0071] Taking the target equipment as water disinfection equipment as an example, the deterioration degree values ​​of the disinfection dose, the deterioration degree values ​​of the ultraviolet intensity, and the deterioration degree values ​​of the energy consumption can be calculated respectively, and then the deterioration degree values ​​of the above operating parameters corresponding to the water disinfection equipment can be weightedly summed to obtain the second evaluation value of the water disinfection equipment.

[0072] If the first evaluation value is greater than the third threshold, or the second evaluation value is greater than the fourth threshold, it indicates that the operating environment data or operating test data of the target device has deteriorated seriously, and the probability of failure of the target device has increased. At this time, the first step length can be increased on the basis of the original gamma parameter value (that is, an adjustment amount can be added), the gamma parameter can be increased, and the increased first gamma parameter can be used as the initial parameter of the support vector machine model to retrain the support vector machine model so that the model pays more attention to local data points, thereby making it easier to identify local faults. In addition, multiple gamma parameters can also be preset. When the first evaluation value is greater than the third threshold, or the second evaluation value is greater than the fourth threshold, a larger gamma parameter is selected for retraining the support vector machine model. Among them, the third threshold and the fourth threshold are both preset constants, and those skilled in the art can set them according to actual needs.

[0073] It can be concluded from the above that this embodiment can obtain the degree of degradation of the operating environment data or the operating test data based on the preliminary analysis of the operating environment data and the operating test data of the target device, and then set the corresponding gamma parameter for retraining the support vector machine model, which is beneficial to improving the training accuracy of the model.

[0074] In one embodiment of the present disclosure, the data processing method further includes: In the process of updating the evaluation model, if the number of fault samples is less than the set number, the penalty parameter C in the support vector machine model is increased.

[0075] In this embodiment, when the number of fault samples is too small (less than the set number), the model may not be able to fully learn the diversity and complexity of the fault mode, resulting in insufficient fault detection capability. To solve the above problem, the penalty parameter C can be increased to make the model pay more attention to the fault samples and improve the recognition capability of the fault state. Exemplarily, the second step size (that is, an adjustment amount) can be added on the basis of the original penalty parameter C, thereby increasing the penalty parameter C.

[0076] It can be concluded from the above that, in this embodiment, when the number of fault samples is too small, by increasing the penalty for errors, the model will try harder to fit the features of the fault samples, thereby compensating for the problem of insufficient number of fault samples to a certain extent.

[0077] In one embodiment of the present disclosure, updating the evaluation model based on the first cycle includes: In response to the first period being greater than a second time period, the evaluation model is updated based on the running test data within the second time period before the update time.

[0078] In this embodiment, if the first cycle is longer (greater than the second time period), it indicates that the operating environment data or operating test data of the target device is relatively constant. At this time, there is no need for too much operating test data to update the evaluation model. Only the most recent part of the data (that is, the operating test data within the second time period before the update time) is selected for updating the evaluation model, so that the model can better reflect the current status and future trends of the device, while reducing the amount of calculation.

[0079] Corresponding to the data processing method of the above embodiment, Figure 2 This is a structural block diagram of a data processing system provided by an embodiment of the present disclosure. For ease of explanation, only the parts related to the embodiment of the present disclosure are shown. Figure 2 The data processing system 20 includes: a first calculation module 21, a second calculation module 22, a third calculation module 23 and a model updating module 24. The first calculation module 21 is used to determine the change amount of the operating environment of the target device based on the operating environment data of the target device.

[0080] The second calculation module 22 is used to determine the change amount of the operation data of the target device based on the operation test data of the target device.

[0081] The third calculation module 23 determines a first period based on a change amount of the operating environment of the target device and a change amount of the operating data of the target device.

[0082] The model updating module 24 is used to update the evaluation model based on the first cycle, and evaluate the operating status of the target device based on the updated evaluation model.

[0083] In one embodiment of the present disclosure, the third calculation module 23 is specifically used to: A first proportional parameter is determined based on the amount of change in the operating environment.

[0084] A second proportional parameter is determined based on the amount of change in the operating data.

[0085] The set reference period is adjusted based on the first proportional parameter and the second proportional parameter to obtain a first period.

[0086] In one embodiment of the present disclosure, the operating environment change amount includes the change rate of multiple operating environment parameters, and the third calculation module 23 is specifically further used to: Determine the proportion of operating environment parameters whose corresponding change rates exceed a first threshold among the multiple operating environment parameters to obtain a first proportion. A first proportion parameter is determined based on the first proportion; the first proportion and the first proportion parameter are negatively correlated.

[0087] In one embodiment of the present disclosure, the operation data variation includes the variation rates of multiple operation parameters, and the third calculation module 23 is further configured to: Determine the proportion of operating parameters whose corresponding change rates exceed the second threshold among the multiple operating parameters to obtain a second proportion. A second proportion parameter is determined based on the second proportion; the second proportion and the second proportion parameter are negatively correlated.

[0088] In one embodiment of the present disclosure, the third calculation module 23 is specifically used to: In response to the first time interval being less than the first duration, the first period is adjusted based on a set third proportional parameter; the first time interval is the time interval between the current time point and the time point when the fault occurs.

[0089] In one embodiment of the present disclosure, the model updating module 24 is specifically used to: An update time of the evaluation model is determined based on the first cycle.

[0090] The evaluation model is updated at the update time.

[0091] The update process includes: A first evaluation value is determined based on the operating environment data of the target device; the first evaluation value is used to indicate the degree of degradation of the operating environment data.

[0092] A second evaluation value is determined based on the operation test data of the target device; the second evaluation value is used to indicate the degree of degradation of the operation test data.

[0093] In response to the first evaluation value being greater than the third threshold, or the second evaluation value being greater than the fourth threshold, the gamma parameter of the support vector machine model is increased by the first step length to obtain the first gamma parameter, the first gamma parameter is determined as the initial parameter of the support vector machine model, and the support vector machine model is retrained.

[0094] In one embodiment of the present disclosure, the model updating module 24 is further configured to: In response to the first period being greater than a second time period, the evaluation model is updated based on the running test data within the second time period before the update time.

[0095] See also Figure 3 , Figure 3 A schematic block diagram of an electronic device provided by an embodiment of the present disclosure. Figure 3The electronic device 300 in the embodiment shown may include: one or more processors 301, one or more input devices 302, one or more output devices 303 and one or more memories 304. The processors 301, input devices 302, output devices 303 and memories 304 communicate with each other via a communication bus 305. The memory 304 is used to store computer programs, which include program instructions. The processor 301 is used to execute the program instructions stored in the memory 304. The processor 301 is configured to call the program instructions to execute the functions of each module / unit in the above-mentioned device embodiments, such as Figure 2 The functions of modules 21 to 24 are shown.

[0096] It should be understood that in the embodiment of the present disclosure, the processor 301 may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0097] The input device 302 may include a touch panel, a fingerprint collection sensor (for collecting the user's fingerprint information and fingerprint direction information), a microphone, etc., and the output device 303 may include a display (LCD, etc.), a speaker, etc.

[0098] The memory 304 may include a read-only memory and a random access memory, and provide instructions and data to the processor 301. A portion of the memory 304 may also include a non-volatile random access memory. For example, the memory 304 may also store information about the device type.

[0099] In a specific implementation, the processor 301, input device 302, and output device 303 described in the embodiments of the present disclosure can execute the implementation methods described in the first and second embodiments of the data processing method provided in the embodiments of the present disclosure, and can also execute the implementation methods of the electronic device described in the embodiments of the present disclosure, which will not be repeated here.

[0100] In another embodiment of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by the processor, all or part of the processes in the above-mentioned embodiment method are implemented, and the computer program can also be completed by instructing the relevant hardware through the computer program. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by the processor, the steps of each of the above-mentioned method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0101] The computer-readable storage medium may be an internal storage unit of the electronic device of any of the aforementioned embodiments, such as a hard disk or memory of the electronic device. The computer-readable storage medium may also be an external storage device of the electronic device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device. Furthermore, the computer-readable storage medium may also include both an internal storage unit of the electronic device and an external storage device. The computer-readable storage medium is used to store computer programs and other programs and data required by the electronic device. The computer-readable storage medium may also be used to temporarily store data that has been output or is to be output.

[0102] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this disclosure.

[0103] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the electronic devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0104] In the several embodiments provided in the present application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces or units, or it can be an electrical, mechanical or other form of connection.

[0105] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of the present disclosure.

[0106] In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0107] The above are only specific embodiments of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present disclosure, and these modifications or replacements should be included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be based on the protection scope of the claims.

Claims

1. A data processing method, characterized in that: include: Determine an amount of change in the operating environment of the target device based on the operating environment data of the target device; Determine the change amount of the operation data of the target device based on the operation test data of the target device; Determining a first period based on a change in the operating environment of the target device and a change in the operating data of the target device; The evaluation model is updated based on the first cycle, and the operating status of the target device is evaluated based on the updated evaluation model.

2. The data processing method according to claim 1, characterized in that: The determining the first period based on the change amount of the operating environment of the target device and the change amount of the operating data of the target device includes: Determining a first proportional parameter based on the operating environment change; determining a second proportional parameter based on the change in the operating data; The set reference period is adjusted based on the first proportion parameter and the second proportion parameter to obtain a first period.

3. The data processing method according to claim 2, characterized in that: The operating environment change amount includes change rates of multiple operating environment parameters, and determining the first proportional parameter based on the operating environment change amount includes: Determine, among the plurality of operating environment parameters, a proportion of operating environment parameters whose corresponding change rates exceed a first threshold, to obtain a first proportion; The first proportion parameter is determined based on the first proportion; the first proportion and the first proportion parameter are negatively correlated.

4. The data processing method according to claim 2, characterized in that: The operation data variation includes the variation rate of multiple operation parameters. The determining of the second proportional parameter based on the change in the operating data comprises: Determine, among the plurality of operating parameters, a proportion of operating parameters whose corresponding change rates exceed a second threshold value, to obtain a second proportion; The second proportion parameter is determined based on the second proportion; the second proportion is negatively correlated with the second proportion parameter.

5. The data processing method according to claim 1, characterized in that: Also includes: In response to the first time interval being less than the first duration, adjusting the first period based on a set third proportional parameter; The first time interval is the time interval between the current time point and the time point when the fault occurs.

6. The data processing method according to claim 1, characterized in that: The evaluation model is a support vector machine model, and the updating of the evaluation model based on the first cycle includes: Determining an update time of the evaluation model based on the first cycle; Updating the evaluation model at an update time; The updating process includes: Determine a first evaluation value based on the operating environment data of the target device; the first evaluation value is used to indicate the degree of deterioration of the operating environment data; determining a second evaluation value based on the operation test data of the target device; the second evaluation value is used to indicate the degree of degradation of the operation test data; In response to the first evaluation value being greater than the third threshold, or the second evaluation value being greater than the fourth threshold, the gamma parameter of the support vector machine model is increased by the first step length to obtain the first gamma parameter, the first gamma parameter is determined as the initial parameter of the support vector machine model, and the support vector machine model is retrained.

7. The data processing method according to claim 6, characterized in that: The updating of the evaluation model based on the first cycle includes: In response to the first period being greater than a second time period, the evaluation model is updated based on the running test data within the second time period before the update time.

8. A data processing system, characterized in that: include: A first calculation module, used to determine the change amount of the operating environment of the target device based on the operating environment data of the target device; A second calculation module, used to determine the change amount of the operation data of the target device based on the operation test data of the target device; A third calculation module determines a first period based on a change in the operating environment of the target device and a change in the operating data of the target device; The model updating module is used to update the evaluation model based on the first cycle, and evaluate the operating status of the target device based on the updated evaluation model.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images