Sewage pump control method, device, electronic equipment and storage medium

Through the sewage pump control system of the scoring pump, the pump is switched on and off in real time according to the configuration score and liquid level changes of the sewage pump, which solves the problems of unstable sewage effect and short service life, and realizes intelligent sewage management.

CN115199518BActive Publication Date: 2024-11-08WUXI HUITIAN WATER TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202210869536.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-07-22
Publication Date
2024-11-08
Estimated Expiration
2042-07-22

AI Technical Summary

Technical Problem

The existing sewage pump control system fails to effectively consider individual differences in water pumps, resulting in unstable sewage discharge effect and the inability to deal with sudden changes in water levels in advance, affecting service life.

Method used

By obtaining the configuration score of each sewage pump, adjusting the pump's opening and closing strategies in real time based on liquid level changes, giving priority to the use of high-scoring pumps for sewage discharge, extending the service life of the pump.

Benefits of technology

It improves the sewage discharge effect and the service life of the pump, realizes intelligent pump group scheduling, and reduces labor costs.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115199518B_ABST
    Figure CN115199518B_ABST
Patent Text Reader

Abstract

The present application provides a control method, device, electronic device and computer-readable storage medium for a sewage pump, the method comprising: obtaining a configuration score of each sewage pump based on the configuration information of each sewage pump; when it is detected that the liquid level in the target drainage area rises and the amount of liquid level rise within a first preset time is greater than a first preset threshold, based on the amount of liquid level rise and the configuration scores of all sewage pumps, obtaining corresponding opening strategies of N sewage pumps, so that the k sewage pumps with the highest configuration scores are turned on; when it is detected that the liquid level in the target drainage area drops and the amount of liquid level drop within the first preset time is greater than a second preset threshold, based on the amount of liquid level drop and the configuration scores of all sewage pumps, obtaining corresponding closing strategies of N sewage pumps, so that the g sewage pumps with the lowest configuration scores are turned off. Let sewage pumps with stronger sewage discharge capacity participate more in sewage discharge work to ensure sewage discharge effect.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical fields of sewage treatment, fault detection, and deep learning, and in particular to a control method, device, electronic device, and computer-readable storage medium for a sewage pump. Background Art

[0002] In recent years, with the rapid development of cities, the amount of urban sewage has also increased, necessitating a large-scale expansion of urban sewage pipes and sewage pumping rooms. The normal operation of sewage pumps in the pumping rooms is related to the water supply of thousands of households.

[0003] When equipment fails or rainwater backflows into the pump room, the sewage pump in the pump room is forced to stop running, which leads to sewage interruption. When the sewage pump is damp, the insulation is damaged, which may cause electric shock accidents, resulting in life-threatening and economic losses. Therefore, it is particularly important to reasonably allocate sewage pumps and respond to sudden surges in water levels in advance.

[0004] Patent CN207264210U discloses a liquid level control system, including multiple water pumps and a float type liquid level gauge, the float type liquid level gauge includes a body, a float and a liquid level control rod, the body includes a near water end and a far water end arranged along its axial direction, a plurality of trigger switches are arranged at intervals along the axial direction on the body, a trigger part is arranged on the liquid level feedback rod, each of the multiple trigger switches is electrically connected to at least one of the multiple water pumps, the trigger part reciprocates along the axial direction of the liquid level feedback rod to trigger the corresponding trigger switch, and the trigger switch sends a corresponding opening or closing signal to control the start or shutdown of the multiple water pumps. However, this method does not take into account the individual differences in the configuration of the water pump, and some water pumps may frequently fail. The sewage discharge capacity of this water pump is not comparable to that of a water pump that has never failed. Therefore, the overall sewage discharge effect is unstable, and prevention is not taken until the water level has risen to a certain height, and it cannot be dealt with in advance. The water pump needs a longer time to work, which will shorten the service life of the water pump.

[0005] Therefore, there is an urgent need to provide a control method, device, electronic device and computer-readable storage medium for a sewage pump to solve the problems existing in the prior art. Summary of the invention

[0006] The purpose of this application is to provide a control method, device, electronic device and computer-readable storage medium for a sewage pump, so that a sewage pump with a strong sewage discharge capacity and relatively stable and reliable operation can participate more in sewage discharge work and ensure the sewage discharge effect.

[0007] The purpose of this application is achieved by the following technical solutions:

[0008] In a first aspect, the present application provides a sewage pump control method for controlling the opening and closing of N sewage pumps corresponding to a target drainage area, the method comprising:

[0009] Based on the configuration information of each of the sewage pumps, a configuration score of each of the sewage pumps is obtained, wherein the configuration information includes a performance score, a number of overhauls, a number of failures, and a remaining service life;

[0010] Using a liquid level sensor to measure the liquid level of the target drainage area in real time;

[0011] When it is detected that the liquid level in the target drainage area rises and the amount of liquid level rise within a first preset time period is greater than a first preset threshold, based on the amount of liquid level rise and the configuration scores of all sewage pumps, the corresponding start-up strategies of N sewage pumps are obtained, so that the k sewage pumps with the highest configuration scores are turned on;

[0012] When it is detected that the liquid level in the target drainage area drops and the amount of the liquid level drop within the first preset time period is greater than a second preset threshold, based on the amount of the liquid level drop and the configuration scores of all sewage pumps, the corresponding shutdown strategies of the N sewage pumps are obtained, so that the g sewage pumps with the lowest configuration scores are shut down;

[0013] Wherein, N is an integer greater than 1, and k and g are positive integers not greater than N.

[0014] The beneficial effect of this technical solution is that: according to the configuration information of each sewage pump, the configuration score corresponding to the sewage pump is obtained. The configuration score can reflect the sewage discharge capacity and stability of the sewage pump. The higher the configuration score, the better the sewage discharge performance of the sewage pump, the less likely it is to suddenly fail, and the more stable and reliable the operation. The control process of the above-mentioned sewage pump does not require human participation to make decisions, has a high degree of intelligence, and consumes low labor costs. After obtaining a certain amount of sewage pump big data, through continuous optimization of the decision, it is possible to make accurate decisions intelligently for a variety of complex scenarios, and has a wide range of applications.

[0015] The liquid level in the target drainage area is measured in real time by using a liquid level sensor. When a liquid level rise is detected and the amount of liquid level rise within a first preset time period is greater than a first preset threshold value, it indicates that the liquid level is rising very quickly. All sewage pumps can be allocated based on their configuration scores and the speed at which the liquid level rises. Sewage pumps with high configuration scores can be turned on first, which can make the liquid level in the target drainage area drop faster than turning on sewage pumps with low configuration scores. When a liquid level drop is detected and the amount of liquid level drop within a first preset time period is greater than a second preset threshold value, it indicates that the liquid level is dropping very quickly. All sewage pumps can be allocated based on their configuration scores and the speed at which the liquid level drops. Sewage pumps are allocated, and sewage pumps with low configuration scores are shut down first. Compared with shutting down sewage pumps with high configuration scores, the performance decline rate of sewage pumps with low configuration scores can be delayed under the premise of rapid drop in the liquid level in the target drainage area, thereby extending their service life (generally speaking, the more times a sewage pump is used and the longer it is used, the lower its performance score and the shorter its remaining service life). In this way, from the perspective of the speed of liquid level change, the change of liquid level can be predicted in advance, and the sewage discharge tasks of sewage pumps can be reasonably allocated, thereby shortening the entire sewage discharge cycle and extending the service life of sewage pumps; sewage pumps with strong sewage discharge capacity and relatively stable and reliable operation can be allowed to participate more in sewage discharge work to ensure the sewage discharge effect.

[0016] In some optional embodiments, obtaining a configuration score of each sewage pump based on the configuration information of each sewage pump includes:

[0017] Inputting the configuration information of each sewage pump into the configuration evaluation model to obtain a configuration score corresponding to each sewage pump;

[0018] The training process of the configuration evaluation model includes:

[0019] Obtain a first training set, where the first training set includes a plurality of first training data, each of the first training data includes configuration information of a sample sewage pump and labeled data of a configuration score of the sample sewage pump;

[0020] For each first training data in the first training set, perform the following processing:

[0021] Inputting the configuration information of the sample sewage pump in the first training data into a preset first deep learning model to obtain prediction data of the configuration score of the sample sewage pump;

[0022] Based on the predicted data and the labeled data of the configuration score of the sample sewage pump, updating the model parameters of the first deep learning model;

[0023] Detect whether a preset first training end condition is met; if so, use the trained first deep learning model as the configuration evaluation model; if not, continue to train the first deep learning model using the next first training data.

[0024] The beneficial effect of this technical solution is that by designing, establishing an appropriate amount of neuron computing nodes and a multi-layer operation hierarchy, and selecting appropriate input layers and output layers, a preset first deep learning model can be obtained. Through learning and tuning of the preset first deep learning model, a functional relationship from input to output is established. Although the functional relationship between input and output cannot be found 100%, the actual correlation relationship can be approached as much as possible. The configuration evaluation model thus trained can obtain the configuration score corresponding to the sewage pump based on the configuration information of the sewage pump, and the calculation results are highly accurate and reliable.

[0025] In some optional embodiments, obtaining a configuration score of each sewage pump based on the configuration information of each sewage pump includes:

[0026] Obtaining a first weight corresponding to the performance score, a second weight corresponding to the number of maintenance times, a third weight corresponding to the number of failures, and a fourth weight corresponding to the remaining service life;

[0027] The configuration score of each sewage pump is calculated based on the performance score of each sewage pump and the first weight, the number of overhauls of each sewage pump and the second weight, the number of failures of each sewage pump and the third weight, and the remaining service life of each sewage pump and the fourth weight.

[0028] The beneficial effect of this technical solution is that it evaluates the performance score, the number of overhauls, the number of failures and the remaining service life, assigns different weights to each aspect, and obtains the configuration score corresponding to each sewage pump after calculation. This calculation method is relatively simple and direct, and the calculated configuration score can reflect the sewage discharge capacity and stability of the sewage pump. Different weights are set for the performance score, the number of overhauls, the number of failures and the remaining service life. These weights are used to reflect the importance of each factor relative to the configuration score, emphasizing the relative importance or contribution of each factor. By setting and adjusting the weights, the configuration score indicator can accurately reflect the performance level of the sewage pump, and the decisions made in the decision-making process of intelligently controlling the drainage of sewage pumps are closer to the needs of actual applications.

[0029] In some optional embodiments, the method further includes:

[0030] When the liquid level in the target drainage area is detected to rise, the following processing is performed for each sewage pump that is turned on:

[0031] When the opening time of the sewage pump reaches a second preset time, obtaining a first difference between the current liquid level and the initial liquid level of the target drainage area, wherein the initial liquid level is the liquid level of the target drainage area before the sewage pump is turned on;

[0032] When the ratio of the first difference to the number of sewage pumps in the turned-on state is greater than a third preset threshold, performing a fault detection on the sewage pump to determine whether a fault occurs;

[0033] When a failure of the sewage pump is detected, the configuration information of the sewage pump is updated to increase the number of failures of the sewage pump by 1, and first prompt information is generated and sent to a user device, wherein the first prompt information includes identification information of the sewage pump.

[0034] The beneficial effect of this technical solution is that when the liquid level in the target drainage area rises, the sewage discharge capacity of the turned-on sewage pump is detected. When the turning-on time of the sewage pump reaches the second preset time, if the ratio of the corresponding first difference to the number of turned-on sewage pumps is greater than the third preset threshold, it indicates that the current liquid level has risen more than the initial liquid level, and the sewage pump has not curbed the rising trend of the liquid level well. The sewage pump is very likely to fail. At this time, the sewage pump can be targeted for fault detection. When a fault is detected in the sewage pump, the configuration information of the sewage pump is updated in time. In this way, the configuration score of the sewage pump that has failed can be adjusted to provide a reference for the allocation of the next sewage discharge work.

[0035] In some optional embodiments, the method further includes:

[0036] When it is detected that the liquid level in the target drainage area drops, the following processing is performed for each sewage pump that is turned on:

[0037] When the opening time of the sewage pump reaches a second preset time, obtaining a second difference between an initial liquid level and a current liquid level in the target drainage area, wherein the initial liquid level is the liquid level in the target drainage area before the sewage pump is turned on;

[0038] When the ratio of the second difference to the number of sewage pumps in the turned-on state is less than a fourth preset threshold, performing a fault detection on the sewage pump to determine whether a fault occurs;

[0039] When a failure of the sewage pump is detected, the configuration information of the sewage pump is updated to increase the number of failures of the sewage pump by 1, and a second prompt message is generated to be sent to a user device, wherein the second prompt message includes identification information of the sewage pump.

[0040] The beneficial effect of this technical solution is that when the liquid level in the target drainage area drops, the sewage discharge capacity of the turned-on sewage pump is detected. When the turn-on time of the sewage pump reaches the second preset time, if the ratio of the corresponding second difference to the number of turned-on sewage pumps is less than the fourth preset threshold, it indicates that the current liquid level is smaller than the initial liquid level, and the sewage pump has not played a good role in sewage discharge. The sewage pump is very likely to fail. At this time, the sewage pump can be targeted for fault detection. When a fault is detected in the sewage pump, the configuration information of the sewage pump is updated in time. In this way, the configuration score of the sewage pump that has failed can be adjusted to provide a reference for the allocation of the next sewage discharge work.

[0041] In some optional embodiments, the performing fault detection on the sewage pump to determine whether a fault occurs includes:

[0042] Acquire measurement data of a plurality of operating parameters of the sewage pump, the plurality of operating parameters comprising at least two of a current parameter, a voltage parameter, a temperature parameter, a vibration parameter, and a speed parameter;

[0043] Respectively detecting whether the measurement data of each of the operating parameters is within its corresponding preset range;

[0044] When it is detected that the measurement data of at least one of the operating parameters is not within the preset range corresponding to itself, the measurement data of multiple operating parameters are used as the first input of the fault detection model, and the predicted fault type and predicted similarity corresponding to the first input are output through the fault detection model; wherein the fault detection model is used to compare the first input with each fault data in the fault database respectively, obtain the similarity between the first input and each fault data, use the highest similarity among the multiple similarities corresponding to the first input as the predicted similarity corresponding to the first input, use the fault type of the fault data with the highest similarity to the first input as the predicted fault type corresponding to the first input, and output the predicted fault type and predicted similarity corresponding to the first input;

[0045] When the predicted similarity corresponding to the first input is less than a preset similarity threshold, it is determined that no fault has occurred; when the predicted similarity corresponding to the first input is not less than the preset similarity threshold, it is determined that a fault has occurred.

[0046] The beneficial effect of this technical solution is that a two-stage detection process is used to determine whether a fault has occurred. When the first stage detects a possible fault, it is not directly determined to be a fault, but enters the second stage of fault detection. When the second stage also detects a possible fault, it is determined that the sewage pump has a fault. Therefore, the obtained fault detection result has high credibility, avoiding frequent misjudgments that affect the normal use of the sewage pump.

[0047] Specifically, in the first stage, multiple sensors are used to obtain measurement data of multiple operating parameters, and each operating parameter's measurement data is detected to see if it is within its corresponding preset range. When one or more operating parameter's measurement data exceeds its corresponding preset range, it indicates that the sewage pump may have a fault, and the second stage is entered. In the second stage, the measurement data of multiple operating parameters are input into the fault detection model, and the fault detection model is used to determine the closest fault type of the sewage pump during the current operation as the predicted fault type. The fault detection model also gives the similarity between the input data and the predicted fault type as the predicted similarity, and determines whether a fault has occurred by comparing the predicted similarity with the preset similarity threshold. Obviously, the higher the similarity, the more likely the sewage pump has a fault corresponding to the predicted fault type.

[0048] In addition, the measurement data of multiple operating parameters are used as the input data of the fault detection model. The correlation between multiple operating parameters is taken into consideration, and a comprehensive judgment is made on the measurement data of multiple operating parameters to avoid misjudgment caused by the numerical fluctuation of a single operating parameter. Instead, multiple operating parameters are taken as a whole and compared one by one with the multiple fault data pre-stored in the fault database to find the fault data with the highest similarity, and the fault type corresponding to the fault data is used as the predicted fault type, which further improves the accuracy of the fault detection results.

[0049] In some optional embodiments, the method further includes:

[0050] For each sewage pump that is not turned on, perform the following processing:

[0051] When the time from the last time the sewage pump ended running is not less than the third preset time, controlling the sewage pump to run and the running time is not less than the fourth preset time, so as to perform fault detection on the sewage pump to determine whether a fault occurs;

[0052] When a failure of the sewage pump is detected, the configuration information of the sewage pump is updated to increase the number of failures of the sewage pump by 1, and third prompt information is generated and sent to the user device, wherein the third prompt information includes identification information of the sewage pump.

[0053] The beneficial effect of this technical solution is that regular fault detection is very necessary for sewage pumps that have not been operated for a long time. Through regular fault detection, the aging of the equipment can be checked to avoid sudden failure of the sewage pump during subsequent operation. When the sewage pump has been running for no less than the third preset time since it last ended, the sewage pump is allowed to run and the running time is no less than the fourth preset time, so that the sewage pump is fault-detected during its operation. When a fault is detected in the sewage pump, the configuration information of the sewage pump is updated in time. In this way, the configuration score of the sewage pump that has failed can be adjusted to provide a reference for the allocation of the next sewage work.

[0054] In a second aspect, the present application provides a sewage pump control device for controlling the opening and closing of N sewage pumps corresponding to a target drainage area, the device comprising:

[0055] A configuration acquisition module, for acquiring a configuration score of each sewage pump based on the configuration information of each sewage pump, wherein the configuration information includes a performance score, a number of overhauls, a number of failures, and a remaining service life;

[0056] A liquid level measurement module, used to measure the liquid level of the target drainage area in real time using a liquid level sensor;

[0057] An opening control module is used to obtain corresponding opening strategies of N sewage pumps based on the amount of liquid level rise and the configuration scores of all sewage pumps when it is detected that the liquid level in the target drainage area rises and the amount of liquid level rise within a first preset time period is greater than a first preset threshold, so as to turn on the k sewage pumps with the highest configuration scores;

[0058] A shutdown control module, configured to, when it is detected that the liquid level in the target drainage area drops and the amount of the liquid level drop within the first preset time period is greater than a second preset threshold, obtain the corresponding shutdown strategies of the N sewage pumps based on the amount of the liquid level drop and the configuration scores of all sewage pumps, so as to shut down the g sewage pumps with the lowest configuration scores;

[0059] Wherein, N is an integer greater than 1, and k and g are positive integers not greater than N.

[0060] In some optional embodiments, the configuration acquisition module is used to: input the configuration information of each sewage pump into the configuration evaluation model to obtain a configuration score corresponding to each sewage pump;

[0061] The training process of the configuration evaluation model includes:

[0062] Obtain a first training set, where the first training set includes a plurality of first training data, each of the first training data includes configuration information of a sample sewage pump and labeled data of a configuration score of the sample sewage pump;

[0063] For each first training data in the first training set, perform the following processing:

[0064] Inputting the configuration information of the sample sewage pump in the first training data into a preset first deep learning model to obtain prediction data of the configuration score of the sample sewage pump;

[0065] Based on the predicted data and the labeled data of the configuration score of the sample sewage pump, updating the model parameters of the first deep learning model;

[0066] Detect whether a preset first training end condition is met; if so, use the trained first deep learning model as the configuration evaluation model; if not, continue to train the first deep learning model using the next first training data.

[0067] In some optional embodiments, the configuration acquisition module includes:

[0068] A weight acquisition unit, used to acquire a first weight corresponding to the performance score, a second weight corresponding to the number of maintenance times, a third weight corresponding to the number of failures, and a fourth weight corresponding to the remaining service life;

[0069] A score calculation unit is used to calculate the configuration score of each sewage pump based on the performance score of each sewage pump and the first weight, the number of overhauls of each sewage pump and the second weight, the number of failures of each sewage pump and the third weight, and the remaining service life of each sewage pump and the fourth weight.

[0070] In some optional embodiments, the device further comprises:

[0071] The first fault detection module is used for:

[0072] When the liquid level in the target drainage area is detected to rise, the following processing is performed for each sewage pump that is turned on:

[0073] When the opening time of the sewage pump reaches a second preset time, obtaining a first difference between the current liquid level and the initial liquid level of the target drainage area, wherein the initial liquid level is the liquid level of the target drainage area before the sewage pump is turned on;

[0074] When the ratio of the first difference to the number of sewage pumps in the turned-on state is greater than a third preset threshold, performing a fault detection on the sewage pump to determine whether a fault occurs;

[0075] When a failure of the sewage pump is detected, the configuration information of the sewage pump is updated to increase the number of failures of the sewage pump by 1, and first prompt information is generated and sent to a user device, wherein the first prompt information includes identification information of the sewage pump.

[0076] In some optional embodiments, the device further comprises:

[0077] The second fault detection module is used for:

[0078] When it is detected that the liquid level in the target drainage area drops, the following processing is performed for each sewage pump that is turned on:

[0079] When the opening time of the sewage pump reaches a second preset time, obtaining a second difference between an initial liquid level and a current liquid level in the target drainage area, wherein the initial liquid level is the liquid level in the target drainage area before the sewage pump is turned on;

[0080] When the ratio of the second difference to the number of sewage pumps in the turned-on state is less than a fourth preset threshold, performing a fault detection on the sewage pump to determine whether a fault occurs;

[0081] When a failure of the sewage pump is detected, the configuration information of the sewage pump is updated to increase the number of failures of the sewage pump by 1, and a second prompt message is generated to be sent to a user device, wherein the second prompt message includes identification information of the sewage pump.

[0082] In some optional embodiments, the process of performing fault detection on the sewage pump includes:

[0083] Acquire measurement data of a plurality of operating parameters of the sewage pump, the plurality of operating parameters comprising at least two of a current parameter, a voltage parameter, a temperature parameter, a vibration parameter, and a speed parameter;

[0084] Respectively detecting whether the measurement data of each of the operating parameters is within its corresponding preset range;

[0085] When it is detected that the measurement data of at least one of the operating parameters is not within the preset range corresponding to itself, the measurement data of multiple operating parameters are used as the first input of the fault detection model, and the predicted fault type and predicted similarity corresponding to the first input are output through the fault detection model; wherein the fault detection model is used to compare the first input with each fault data in the fault database respectively, obtain the similarity between the first input and each fault data, use the highest similarity among the multiple similarities corresponding to the first input as the predicted similarity corresponding to the first input, use the fault type of the fault data with the highest similarity to the first input as the predicted fault type corresponding to the first input, and output the predicted fault type and predicted similarity corresponding to the first input;

[0086] When the predicted similarity corresponding to the first input is less than a preset similarity threshold, it is determined that no fault has occurred; when the predicted similarity corresponding to the first input is not less than the preset similarity threshold, it is determined that a fault has occurred.

[0087] In some optional embodiments, the device further comprises:

[0088] The third fault detection module is used for:

[0089] For each sewage pump that is not turned on, perform the following processing:

[0090] When the time from the last time the sewage pump ended running is not less than the third preset time, controlling the sewage pump to run and the running time is not less than the fourth preset time, so as to perform fault detection on the sewage pump to determine whether a fault occurs;

[0091] When a failure of the sewage pump is detected, the configuration information of the sewage pump is updated to increase the number of failures of the sewage pump by 1, and third prompt information is generated and sent to the user device, wherein the third prompt information includes identification information of the sewage pump.

[0092] In a third aspect, the present application provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any one of the above methods when executing the computer program.

[0093] In a fourth aspect, the present application provides a computer-readable storage medium storing a computer program, which implements the steps of any of the above methods when executed by a processor. BRIEF DESCRIPTION OF THE DRAWINGS

[0094] The present application is further described below in conjunction with the accompanying drawings and embodiments.

[0095] Figure 1It is a flow chart of a sewage pump control method provided in an embodiment of the present application.

[0096] Figure 2 It is a structural block diagram of a sewage treatment system provided in an embodiment of the present application.

[0097] Figure 3 It is a structural block diagram of a control device for a sewage pump provided in an embodiment of the present application.

[0098] Figure 4 It is a structural block diagram of an electronic device provided in an embodiment of the present application.

[0099] Figure 5 It is a structural block diagram of a program product provided in an embodiment of the present application. DETAILED DESCRIPTION

[0100] Below, the present application is further described in conjunction with the accompanying drawings and specific implementation methods. It should be noted that, under the premise of no conflict, the various embodiments or technical features described below can be arbitrarily combined to form a new embodiment.

[0101] See also Figure 1 , Figure 1 It is a flow chart of a sewage pump control method provided in an embodiment of the present application.

[0102] The method is used to control the opening and closing of N sewage pumps corresponding to the target drainage area, and the method includes:

[0103] Step S101: Based on the configuration information of each sewage pump, a configuration score of each sewage pump is obtained, wherein the configuration information includes a performance score, a number of overhauls, a number of failures, and a remaining service life;

[0104] Step S102: using a liquid level sensor to measure the liquid level of the target drainage area in real time;

[0105] Step S103: when it is detected that the liquid level in the target drainage area rises and the amount of liquid level rise within a first preset time period is greater than a first preset threshold, based on the amount of liquid level rise and the configuration scores of all sewage pumps, the corresponding start-up strategies of N sewage pumps are obtained, so that the k sewage pumps with the highest configuration scores are turned on;

[0106] Step S104: when it is detected that the liquid level in the target drainage area drops and the amount of the liquid level drop within the first preset time period is greater than a second preset threshold, based on the amount of the liquid level drop and the configuration scores of all sewage pumps, the corresponding shutdown strategies of the N sewage pumps are obtained, so that the g sewage pumps with the lowest configuration scores are shut down;

[0107] Wherein, N is an integer greater than 1, and k and g are positive integers not greater than N.

[0108] Therefore, according to the configuration information of each sewage pump, the configuration score corresponding to the sewage pump is obtained. The configuration score can reflect the sewage discharge capacity and stability of the sewage pump. The higher the configuration score, the better the sewage discharge performance of the sewage pump, the less likely it is to fail suddenly, and the more stable and reliable its operation.

[0109] The liquid level in the target drainage area is measured in real time by using a liquid level sensor. When a liquid level rise is detected and the amount of liquid level rise within a first preset time period is greater than a first preset threshold value, it indicates that the liquid level is rising very quickly. All sewage pumps can be allocated based on their configuration scores and the speed at which the liquid level rises. Sewage pumps with high configuration scores can be turned on first, which can make the liquid level in the target drainage area drop faster than turning on sewage pumps with low configuration scores. When a liquid level drop is detected and the amount of liquid level drop within a first preset time period is greater than a second preset threshold value, it indicates that the liquid level is dropping very quickly. All sewage pumps can be allocated based on their configuration scores and the speed at which the liquid level drops. Sewage pumps are allocated, and sewage pumps with low configuration scores are shut down first. Compared with shutting down sewage pumps with high configuration scores, the performance decline rate of sewage pumps with low configuration scores can be delayed under the premise of rapid drop in the liquid level in the target drainage area, thereby extending their service life (generally speaking, the more times a sewage pump is used and the longer it is used, the lower its performance score and the shorter its remaining service life). In this way, from the perspective of the speed of liquid level change, the change of liquid level can be predicted in advance, and the sewage discharge tasks of sewage pumps can be reasonably allocated, thereby shortening the entire sewage discharge cycle and extending the service life of sewage pumps; sewage pumps with strong sewage discharge capacity and relatively stable and reliable operation can be allowed to participate more in sewage discharge work to ensure the sewage discharge effect.

[0110] The performance score is used to indicate the quality of the parameters such as vibration intensity, power, and speed of the sewage pump. The performance score is directly related to the model and strength of the parts used in the sewage pump. The performance score can be expressed as a number or a percentage, such as 60, 70, or 80. Generally speaking, the higher the performance score, the better the performance of the sewage pump.

[0111] The target drainage area can be a sump or sewage tank connected to N sewage pumps.

[0112] The present application can be applied to sewage treatment occasions as well as non-sewage treatment occasions, such as sinks, reservoirs, swimming pools, rivers, etc. that need to be drained.

[0113] The present application does not limit the first preset time length, the first preset threshold and the second preset threshold. The first preset time length is, for example, 10 minutes, 20 minutes or 30 minutes, the first preset threshold is, for example, 5 cm, 8 cm or 10 cm, and the second preset threshold is, for example, 5 cm, 8 cm or 10 cm.

[0114] The present application does not limit N, and N is, for example, 2, 5, 11 or 20.

[0115] When it is detected that the liquid level in the target drainage area rises and the amount of liquid level increase within the first preset time period is not greater than the first preset threshold, or when it is detected that the liquid level in the target drainage area drops and the amount of liquid level drop within the first preset time period is not greater than the second preset threshold, it indicates that the rising speed or the falling speed of the liquid level is relatively slow, and the N sewage pumps maintain the current operating state without adjusting the opening strategy or the closing strategy.

[0116] In some embodiments, obtaining the corresponding starting strategies of N sewage pumps based on the liquid level rise and the configuration scores of all sewage pumps so as to turn on the k sewage pumps with the highest configuration scores may include: inputting the liquid level rise and the configuration scores of all sewage pumps into a preset first calculation formula, and calculating a value k to turn on the k sewage pumps with the highest configuration scores.

[0117] Correspondingly, the method of obtaining the corresponding shutdown strategies of N sewage pumps based on the liquid level drop and the configuration scores of all sewage pumps to shut down the g sewage pumps with the lowest configuration scores may include: inputting the liquid level drop and the configuration scores of all sewage pumps into a preset second calculation formula, and calculating the value g to shut down the g sewage pumps with the lowest configuration scores.

[0118] The present application does not limit the preset first calculation formula / second calculation formula, such as a univariate polynomial or a multivariate polynomial, or a linear polynomial or a nonlinear polynomial.

[0119] In some optional implementations, the performance score of the sewage pump may be expressed in percentage (0 to 100 points).

[0120] In other optional embodiments, the configuration score of the sewage pump is a value not less than 0 and not greater than 1 (the score on a percentage basis divided by 100). A configuration score of 0 for the sewage pump indicates that the sewage pump cannot work, and a configuration score of 1 for the sewage pump indicates that the performance of the sewage pump is at its best (the sewage pump with a configuration score of 1 is taken as a standard sewage pump).

[0121] The first calculation formula may be, for example: ((liquid level rise / first preset time)*(cross-sectional area of ​​target drainage area)) / (discharge per unit time of standard sewage pump*average configuration score of N sewage pumps).

[0122] The second calculation formula may be, for example: ((liquid level drop / first preset time)*(cross-sectional area of ​​target drainage area)) / (discharge per unit time of standard sewage pump*average configuration score of N sewage pumps).

[0123] The first calculation formula and the independent variables (liquid level rise and the configuration scores of all sewage pumps) are used to calculate the dependent variable (value k, rounded to an integer); the second calculation formula and the independent variables (liquid level drop and the configuration scores of all sewage pumps) are used to calculate the dependent variable (value g, rounded to an integer). The calculation process based on the calculation formula consumes less computing resources, takes less computing time, and has higher computing efficiency.

[0124] In some embodiments, when it is detected that the liquid level in the target drainage area has risen and the amount of liquid level rise within a first preset time period is greater than a first preset threshold, the k sewage pumps with the highest configuration scores can be turned on and the remaining sewage pumps can be turned off (the k sewage pumps with the highest configuration scores are turned on, and the Nk sewage pumps with lower configuration scores are turned off).

[0125] When it is detected that the liquid level in the target drainage area has dropped and the amount of drop in the liquid level within the first preset time period is greater than the second preset threshold, the g sewage pumps with the lowest configuration score can be turned off and the remaining sewage pumps can be turned on (the g sewage pumps with the lowest configuration score are turned off, and Ng sewage pumps with higher configuration scores are turned on).

[0126] In some implementations, acquiring corresponding start-up strategies of N sewage pumps based on the liquid level rise and the configuration scores of all sewage pumps so as to start k sewage pumps with the highest configuration scores may include:

[0127] Get the average configuration score of N sewage pumps;

[0128] The liquid level rise and the average configuration score are input into a first mapping table to obtain a corresponding value k, so that the k sewage pumps with the highest configuration scores are turned on.

[0129] Accordingly, the acquiring corresponding shutdown strategies of the N sewage pumps based on the liquid level drop and the configuration scores of all sewage pumps so as to shut down the g sewage pumps with the lowest configuration scores may include:

[0130] Get the average configuration score of N sewage pumps;

[0131] The liquid level drop and the average configuration score are input into a second mapping table to obtain a corresponding value g, so that the g sewage pumps with the lowest configuration scores are turned off.

[0132] For a specific drainage area (such as a sump with a fixed size), the number of sewage pumps in the corresponding pump room is often fixed within a period of time, so a customized first mapping table and a second mapping table can be set for each pump room.

[0133] The first mapping table is used to indicate the correspondence between the amount of liquid level rise, the average configuration score and the value k, and the second mapping table is used to indicate the correspondence between the amount of liquid level drop, the average configuration score and the value g.

[0134] In a specific application, the first mapping table indicates that the liquid level rise is 2 cm, the average configuration score is 0.6, and the value k=7;

[0135] The liquid level rise is 1 cm, the average configuration score is 0.7, and the value k=3.

[0136] In a specific application, the second mapping table indicates that the liquid level drop is 2 cm, the average configuration score is 0.6, and the value g=2;

[0137] The liquid level rise is 1 cm, and the average configuration score is 0.5, so the value g=5.

[0138] In some optional embodiments, the step S101 may include:

[0139] Inputting the configuration information of each sewage pump into the configuration evaluation model to obtain a configuration score corresponding to each sewage pump;

[0140] The training process of the configuration evaluation model includes:

[0141] Obtain a first training set, where the first training set includes a plurality of first training data, each of the first training data includes configuration information of a sample sewage pump and labeled data of a configuration score of the sample sewage pump;

[0142] For each first training data in the first training set, perform the following processing:

[0143] Inputting the configuration information of the sample sewage pump in the first training data into a preset first deep learning model to obtain prediction data of the configuration score of the sample sewage pump;

[0144] Based on the predicted data and the labeled data of the configuration score of the sample sewage pump, updating the model parameters of the first deep learning model;

[0145] Detect whether a preset first training end condition is met; if so, use the trained first deep learning model as the configuration evaluation model; if not, continue to train the first deep learning model using the next first training data.

[0146] Therefore, by designing, establishing an appropriate amount of neuron computing nodes and a multi-layer operation hierarchy, and selecting appropriate input and output layers, a preset first deep learning model can be obtained. Through the learning and tuning of the preset first deep learning model, a functional relationship from input to output is established. Although the functional relationship between input and output cannot be found 100%, the actual correlation relationship can be approached as much as possible. The configuration evaluation model thus trained can obtain the configuration score corresponding to the sewage pump based on the configuration information of the sewage pump, and the calculation results have high accuracy and reliability.

[0147] The present application does not limit the method for obtaining the annotation data for configuration scoring. For example, manual annotation, automatic annotation, or semi-automatic annotation may be used.

[0148] The present application does not limit the training process of the configuration evaluation model, which may adopt the above-mentioned supervised learning training method, or may adopt a semi-supervised learning training method, or may adopt an unsupervised learning training method.

[0149] The present application does not limit the preset first training end condition, which may be, for example, that the number of trainings reaches a preset number of times (the preset number of times is, for example, 1 time, 3 times, 10 times, 100 times, 1000 times, 10000 times, etc.), or that the first training data in the first training set has completed one or more trainings, or that the total loss value obtained in this training is not greater than the preset loss value.

[0150] In some optional embodiments, the step S101 may include:

[0151] Obtaining a first weight corresponding to the performance score, a second weight corresponding to the number of maintenance times, a third weight corresponding to the number of failures, and a fourth weight corresponding to the remaining service life;

[0152] The configuration score of each sewage pump is calculated based on the performance score of each sewage pump and the first weight, the number of overhauls of each sewage pump and the second weight, the number of failures of each sewage pump and the third weight, and the remaining service life of each sewage pump and the fourth weight.

[0153] Therefore, the performance score, number of overhauls, number of failures and remaining service life are evaluated, and different weights are assigned to each aspect. After calculation, the configuration score corresponding to each sewage pump is obtained. This calculation method is relatively simple and direct. The calculated configuration score can reflect the sewage discharge capacity and stability of the sewage pump. Different weights are set for the performance score, number of overhauls, number of failures and remaining service life. These weights are used to reflect the importance of each factor relative to the configuration score, emphasizing the relative importance or contribution of each factor. By setting and adjusting the weights, the configuration score indicator can accurately reflect the performance level of the sewage pump, and the decisions made in the decision-making process of intelligent control of sewage pump drainage are closer to the needs of actual applications.

[0154] The present application does not limit the first weight, the second weight, the third weight and the fourth weight. The first weight, the second weight, the third weight and the fourth weight can be expressed by numbers or percentages.

[0155] In a specific application, the first weight is 1, the second weight is -2, the third weight is -3, and the fourth weight is 2.

[0156] The performance score of sewage pump a is 80, the number of overhauls is 5, the number of failures is 2, and the remaining service life is 5 (years); the performance score of sewage pump b is 90, the number of overhauls is 3, the number of failures is 1, and the remaining service life is 8 (years); the performance score of sewage pump c is 85, the number of overhauls is 4, the number of failures is 2, and the remaining service life is 7 (years).

[0157] The configuration score of sewage pump a is:

[0158] The configuration score of sewage pump b is:

[0159] The configuration score of sewage pump c is:

[0160] In some optional embodiments, the method may further include:

[0161] When the liquid level in the target drainage area is detected to rise, the following processing is performed for each sewage pump that is turned on:

[0162] When the opening time of the sewage pump reaches a second preset time, obtaining a first difference between the current liquid level and the initial liquid level of the target drainage area, wherein the initial liquid level is the liquid level of the target drainage area before the sewage pump is turned on;

[0163] When the ratio of the first difference to the number of sewage pumps in the turned-on state is greater than a third preset threshold, performing a fault detection on the sewage pump to determine whether a fault occurs;

[0164] When a failure of the sewage pump is detected, the configuration information of the sewage pump is updated to increase the number of failures of the sewage pump by 1, and first prompt information is generated and sent to a user device, wherein the first prompt information includes identification information of the sewage pump.

[0165] Therefore, when the liquid level in the target drainage area rises, the sewage discharge capacity of the turned-on sewage pump is tested. When the turning-on time of the sewage pump reaches the second preset time, if the ratio of the corresponding first difference to the number of turned-on sewage pumps is greater than the third preset threshold, it indicates that the current liquid level has risen more than the initial liquid level, and the sewage pump has not curbed the rising trend of the liquid level well. The sewage pump is very likely to fail. At this time, the sewage pump can be targeted for fault detection. When a fault is detected in the sewage pump, the configuration information of the sewage pump is updated in time. In this way, the configuration score of the sewage pump that has failed can be adjusted to provide a reference for the allocation of the next sewage discharge work.

[0166] The sewage pump in the on state refers to a sewage pump (including the current sewage pump itself) that has been running (not shut down) from the time when the current sewage pump is just turned on until the on time reaches the second preset time.

[0167] The present application does not limit the second preset time length and the third preset threshold value. The second preset time length is, for example, 10 minutes, 30 minutes or 60 minutes, and the third preset threshold value is, for example, 1, 2 or 3.

[0168] The first prompt information may be prompt information in the form of text, image, video or voice.

[0169] The user device can be a smart terminal device such as a mobile phone, tablet computer, laptop computer, desktop computer, smart wearable device, etc., or it can be a workstation or console.

[0170] The identification information of the sewage pump can be represented by one or more of Chinese characters, letters, punctuation marks and special characters, for example, it can be A001 or pump #1.

[0171] In some optional embodiments, the method may further include:

[0172] When it is detected that the liquid level in the target drainage area drops, the following processing is performed for each sewage pump that is turned on:

[0173] When the opening time of the sewage pump reaches a second preset time, obtaining a second difference between an initial liquid level and a current liquid level in the target drainage area, wherein the initial liquid level is the liquid level in the target drainage area before the sewage pump is turned on;

[0174] When the ratio of the second difference to the number of sewage pumps in the turned-on state is less than a fourth preset threshold, performing a fault detection on the sewage pump to determine whether a fault occurs;

[0175] When a failure of the sewage pump is detected, the configuration information of the sewage pump is updated to increase the number of failures of the sewage pump by 1, and a second prompt message is generated to be sent to a user device, wherein the second prompt message includes identification information of the sewage pump.

[0176] Therefore, when the liquid level in the target drainage area drops, the sewage discharge capacity of the turned-on sewage pump is tested. When the turning-on time of the sewage pump reaches the second preset time, if the ratio of the corresponding second difference to the number of turned-on sewage pumps is less than the fourth preset threshold, it indicates that the current liquid level is smaller than the initial liquid level, and the sewage pump has not played a good role in sewage discharge. The sewage pump is very likely to fail. At this time, the sewage pump can be targeted for fault detection. When a fault is detected in the sewage pump, the configuration information of the sewage pump is updated in time. In this way, the configuration score of the sewage pump that has failed can be adjusted to provide a reference for the allocation of the next sewage discharge work.

[0177] The present application does not limit the second preset time length and the fourth preset threshold value. The second preset time length is, for example, 10 minutes, 30 minutes or 60 minutes, and the fourth preset threshold value is, for example, 1 cm / unit, 2 cm / unit or 3 cm / unit.

[0178] The second prompt information may be prompt information in the form of text, image, video or voice.

[0179] In some optional embodiments, the performing fault detection on the sewage pump to determine whether a fault occurs includes:

[0180] Acquire measurement data of a plurality of operating parameters of the sewage pump, the plurality of operating parameters comprising at least two of a current parameter, a voltage parameter, a temperature parameter, a vibration parameter, and a speed parameter;

[0181] Respectively detecting whether the measurement data of each of the operating parameters is within its corresponding preset range;

[0182] When it is detected that the measurement data of at least one of the operating parameters is not within the preset range corresponding to itself, the measurement data of multiple operating parameters are used as the first input of the fault detection model, and the predicted fault type and predicted similarity corresponding to the first input are output through the fault detection model; wherein the fault detection model is used to compare the first input with each fault data in the fault database respectively, obtain the similarity between the first input and each fault data, use the highest similarity among the multiple similarities corresponding to the first input as the predicted similarity corresponding to the first input, use the fault type of the fault data with the highest similarity to the first input as the predicted fault type corresponding to the first input, and output the predicted fault type and predicted similarity corresponding to the first input;

[0183] When the predicted similarity corresponding to the first input is less than a preset similarity threshold, it is determined that no fault has occurred; when the predicted similarity corresponding to the first input is not less than the preset similarity threshold, it is determined that a fault has occurred.

[0184] Therefore, a two-stage detection process is used to determine whether a fault has occurred. When the first stage detects a possible fault, it is not directly determined to be a fault, but enters the second stage of fault detection. When the second stage also detects a possible fault, it is determined that the sewage pump has a fault. Therefore, the obtained fault detection result has high credibility, avoiding frequent misjudgments that affect the normal use of the sewage pump.

[0185] Specifically, in the first stage, multiple sensors are used to obtain measurement data of multiple operating parameters, and each operating parameter's measurement data is detected to see if it is within its corresponding preset range. When one or more operating parameter's measurement data exceeds its corresponding preset range, it indicates that the sewage pump may have a fault, and the second stage is entered. In the second stage, the measurement data of multiple operating parameters are input into the fault detection model, and the fault detection model is used to determine the closest fault type of the sewage pump during the current operation as the predicted fault type. The fault detection model also gives the similarity between the input data and the predicted fault type as the predicted similarity, and determines whether a fault has occurred by comparing the predicted similarity with the preset similarity threshold. Obviously, the higher the similarity, the more likely the sewage pump has a fault corresponding to the predicted fault type.

[0186] In addition, the measurement data of multiple operating parameters are used as the input data of the fault detection model. The correlation between multiple operating parameters is taken into consideration, and a comprehensive judgment is made on the measurement data of multiple operating parameters to avoid misjudgment caused by the numerical fluctuation of a single operating parameter. Instead, multiple operating parameters are taken as a whole and compared one by one with the multiple fault data pre-stored in the fault database to find the fault data with the highest similarity, and the fault type corresponding to the fault data is used as the predicted fault type, which further improves the accuracy of the fault detection results.

[0187] The present application does not limit the number “at least two”, which can be 2, 3 or 5.

[0188] In one embodiment, there are 100 kinds of fault data in the fault database, each kind of fault data has a corresponding fault type, and the fault type can be identified by one or more of letters, numbers, Chinese characters and special symbols, for example, it can be expressed as "E4", "abnormal speed", etc. The fault detection model compares the first input with the 100 kinds of fault data respectively, and obtains 100 similarities, for example: 30%, 60%, ..., 98%, ..., 74%, 88%, and takes the highest similarity of 98% as the predicted similarity, and the fault type of the fault data corresponding to the 98% similarity is taken as the predicted fault type.

[0189] The present application does not limit the selection of the preset similarity threshold. In some embodiments, the preset similarity threshold is, for example, 90%, 95% or 99%.

[0190] In some optional embodiments, the process of obtaining the preset range corresponding to each operating parameter is as follows:

[0191] For each of the operating parameters, when the sewage pump is in a normal operating state, respectively record the measurement data of the operating parameter at a plurality of preset moments;

[0192] Calculating an average value using the measurement data of the operating parameter at multiple preset moments;

[0193] A preset range including the average value is obtained, and the ratio of the difference between the maximum value and the minimum value of the preset range and the average value is a preset constant corresponding to the operating parameter.

[0194] The present application does not limit the selection of multiple preset moments. In one embodiment, the multiple preset moments are, for example, multiple preset moments at intervals of 5 minutes.

[0195] The preset constants corresponding to each operating parameter may be the same or different. In one embodiment, the preset constants corresponding to the current parameter, the voltage parameter, the temperature parameter, the vibration parameter and the speed parameter may all be 10%.

[0196] Therefore, when the sewage pump is in normal operation, the measurement data at multiple preset moments are recorded and the average value is calculated. The average value obtained can be used as a reference value of the operating parameter during normal operation. On this basis, an appropriate fluctuation range is set to obtain a preset range containing the average value. The obtained preset range has a high reference value. The values ​​of different operating parameters vary greatly and may not be of the same order of magnitude. Therefore, the same or different preset constants are set for each operating parameter, and the ratio of the difference between the maximum value and the minimum value of the preset range to the average value is set as the preset constant corresponding to the operating parameter. In this way, the fluctuation range of different operating parameters is limited. The obtained preset range is accurate and reasonable, and more in line with the needs of practical applications.

[0197] In some optional embodiments, the training process of the fault detection model is as follows:

[0198] Acquire a second training set, where each second training data in the second training set includes sample data of a plurality of operating parameters and their corresponding labeled fault types and labeled similarities, and the sample data is obtained by actual measurement or generated by using a generation network of a GAN model;

[0199] For each of the second training data, sample data of multiple operating parameters in the second training data are used as the second input of the preset second deep learning model, and the predicted fault type and predicted similarity corresponding to the second input are output through the preset second deep learning model; wherein the preset second deep learning model is used to compare the second input with each fault data in the fault database respectively, obtain the similarity between the second input and each fault data, use the highest similarity among the multiple similarities corresponding to the second input as the predicted similarity corresponding to the second input, use the fault type of the fault data with the highest similarity to the second input as the predicted fault type corresponding to the second input, and output the predicted fault type and predicted similarity corresponding to the second input;

[0200] Based on the predicted fault type and predicted similarity corresponding to the second input and the labeled fault type and labeled similarity corresponding to the second input, updating the model parameters of the preset second deep learning model;

[0201] Check whether the preset second training end condition is met. If yes, stop the training and use the preset second deep learning model obtained by training as the fault detection model. If not, continue to train the preset second deep learning model using the next second training data.

[0202] Among them, the GAN model is a Generative Adversarial Network, which consists of a generator network and a discriminator network. The generator network randomly samples from the latent space as input, and its output needs to imitate the real samples in the second training set as much as possible. The input of the discriminator network is the real sample or the output of the generator network. Its purpose is to distinguish the output of the generator network from the real sample as much as possible. The generator network should deceive the discriminator network as much as possible. The two networks confront each other and constantly adjust the parameters. The ultimate goal is to make the discriminator network unable to determine whether the output of the generator network is true. The GAN model can generate sample data of multiple operating parameters for the training process of the fault detection model, which can effectively reduce the amount of original data collection and greatly reduce the cost of data collection and annotation.

[0203] The preset second training end condition can be set according to actual needs, and the present application does not make any limitation on it. In one embodiment, the preset second training end condition can be reaching a preset number of training times.

[0204] Thus, the second training set is used to train the preset second deep learning model to obtain a fault detection model. The fault detection model can be trained by a large amount of second training data, and can predict corresponding fault detection results for a variety of input data. It has a wide range of applications and a high level of intelligence. By designing, establishing an appropriate amount of neuron computing nodes and a multi-layer operation hierarchy, and selecting a suitable input layer and output layer, the preset second deep learning model can be obtained. Through the learning and tuning of the preset second deep learning model, a functional relationship from input to output is established. Although the functional relationship between input and output cannot be found 100%, it can be as close to the actual correlation as possible. The fault detection model obtained by training can realize the self-diagnosis function of fault detection, and the diagnostic result is highly reliable.

[0205] In one embodiment, the fault detection model is trained using a preset second deep learning model. In another embodiment, the fault detection model may be trained using a preset machine learning model. In yet another embodiment, the fault detection model may be optimized using a preset linear regression model.

[0206] In some optional embodiments, the method may further include:

[0207] For each sewage pump that is not turned on, perform the following processing:

[0208] When the time from the last time the sewage pump ended running is not less than the third preset time, controlling the sewage pump to run and the running time is not less than the fourth preset time, so as to perform fault detection on the sewage pump to determine whether a fault occurs;

[0209] When a failure of the sewage pump is detected, the configuration information of the sewage pump is updated to increase the number of failures of the sewage pump by 1, and third prompt information is generated and sent to the user device, wherein the third prompt information includes identification information of the sewage pump.

[0210] Therefore, regular fault detection is necessary for sewage pumps that have not been operated for a long time. Through regular fault detection, the aging of the equipment can be checked to avoid sudden failure of the sewage pump during subsequent operation. When the sewage pump has been running for no less than the third preset time since it last ended, the sewage pump is allowed to run and the running time is no less than the fourth preset time, so that the sewage pump is fault-detected during its operation. When a fault is detected in the sewage pump, the configuration information of the sewage pump is updated in time. In this way, the configuration score of the sewage pump that has failed can be adjusted to provide a reference for the allocation of the next sewage work.

[0211] See also Figure 2 , Figure 2 It is a structural block diagram of a sewage treatment system provided in an embodiment of the present application.

[0212] The sewage treatment system includes a liquid level sensor 30 , a control cabinet 40 , a first sewage pump 10 and a second sewage pump 20 .

[0213] The first sewage pump 10 and the second sewage pump 20 are turned on and off by the control cabinet 40, and the control cabinet 40 includes a PLC 41 (Programmable Logic Controller), a voltage transmitter 42 and a current transmitter 43. The specific process is as follows:

[0214] The liquid level of the sump is measured in real time by the liquid level sensor 30. When the liquid level of the sump exceeds a set first liquid level (for example, 2 cm), the first sewage pump 10 is started;

[0215] When the liquid level in the sump continues to rise and exceeds a set second liquid level (e.g., 5 cm), the second sewage pump 20 is started;

[0216] When the liquid level in the sump drops below the second liquid level (e.g., 5 cm), the first sewage pump 10 stops working;

[0217] When the liquid level in the sump continues to drop and is lower than the first liquid level (eg, 2 cm), the second sewage pump 20 stops working.

[0218] Next time when the pump start condition is met, the second sewage pump 20 is started first, and then the first sewage pump 10 is started; similarly, next time when the pump stop condition is met, the second sewage pump 20 is stopped first, and then the first sewage pump 10 is stopped, and so on.

[0219] During the operation of each sewage pump, the current transmitter and voltage transmitter are used to monitor the operating data of the sewage pump in real time. When the collected data matches the preset fault data, PLC41 automatically issues a fault diagnosis report.

[0220] When the first sewage pump 10 or the second sewage pump 20 has not been started for a long time, it will automatically run for 5 seconds. If fault data occurs, the PLC 41 will automatically alarm and notify the operation and maintenance personnel.

[0221] Therefore, on the one hand, it can ensure that each sewage pump can be rotated to run and ensure the same running time; on the other hand, it can run automatically and regularly to perform fault diagnosis on the operating current and voltage.

[0222] See also Figure 3 , Figure 3 It is a structural block diagram of a control device for a sewage pump provided in an embodiment of the present application.

[0223] The device is used to control the opening and closing of N sewage pumps corresponding to the target drainage area. Its specific implementation method is consistent with the implementation method and the technical effect achieved in the embodiment of the above-mentioned control method, and some contents will not be repeated here.

[0224] The device comprises:

[0225] The configuration acquisition module 101 is used to acquire the configuration score of each sewage pump based on the configuration information of each sewage pump, wherein the configuration information includes the performance score, the number of maintenance times, the number of failures and the remaining service life;

[0226] A liquid level measurement module 102, used to measure the liquid level of the target drainage area in real time using a liquid level sensor;

[0227] The start control module 103 is used to obtain the corresponding start strategies of N sewage pumps based on the liquid level rise and the configuration scores of all sewage pumps when it is detected that the liquid level in the target drainage area rises and the liquid level rise within the first preset time is greater than the first preset threshold, so as to start the k sewage pumps with the highest configuration scores;

[0228] The shutdown control module 104 is used to obtain the corresponding shutdown strategies of N sewage pumps based on the liquid level drop and the configuration scores of all sewage pumps when it is detected that the liquid level in the target drainage area drops and the liquid level drop within the first preset time period is greater than the second preset threshold, so as to shut down the g sewage pumps with the lowest configuration scores;

[0229] Wherein, N is an integer greater than 1, and k and g are positive integers not greater than N.

[0230] In some optional embodiments, the configuration acquisition module 101 is used to: input the configuration information of each sewage pump into a configuration evaluation model to obtain a configuration score corresponding to each sewage pump;

[0231] The training process of the configuration evaluation model includes:

[0232] Acquire a first and a second training set, wherein the first and the second training set include a plurality of first and second training data, each of the first and the second training data includes configuration information of a sample sewage pump and labeled data of a configuration score of the sample sewage pump;

[0233] For each first and second training data in the first and second training sets, the following processing is performed:

[0234] Inputting the configuration information of the sample sewage pump in the first and second training data into the preset first and second deep learning models to obtain prediction data of the configuration score of the sample sewage pump;

[0235] Based on the predicted data and the labeled data of the configuration score of the sample sewage pump, the model parameters of the first and second deep learning models are updated;

[0236] Detect whether the preset first and second training end conditions are met; if yes, use the trained first and second deep learning models as the configuration evaluation model; if not, continue to train the first and second deep learning models using the next first and second training data.

[0237] In some optional embodiments, the configuration acquisition module 101 includes:

[0238] A weight acquisition unit, used to acquire a first weight corresponding to the performance score, a second weight corresponding to the number of maintenance times, a third weight corresponding to the number of failures, and a fourth weight corresponding to the remaining service life;

[0239] A score calculation unit is used to calculate the configuration score of each sewage pump based on the performance score of each sewage pump and the first weight, the number of overhauls of each sewage pump and the second weight, the number of failures of each sewage pump and the third weight, and the remaining service life of each sewage pump and the fourth weight.

[0240] In some optional embodiments, the device further comprises:

[0241] The first fault detection module is used for:

[0242] When the liquid level in the target drainage area is detected to rise, the following processing is performed for each sewage pump that is turned on:

[0243] When the opening time of the sewage pump reaches a second preset time, obtaining a first difference between the current liquid level and the initial liquid level of the target drainage area, wherein the initial liquid level is the liquid level of the target drainage area before the sewage pump is turned on;

[0244] When the ratio of the first difference to the number of sewage pumps in the turned-on state is greater than a third preset threshold, performing a fault detection on the sewage pump to determine whether a fault occurs;

[0245] When a failure of the sewage pump is detected, the configuration information of the sewage pump is updated to increase the number of failures of the sewage pump by 1, and first prompt information is generated and sent to a user device, wherein the first prompt information includes identification information of the sewage pump.

[0246] In some optional embodiments, the device further comprises:

[0247] The second fault detection module is used for:

[0248] When it is detected that the liquid level in the target drainage area drops, the following processing is performed for each sewage pump that is turned on:

[0249] When the opening time of the sewage pump reaches a second preset time, obtaining a second difference between an initial liquid level and a current liquid level in the target drainage area, wherein the initial liquid level is the liquid level in the target drainage area before the sewage pump is turned on;

[0250] When the ratio of the second difference to the number of sewage pumps in the turned-on state is less than a fourth preset threshold, performing a fault detection on the sewage pump to determine whether a fault occurs;

[0251] When a failure of the sewage pump is detected, the configuration information of the sewage pump is updated to increase the number of failures of the sewage pump by 1, and a second prompt message is generated to be sent to a user device, wherein the second prompt message includes identification information of the sewage pump.

[0252] In some optional embodiments, the process of performing fault detection on the sewage pump includes:

[0253] Acquire measurement data of a plurality of operating parameters of the sewage pump, the plurality of operating parameters comprising at least two of a current parameter, a voltage parameter, a temperature parameter, a vibration parameter, and a speed parameter;

[0254] Respectively detecting whether the measurement data of each of the operating parameters is within its corresponding preset range;

[0255] When it is detected that the measurement data of at least one of the operating parameters is not within the preset range corresponding to itself, the measurement data of multiple operating parameters are used as the first input of the fault detection model, and the predicted fault type and predicted similarity corresponding to the first input are output through the fault detection model; wherein the fault detection model is used to compare the first input with each fault data in the fault database respectively, obtain the similarity between the first input and each fault data, use the highest similarity among the multiple similarities corresponding to the first input as the predicted similarity corresponding to the first input, use the fault type of the fault data with the highest similarity to the first input as the predicted fault type corresponding to the first input, and output the predicted fault type and predicted similarity corresponding to the first input;

[0256] When the predicted similarity corresponding to the first input is less than a preset similarity threshold, it is determined that no fault has occurred; when the predicted similarity corresponding to the first input is not less than the preset similarity threshold, it is determined that a fault has occurred.

[0257] In some optional embodiments, the device further comprises:

[0258] The third fault detection module is used for:

[0259] For each sewage pump that is not turned on, perform the following processing:

[0260] When the time from the last time the sewage pump ended running is not less than the third preset time, controlling the sewage pump to run and the running time is not less than the fourth preset time, so as to perform fault detection on the sewage pump to determine whether a fault occurs;

[0261] When a failure of the sewage pump is detected, the configuration information of the sewage pump is updated to increase the number of failures of the sewage pump by 1, and third prompt information is generated and sent to the user device, wherein the third prompt information includes identification information of the sewage pump.

[0262] See also Figure 4 The embodiment of the present application further provides an electronic device 200, which includes at least one memory 210, at least one processor 220, and a bus 230 connecting different platform systems.

[0263] The memory 210 may include a readable medium in the form of a volatile memory, such as a random access memory (RAM) 211 and / or a cache memory 212 , and may further include a read only memory (ROM) 213 .

[0264] Among them, the memory 210 also stores a computer program, which can be executed by the processor 220, so that the processor 220 executes the steps of the control method in the embodiment of the present application. Its specific implementation method is consistent with the implementation method and the technical effect achieved recorded in the embodiment of the above-mentioned control method, and some contents will not be repeated here.

[0265] The memory 210 may also include a utility 214 having at least one program module 215, such program module 215 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0266] Accordingly, the processor 220 may execute the above-mentioned computer program and may execute the utility 214 .

[0267] Bus 230 may represent one or more of several types of bus structures, including a memory bus or memory control method, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures.

[0268] The electronic device 200 may also communicate with one or more external devices 240 such as keyboards, pointing devices, Bluetooth devices, etc., and may also communicate with one or more devices that can interact with the electronic device 200, and / or communicate with any device (such as a router, a modem, etc.) that enables the electronic device 200 to communicate with one or more other computing devices. Such communication may be performed through the input and output interface 250. In addition, the electronic device 200 may also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN) and / or a public network, such as the Internet) through a network adapter 260. The network adapter 260 may communicate with other modules of the electronic device 200 through the bus 230. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 200, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage platforms.

[0269] The embodiment of the present application also provides a computer-readable storage medium, which is used to store a computer program. When the computer program is executed, the steps of the control method in the embodiment of the present application are implemented. The specific implementation method is consistent with the implementation method and the technical effect achieved in the embodiment of the above-mentioned control method, and some contents will not be repeated here.

[0270] Figure 5The program product 300 provided in this embodiment for implementing the above control method is shown, which can adopt a portable compact disk read-only memory (CD-ROM) and include program code, and can be run on a terminal device, such as a personal computer. However, the program product 300 of the present invention is not limited to this. In the present application, the readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it. The program product 300 can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of readable storage media (non-exhaustive list) include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0271] Computer-readable storage media may include data signals propagated in baseband or as part of a carrier wave, wherein readable program codes are carried. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The readable storage medium may also be any readable medium, which may send, propagate, or transmit a program for use by an instruction execution system, an apparatus, or a device or for use in combination with the program. The program code contained on the readable storage medium may be transmitted with any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the above. The program code for performing the operation of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and also conventional procedural programming languages ​​such as C language or similar programming languages. The program code may be executed entirely on a user computing device, partially on a user device, as an independent software package, partially on a user computing device, partially on a remote computing device, or entirely on a remote computing device or server. Where a remote computing device is involved, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0272] The terms "first", "second", "third", "fourth", "fifth", "sixth", "seventh", "eighth", "ninth", etc. (if any) in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "corresponding to" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0273] This application is explained from the perspectives of purpose of use, effectiveness, progress and novelty, and has met the functional enhancement and usage requirements emphasized by the Patent Law. The above description and drawings of this application are only the preferred embodiments of this application, and are not intended to limit this application. Therefore, all structures, devices, features, etc. that are similar or identical to this application, that is, all equivalent replacements or modifications made in accordance with the scope of the patent application of this application, should fall within the scope of protection of the patent application of this application.

Claims

1. A method for controlling a sewage pump, characterized in that: For controlling the opening and closing of N sewage pumps corresponding to the target drainage area, the method comprises: Based on the configuration information of each of the sewage pumps, a configuration score of each of the sewage pumps is obtained, wherein the configuration information includes a performance score, a number of overhauls, a number of failures, and a remaining service life; Using a liquid level sensor to measure the liquid level of the target drainage area in real time; When it is detected that the liquid level in the target drainage area rises and the amount of liquid level rise within a first preset time period is greater than a first preset threshold, based on the amount of liquid level rise and the configuration scores of all sewage pumps, the corresponding start-up strategies of N sewage pumps are obtained, so that the k sewage pumps with the highest configuration scores are turned on; When it is detected that the liquid level in the target drainage area drops and the amount of the liquid level drop within the first preset time period is greater than a second preset threshold, based on the amount of the liquid level drop and the configuration scores of all sewage pumps, the corresponding shutdown strategies of the N sewage pumps are obtained, so that the g sewage pumps with the lowest configuration scores are shut down; Wherein, N is an integer greater than 1, and k and g are positive integers not greater than N; When the liquid level in the target drainage area is detected to rise, the following processing is performed for each sewage pump that is turned on: When the opening time of the sewage pump reaches a second preset time, obtaining a first difference between the current liquid level and the initial liquid level of the target drainage area, wherein the initial liquid level is the liquid level of the target drainage area before the sewage pump is turned on; When the ratio of the first difference to the number of sewage pumps in the turned-on state is greater than a third preset threshold, performing a fault detection on the sewage pump to determine whether a fault occurs; When a failure of the sewage pump is detected, the configuration information of the sewage pump is updated to increase the number of failures of the sewage pump by 1, and first prompt information is generated and sent to a user device, wherein the first prompt information includes identification information of the sewage pump.

2. The control method according to claim 1, characterized in that: The obtaining of a configuration score of each sewage pump based on the configuration information of each sewage pump comprises: Inputting the configuration information of each sewage pump into the configuration evaluation model to obtain a configuration score corresponding to each sewage pump; The training process of the configuration evaluation model includes: Obtain a first training set, where the first training set includes a plurality of first training data, each of the first training data includes configuration information of a sample sewage pump and labeled data of a configuration score of the sample sewage pump; For each first training data in the first training set, perform the following processing: Inputting the configuration information of the sample sewage pump in the first training data into a preset first deep learning model to obtain prediction data of the configuration score of the sample sewage pump; Based on the predicted data and the labeled data of the configuration score of the sample sewage pump, updating the model parameters of the first deep learning model; Detect whether a preset first training end condition is met; if so, use the trained first deep learning model as the configuration evaluation model; if not, continue to train the first deep learning model using the next first training data.

3. The control method according to claim 1, characterized in that: The obtaining of a configuration score of each sewage pump based on the configuration information of each sewage pump comprises: Obtaining a first weight corresponding to the performance score, a second weight corresponding to the number of maintenance times, a third weight corresponding to the number of failures, and a fourth weight corresponding to the remaining service life; The configuration score of each sewage pump is calculated based on the performance score of each sewage pump and the first weight, the number of overhauls of each sewage pump and the second weight, the number of failures of each sewage pump and the third weight, and the remaining service life of each sewage pump and the fourth weight.

4. The control method according to claim 1, characterized in that: The method further comprises: When it is detected that the liquid level in the target drainage area drops, the following processing is performed for each sewage pump that is turned on: When the opening time of the sewage pump reaches a second preset time, obtaining a second difference between an initial liquid level and a current liquid level in the target drainage area, wherein the initial liquid level is the liquid level in the target drainage area before the sewage pump is turned on; When the ratio of the second difference to the number of sewage pumps in the turned-on state is less than a fourth preset threshold, performing a fault detection on the sewage pump to determine whether a fault occurs; When a failure of the sewage pump is detected, the configuration information of the sewage pump is updated to increase the number of failures of the sewage pump by 1, and a second prompt message is generated to be sent to a user device, wherein the second prompt message includes identification information of the sewage pump.

5. The control method according to claim 1 or 4, characterized in that: The performing fault detection on the sewage pump to determine whether a fault occurs includes: Acquire measurement data of a plurality of operating parameters of the sewage pump, the plurality of operating parameters comprising at least two of a current parameter, a voltage parameter, a temperature parameter, a vibration parameter, and a speed parameter; Respectively detecting whether the measurement data of each of the operating parameters is within its corresponding preset range; When it is detected that the measurement data of at least one of the operating parameters is not within the preset range corresponding to itself, the measurement data of multiple operating parameters are used as the first input of the fault detection model, and the predicted fault type and predicted similarity corresponding to the first input are output through the fault detection model; wherein the fault detection model is used to compare the first input with each fault data in the fault database respectively, obtain the similarity between the first input and each fault data, use the highest similarity among the multiple similarities corresponding to the first input as the predicted similarity corresponding to the first input, use the fault type of the fault data with the highest similarity to the first input as the predicted fault type corresponding to the first input, and output the predicted fault type and predicted similarity corresponding to the first input; When the predicted similarity corresponding to the first input is less than a preset similarity threshold, it is determined that no fault has occurred; when the predicted similarity corresponding to the first input is not less than the preset similarity threshold, it is determined that a fault has occurred.

6. The control method according to claim 5, characterized in that: The method further comprises: For each sewage pump that is not turned on, perform the following processing: When the time from the last time the sewage pump ended running is not less than the third preset time, controlling the sewage pump to run and the running time is not less than the fourth preset time, so as to perform fault detection on the sewage pump to determine whether a fault occurs; When a failure of the sewage pump is detected, the configuration information of the sewage pump is updated to increase the number of failures of the sewage pump by 1, and third prompt information is generated and sent to the user device, wherein the third prompt information includes identification information of the sewage pump.

7. A control device for a sewage pump, characterized in that: Used to control the opening and closing of N sewage pumps corresponding to the target drainage area, the device includes: A configuration acquisition module, for acquiring a configuration score of each sewage pump based on the configuration information of each sewage pump, wherein the configuration information includes a performance score, a number of overhauls, a number of failures, and a remaining service life; A liquid level measurement module, used to measure the liquid level of the target drainage area in real time using a liquid level sensor; An opening control module is used to obtain corresponding opening strategies of N sewage pumps based on the amount of liquid level rise and the configuration scores of all sewage pumps when it is detected that the liquid level in the target drainage area rises and the amount of liquid level rise within a first preset time period is greater than a first preset threshold, so as to turn on the k sewage pumps with the highest configuration scores; A shutdown control module, configured to, when it is detected that the liquid level in the target drainage area drops and the amount of the liquid level drop within the first preset time period is greater than a second preset threshold, obtain the corresponding shutdown strategies of the N sewage pumps based on the amount of the liquid level drop and the configuration scores of all sewage pumps, so as to shut down the g sewage pumps with the lowest configuration scores; Wherein, N is an integer greater than 1, and k and g are positive integers not greater than N; The first fault detection module is used to perform the following processing for each sewage pump that is turned on when the liquid level in the target drainage area is detected to rise: When the opening time of the sewage pump reaches a second preset time, obtaining a first difference between the current liquid level and the initial liquid level of the target drainage area, wherein the initial liquid level is the liquid level of the target drainage area before the sewage pump is turned on; When the ratio of the first difference to the number of sewage pumps in the turned-on state is greater than a third preset threshold, performing a fault detection on the sewage pump to determine whether a fault occurs; When a failure of the sewage pump is detected, the configuration information of the sewage pump is updated to increase the number of failures of the sewage pump by 1, and first prompt information is generated and sent to a user device, wherein the first prompt information includes identification information of the sewage pump.

8. An electronic device, characterized in that: The electronic device comprises a memory and a processor, the memory stores a computer program, and the processor implements the steps of the method according to any one of claims 1 to 6 when executing the computer program.

9. A computer-readable storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.