CN117451284B

CN117451284B - Container air tightness abnormality detection method, device, electronic equipment and storage medium

Info

Publication number: CN117451284B
Application number: CN202311800568.7A
Authority: CN
Inventors: 靖志成; 晋文静; 韩误存; 谢国涛; 程涛; 胡瑞祥; 金艾明; 张坤
Original assignee: Contemporary Amperex Technology Co Ltd
Current assignee: Contemporary Amperex Technology Co Ltd
Priority date: 2023-12-26
Filing date: 2023-12-26
Publication date: 2024-04-12
Anticipated expiration: 2043-12-26
Also published as: CN117451284A

Abstract

The application discloses a container air tightness abnormality detection method, a device, electronic equipment and a storage medium. Wherein the method comprises the following steps: acquiring pressure parameters corresponding to working conditions of the current container in the operation process; the pressure parameters corresponding to the working conditions comprise the pressure parameters in the current container; preprocessing the pressure parameters corresponding to the working conditions to obtain preprocessed characteristic data, inputting the preprocessed characteristic data into a pre-training fault prediction model, and obtaining fault types corresponding to the pressure parameters; and outputting the fault type and the maintenance scheme corresponding to the fault type. According to the embodiment of the application, the accuracy of detecting the abnormal air tightness of the container can be improved.

Description

Container air tightness abnormality detection method, device, electronic equipment and storage medium

Technical Field

The application relates to the technical field of air tightness detection, in particular to a method and a device for detecting abnormal air tightness of a container, electronic equipment and a storage medium.

Background

The stirring tank body is a container for stirring and mixing slurry, and the tank body needs to be vacuumized in the stirring process so as to remove air in the tank body and avoid the influence of bubbles in the slurry on the quality of processed products. Because pipeline, valve body, sealing washer etc. of the agitator tank body can take place to block up or wearing and tearing, and then can influence the gas tightness of the tank body, still can cause the tank body vacuum unusual when serious, and then lead to tank body equipment to report to the police and shut down, influence the quality of the product through thick liquids production, it is very important to detect whether the gas tightness of the agitator tank body appears unusual.

Currently, in the related art, whether the air tightness of a valve body of a container is qualified is judged mainly through pointer change of an air pressure display of the container, or the air tightness of the container is detected by installing equipment such as a differential pressure sensor, an air quantity monitoring device and the like and then comparing a difference value between measured values of air inlet and outlet with a threshold value through calculation; however, the stirring tank body has a large volume and complex process, and is in a state of frequent vacuumizing and vacuum release, and whether the air tightness of the stirring tank body is abnormal or not is monitored only by a sensor and other instruments, so that the abnormal detection accuracy of the air tightness of the stirring tank body is lower.

The statements are to be understood as merely provide background information related to the present application and may not necessarily constitute prior art.

Disclosure of Invention

In view of the above problems, the present application provides a method, an apparatus, an electronic device, and a storage medium for detecting abnormal tightness of a container, which can solve the technical problem of low accuracy in detecting abnormal tightness of a container in the related art.

In a first aspect, the present application provides a method for detecting abnormal tightness of a container, including: acquiring pressure parameters corresponding to working conditions of the current container in the operation process; the pressure parameters corresponding to the working conditions comprise the pressure parameters in the current container; preprocessing the pressure parameters corresponding to the working conditions to obtain preprocessed characteristic data, inputting the preprocessed characteristic data into a pre-training fault prediction model, and obtaining fault types corresponding to the pressure parameters; and outputting the fault type and the maintenance scheme corresponding to the fault type.

According to the technical scheme provided by the embodiment of the invention, the pressure parameters corresponding to various working conditions of the container in the operation process are preprocessed, and then the failure type corresponding to the pressure parameters is predicted based on the preprocessing data by utilizing the pre-training failure prediction model, so that whether the air tightness of the container is abnormal can be accurately judged, the failure type of the air tightness and a maintenance scheme corresponding to the failure type can be provided, unexpected shutdown of production line equipment where the container is located is avoided, and the quality of products processed by the container is improved.

In some embodiments, the obtaining the pressure parameter corresponding to each working condition of the current container in the operation process includes: acquiring pressure parameters in the current container at a plurality of data acquisition moments; and determining the working condition of the pressure parameter corresponding to each data acquisition time. In this embodiment, by using the attribute of the pressure parameter in the plurality of data collection moments, the working condition of the pressure parameter corresponding to each data collection moment can be accurately determined, and whether the current container is abnormal or not can be accurately determined according to the working condition corresponding to each pressure parameter.

In some embodiments, the pressure parameters include a vacuum threshold, a preset upper and lower pressure limit for the current container, and an internal pressure value for the current container; the determining the working condition of the pressure parameter corresponding to each data acquisition time comprises the following steps: traversing a vacuumizing threshold state value, a discharging threshold state value, a preset pressure upper limit value, a preset pressure lower limit value and an internal pressure value corresponding to each data acquisition time; when the state value of the vacuumizing valve corresponding to the current collection time is a first value, the state value of the discharging valve is a second value, and the preset upper pressure limit value and the preset lower pressure limit value are both zero, and the internal pressure value is within a first preset range, determining that the working condition of the pressure parameter corresponding to the current collection time is a normal pressure working condition; the first value is used for indicating that the vacuumizing valve is in a closed state, and the second value is used for indicating that the vacuumizing valve is in an open state. In this embodiment, the working conditions of the pressure parameters corresponding to the data collection moments can be more accurately determined through the vacuumizing threshold state value, the emptying threshold state value, the preset upper pressure limit value and the preset lower pressure limit value of the current container and the internal pressure value of the current container.

In some embodiments, preprocessing the pressure parameters corresponding to the working conditions to obtain preprocessed feature data, inputting the preprocessed feature data into a pre-training fault prediction model, and obtaining a fault type corresponding to the pressure parameters includes: preprocessing each internal pressure value corresponding to the normal pressure working condition to obtain preprocessing characteristic data corresponding to the normal pressure working condition; the preprocessing characteristic data comprises at least one of a mean value, a standard deviation, a maximum value and a minimum value corresponding to each internal pressure value and a ratio between the number of positive numerical values and the number of negative numerical values in each internal pressure value; and inputting the preprocessing characteristic data into the pre-training fault prediction model to obtain the fault type corresponding to the pressure parameter of the normal pressure working condition. In the embodiment, the fault type corresponding to the pressure parameter of the normal pressure working condition can be accurately judged by acquiring the pretreatment characteristic data corresponding to the normal pressure working condition and based on the pretreatment characteristic data and the pre-training fault prediction model.

In some embodiments, the pressure parameters include an evacuation threshold state value, a venting threshold state value, preset upper and lower pressure limit values, and an internal pressure value of the current vessel; the determining the working condition of the pressure parameter corresponding to each data acquisition time comprises the following steps: traversing a vacuumizing threshold state value, a discharging threshold state value, a preset pressure upper limit value, a preset pressure lower limit value and an internal pressure value corresponding to each data acquisition time; determining a first starting time and a first ending time of a working condition of the current acquisition time according to the state values of the vacuumizing valve and the vacuumizing valve corresponding to the two adjacent acquisition times; when the vacuumizing valve state value corresponding to the current collection time is a second value, the vacuumizing valve state value is a first value, the preset pressure upper limit value and the pressure lower limit value are smaller than zero, the internal pressure value corresponding to the first starting time is in a first preset range, and the internal pressure value corresponding to the first ending time is in a second preset range, the working condition of the pressure parameter corresponding to the current collection time is determined to be a vacuumizing working condition; the second numerical value is used for indicating that the vacuumizing valve is in a closed state, and the first numerical value is used for indicating that the vacuumizing valve is in an open state. In this embodiment, the working conditions of the pressure parameters corresponding to the data collection moments can be more accurately determined through the vacuumizing threshold state value, the emptying threshold state value, the preset upper pressure limit value and the preset lower pressure limit value of the current container and the internal pressure value of the current container.

In some embodiments, preprocessing the pressure parameters corresponding to the working conditions to obtain preprocessed feature data, inputting the preprocessed feature data into a pre-training fault prediction model, and obtaining a fault type corresponding to the pressure parameters includes: preprocessing each internal pressure value corresponding to the pumping working condition to obtain preprocessing characteristic data corresponding to the pumping working condition, wherein the preprocessing characteristic data comprises at least one of the internal pressure values corresponding to the first starting time and the first ending time, the duration between the first starting time and the first ending time and the slope corresponding to each internal pressure value in an internal pressure value change curve in the duration; and inputting the preprocessing characteristic data into the pre-training fault prediction model, and obtaining the fault type corresponding to the pressure parameter of the pumping working condition.

In the embodiment, by acquiring the preprocessing feature data corresponding to the pumping working condition, the fault type corresponding to the pressure parameter of the pumping working condition can be accurately judged based on the preprocessing feature data and the pre-training fault prediction model.

In some embodiments, the pressure parameters include a vacuum threshold, preset upper and lower pressure values, and an internal pressure value of the current vessel; the determining the working condition of the pressure parameter corresponding to each data acquisition time comprises the following steps: traversing the vacuumizing valve state value, the emptying valve state value, the preset pressure upper limit value, the preset pressure lower limit value and the internal pressure value corresponding to each first data acquisition moment; the first data acquisition time is any data acquisition time except the data acquisition time corresponding to the pumping working condition in the data acquisition times; when the vacuumizing valve state value corresponding to the current collection time is a second value, the discharging valve state value is a first value, and the preset pressure upper limit value and the pressure lower limit value are smaller than zero, and the internal pressure value corresponding to the current collection time is in a third preset range, determining that the working condition to which the pressure parameter corresponding to the current collection time belongs is a pressure maintaining working condition; the third preset range is a pressure range determined based on the sum of the pressure upper limit values and the pressure lower limit value.

In this embodiment, the working conditions of the pressure parameters corresponding to the data collection moments can be more accurately determined through the vacuumizing threshold state value, the emptying threshold state value, the preset upper pressure limit value and the preset lower pressure limit value of the current container and the internal pressure value of the current container.

In some embodiments, preprocessing the pressure parameters corresponding to the working conditions to obtain preprocessed feature data, inputting the preprocessed feature data into a pre-training fault prediction model, and obtaining a fault type corresponding to the pressure parameters includes: preprocessing each internal pressure value corresponding to the pressure maintaining working condition to obtain preprocessing characteristic data corresponding to the pressure maintaining working condition, wherein the preprocessing characteristic data comprises at least one of a mean value, a standard deviation, a maximum value and a minimum value corresponding to each internal pressure value, a ratio of the number exceeding the upper pressure limit value to the number exceeding the lower pressure limit value in each internal pressure value and a maximum value of the change rate of each internal pressure value; and inputting the preprocessing characteristic data into the pre-training fault prediction model, and obtaining the fault type corresponding to the pressure parameter of the pressure maintaining working condition.

In the embodiment, the fault type corresponding to the pressure parameter of the pressure maintaining working condition can be accurately judged by acquiring the preprocessing characteristic data corresponding to the pressure maintaining working condition and based on the preprocessing characteristic data and the pre-training fault prediction model.

In some embodiments, the pressure parameters include an evacuation threshold state value, a venting threshold state value, preset upper and lower pressure limit values, and an internal pressure value of the current vessel; the determining the working condition of the pressure parameter corresponding to each data acquisition time comprises the following steps:

traversing a vacuumizing threshold state value, a discharging threshold state value, a preset pressure upper limit value and pressure lower limit value and an internal pressure value corresponding to the second data acquisition time; the second data acquisition time is any data acquisition time except the data acquisition time corresponding to the normal pressure working condition in the data acquisition times; determining a second starting time and a second ending time of the working condition of the current acquisition time according to the state values of the vacuumizing valve and the vacuumizing valve corresponding to the two adjacent acquisition times; when the vacuumizing valve state value corresponding to the current collection time is a first value, the vacuumizing valve state value is a second value, the preset pressure upper limit value and the pressure lower limit value are smaller than zero, the internal pressure value corresponding to the second starting time is in a fourth preset range, and the internal pressure value corresponding to the second ending time is in a fifth preset range, the working condition of the pressure parameter corresponding to the current collection time is determined to be a pressure releasing working condition; the first value is used for indicating that the vacuumizing valve is in a closed state, and the second value is used for indicating that the vacuumizing valve is in an open state. In this embodiment, the working condition to which the pressure parameter corresponding to each data collection time belongs may be more accurately determined by the current vacuum pumping threshold, the vacuum discharging threshold, the preset upper pressure limit and lower pressure limit of the container, and the internal pressure value of the current container.

In some embodiments, preprocessing the pressure parameters corresponding to the working conditions to obtain preprocessed feature data, inputting the preprocessed feature data into a pre-training fault prediction model, and obtaining a fault type corresponding to the pressure parameters includes: preprocessing each internal pressure value corresponding to the pressure release working condition to obtain preprocessing characteristic data corresponding to the pressure release working condition, wherein the preprocessing characteristic data comprises at least one of duration between the second starting time and the second ending time, the internal pressure value corresponding to the second starting time, the internal pressure value corresponding to the second ending time and the change rate of each internal pressure value in the duration; and inputting the preprocessing characteristic data into the pre-training fault prediction model, and obtaining the fault type corresponding to the pressure parameter of the pressure release working condition.

In the embodiment, by acquiring the preprocessing feature data corresponding to the pressure release working condition, the fault type corresponding to the pressure parameter of the pressure release working condition can be accurately judged based on the preprocessing feature data and the pre-training fault prediction model.

In some embodiments, the container gas tightness anomaly detection method further comprises: taking working condition parameters corresponding to each fault type as sample pressure parameters; and training the classification model by using the sample pressure parameters to obtain the pre-training fault prediction model. In this embodiment, by training the classification model using each failure type and the operating condition parameter corresponding to each failure type as a sample, a prediction model for accurately predicting whether the container is abnormal in airtightness can be obtained.

In a second aspect, an embodiment of the present invention provides a device for detecting abnormal tightness of a container, including: the acquisition unit is used for acquiring pressure parameters corresponding to working conditions of the current container in the operation process; the pressure parameters corresponding to the working conditions comprise the pressure parameters in the current container; the prediction unit is used for preprocessing the pressure parameters corresponding to the working conditions to obtain preprocessed characteristic data, inputting the preprocessed characteristic data into a pre-training fault prediction model, and obtaining fault types corresponding to the pressure parameters; and the output unit is used for outputting the fault type and the maintenance scheme corresponding to the fault type.

In a third aspect, an embodiment of the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the method according to the first aspect when executing the computer program.

In a fourth aspect, embodiments of the present invention provide a computer-readable storage medium storing a computer program which, when executed by a processor, implements a method according to the first aspect.

The foregoing description is only an overview of the technical solutions of the present application, and may be implemented according to the content of the specification in order to make the technical means of the present application more clearly understood, and in order to make the above-mentioned and other objects, features and advantages of the present application more clearly understood, the following detailed description of the present application will be given.

Drawings

Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the application. Also, like reference numerals are used to designate like parts throughout the accompanying drawings. In the drawings:

fig. 1 is a flowchart of a method for detecting abnormal tightness of a container according to an embodiment of the present application;

FIG. 2 is a graph showing the variation of pressure values of a container under different working conditions according to an embodiment of the present application;

FIG. 3 is a graph showing the variation of pressure values of a container under normal pressure conditions according to an embodiment of the present application;

FIG. 4 is a graph showing the variation of pressure values of a container under pumping conditions according to an embodiment of the present disclosure;

FIG. 5 is a graph showing the variation of pressure values of a container under a pressure maintaining condition according to an embodiment of the present disclosure;

FIG. 6 is a graph showing the variation of pressure values of a container under a pressure release condition according to an embodiment of the present disclosure;

FIG. 7 is a flowchart of another method for detecting abnormal tightness of a container according to an embodiment of the present disclosure;

FIG. 8 is a flowchart of another method for detecting abnormal tightness of a container according to an embodiment of the present disclosure;

FIG. 9 is a flowchart of another method for detecting abnormal tightness of a container according to an embodiment of the present application;

FIG. 10 is a flowchart of another method for detecting abnormal tightness of a container according to an embodiment of the present disclosure;

FIG. 11 is a flowchart of another method for detecting abnormal tightness of a container according to an embodiment of the present disclosure;

FIG. 12 is a flowchart of another method for detecting abnormal tightness of a container according to an embodiment of the present disclosure;

fig. 13 is a schematic structural view of a device for detecting abnormal tightness of a container according to an embodiment of the present application;

fig. 14 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed Description

Embodiments of the technical solutions of the present application will be described in detail below with reference to the accompanying drawings. The following examples are only for more clearly illustrating the technical solutions of the present application, and thus are only examples, and are not intended to limit the scope of protection of the present application.

Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "comprising" and "having" and any variations thereof in the description and claims of the present application and in the description of the figures above are intended to cover non-exclusive inclusions.

In the description of embodiments of the present invention, the technical terms "first," "second," and the like are used merely to distinguish between different objects and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated, a particular order or a primary or secondary relationship. In the description of the embodiments of the present invention, the meaning of "plurality" is two or more unless explicitly defined otherwise.

Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the present application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.

In the description of the embodiments of the present invention, the term "and/or" is merely an association relationship describing an association object, and indicates that three relationships may exist, for example, a and/or B may indicate: a exists alone, A and B exist together, and B exists alone. In addition, the character "/" herein generally indicates that the front and rear associated objects are an "or" relationship.

In the description of the embodiments of the present invention, the term "plurality" means two or more (including two), and similarly, "plural sets" means two or more (including two), and "plural sheets" means two or more (including two).

At present, in the field of battery processing, such as slurry required by a coating process in the production and manufacture of lithium batteries, the slurry needs to be uniformly mixed by a stirring tank body to be coated on the surface of a metal foil. The stirring tank body is used as a container for stirring and mixing the slurry, and the tank body needs to be vacuumized in the stirring process so as to remove air in the tank body, and avoid the influence of bubbles in the slurry on the quality of processed products. Because pipeline, valve body, sealing washer etc. of the agitator tank body can take place to block up or wearing and tearing, and then can influence the gas tightness of the agitator tank body, still can initiate tank body vacuum anomaly when serious, and then lead to tank body equipment to report to the police and shut down, influence the product quality of coating technology and lithium cell, it is very important to detect whether the gas tightness of the agitator tank body appears unusual.

Currently, in the related art, whether the air tightness of a valve body of a container is qualified is judged mainly through pointer change of an air pressure display of the container, or whether the air tightness of the container is detected by installing equipment such as a differential pressure sensor, an air quantity monitoring device and the like, and then comparing a difference value between measured values of air inlet and outlet with a threshold value through calculation; however, the stirring tank body has a large volume and complex process, and is in a state of frequent vacuumizing and vacuum release, and whether the air tightness of the stirring tank body is abnormal or not is monitored only by a sensor and other instruments, so that the abnormal detection accuracy of the air tightness of the stirring tank body is lower.

In order to improve the quality of a battery pack, a vehicle pack or other products requiring abnormal detection of the air tightness of a container, the air tightness of a stirring tank is generally required to be high.

In order to improve the abnormality detection accuracy of the air tightness of a container, the application designs a method for detecting the abnormality of the air tightness of the container, which comprises the following steps: acquiring pressure parameters corresponding to working conditions of the current container in the operation process; preprocessing the pressure parameters corresponding to the working conditions to obtain preprocessed characteristic data, inputting the preprocessed characteristic data into a pre-training fault prediction model, and obtaining fault types corresponding to the pressure parameters; and outputting the fault type and the maintenance scheme corresponding to the fault type.

According to the method, the pressure parameters corresponding to various working conditions of the container in the operation process are preprocessed, and then the pre-trained fault prediction model is utilized to predict the fault type corresponding to the pressure parameters based on the preprocessed data, so that whether the air tightness of the container is abnormal or not can be accurately judged, the fault type of the air tightness and a maintenance scheme corresponding to the fault type can be provided, accidental shutdown of production line equipment where the container is located is avoided, the quality of products processed through the container is improved, and the risk in the generation process is reduced.

The embodiment of the application is not limited to the application scenario listed above, and any other application scenario requiring air tightness detection can be used for detecting whether the air tightness of the production equipment or the closed space is abnormal according to the method provided by the embodiment of the application. The method not only can realize the improvement of the stability and the accuracy of the abnormal detection of the air tightness of the container and maximally meet the requirements of clients, but also has the advantages of small limitation, high universality and the like.

The following describes in detail, by way of specific examples, specific procedures of the container air tightness abnormality detection method of the present application. Referring to a flowchart of a method for detecting abnormal tightness of a container shown in fig. 1, the method specifically includes the following steps:

S101, acquiring pressure parameters corresponding to working conditions of the current container in the operation process; the pressure parameters corresponding to the working conditions comprise the pressure parameters in the current container;

s102, preprocessing the pressure parameters corresponding to the working conditions to obtain preprocessed characteristic data, inputting the preprocessed characteristic data into a pre-training fault prediction model, and obtaining fault types corresponding to the pressure parameters;

s103, outputting the fault type and the maintenance scheme corresponding to the fault type.

Specifically, in the embodiment of the present application, taking the current container as the stirring tank, as shown in table 1, the above pressure parameters include, but are not limited to, pressure parameters inside the stirring tank, such as an internal pressure value of the stirring tank, and a pressure lower limit value, a pressure upper limit value, a vacuumizing threshold value, and a vacuumizing threshold value. Here, the absolute value of the upper pressure limit value is larger than the absolute value of the upper pressure limit value. And determining the type of the working condition of each data acquisition moment according to the parameter value of the pressure parameter corresponding to each data acquisition moment. The method comprises the steps of selecting a pressure parameter as an internal pressure value of a current container, preprocessing the internal pressure values at a plurality of data acquisition moments, inputting preprocessing characteristic data into a pre-training fault prediction model, accurately acquiring a fault type corresponding to the pressure parameter, determining a maintenance scheme corresponding to the output fault type through a corresponding relation between the preset fault type and the maintenance scheme, and pushing the maintenance scheme to a user.

According to the method and the device, the pressure parameters corresponding to various working conditions of the container in the operation process are preprocessed, and then the pre-trained fault prediction model is utilized to predict the fault type corresponding to the pressure parameters based on the preprocessed data, so that whether the air tightness of the container is abnormal or not can be accurately judged, the fault type of the air tightness and a maintenance scheme corresponding to the fault type can be provided, accidental shutdown of production line equipment where the container is located is avoided, and quality of products processed through the container is improved.

TABLE 1

In one or more embodiments of the present application, the obtaining the pressure parameter corresponding to each working condition of the current container during the operation process includes: acquiring pressure parameters in the current container at a plurality of data acquisition moments; and determining the working condition of the pressure parameter corresponding to each data acquisition time.

Specifically, in the embodiment of the application, for example, a data collection period is 1 hour, and a 2 times data collection frequency per second is used, so that the pressure parameter inside the current container can be obtained 7200 times, in this embodiment of the application, the working conditions include a normal pressure working condition, a pumping working condition, a pressure maintaining working condition and a pressure releasing working condition, by using the judging conditions shown in table 2, the working condition of the 7200 times of data collection can be divided, as shown in fig. 2, after the working condition division, it is determined that the working condition to which the pressure parameter between the data collection time corresponding to the point a and the data collection time corresponding to the point B belongs is a normal pressure working condition, the working condition to which the pressure parameter between the data collection time corresponding to the point B and the data collection time corresponding to the point C belongs is a pumping working condition, the working condition to which the pressure parameter between the data collection time corresponding to the point C and the data collection time corresponding to the point D belongs to a pressure releasing working condition, and the working condition to which the pressure parameter between the data collection time corresponding to the point E belongs is a pressure releasing working condition, and the working condition to which the working condition corresponding to the point F belongs to the working condition.

TABLE 2

In the embodiment of the application, the working conditions of the pressure parameters corresponding to the data acquisition moments can be accurately judged through the attributes of the pressure parameters in the data acquisition moments, and whether the current container is abnormal or not can be accurately judged according to the working conditions corresponding to the pressure parameters.

In one or more embodiments of the present application, the pressure parameter includes a vacuum pumping threshold, a vacuum releasing threshold, a preset upper pressure limit and a preset lower pressure limit of the current container, and an internal pressure value of the current container; the determining the working condition of the pressure parameter corresponding to each data acquisition time comprises the following steps: traversing a vacuumizing threshold state value, a discharging threshold state value, a preset pressure upper limit value, a preset pressure lower limit value and an internal pressure value corresponding to each data acquisition time; when the state value of the vacuumizing valve corresponding to the current collection time is a first value, the state value of the discharging valve is a second value, and the preset upper pressure limit value and the preset lower pressure limit value are both zero, and the internal pressure value is within a first preset range, determining that the working condition of the pressure parameter corresponding to the current collection time is a normal pressure working condition; the first value is used for indicating that the vacuumizing valve is in a closed state, and the second value is used for indicating that the vacuumizing valve is in an open state.

Specifically, in the embodiment of the present application, for example, taking the current container internal pressure parameter obtained at 7200 data acquisition moments in a history period as an example, traversing the vacuumizing threshold state value, the preset upper pressure limit value and lower pressure limit value and the internal pressure value corresponding to each data acquisition moment; under the conditions that the state value of the vacuumizing valve corresponding to the current collection time is 0, the state value of the discharging valve is 1, the preset upper pressure limit value and the preset lower pressure limit value are both zero, and the internal pressure value is within +/-2 kPa, the working condition of the pressure parameter corresponding to the current collection time is determined to be a normal pressure working condition; as shown in fig. 3, the working conditions of the pressure parameters from the data acquisition time corresponding to the point a to the data acquisition time corresponding to the point B and the working conditions of the pressure parameters from the data acquisition time corresponding to the point E to the data acquisition time corresponding to the point F are all normal pressure working conditions, and the internal pressure values in the intervals are all kept between 0.4kPa and 1 kPa. It should be noted that, the value for indicating that the vacuumizing valve is in the closed state may be configured as 0, the value for indicating that the vacuumizing valve is in the open state may be configured as 1, and the configuration identifier may be configured as other values or characters, which is not limited in any way in the embodiment of the present application.

In the embodiment of the application, the working conditions of the pressure parameters corresponding to the data acquisition time can be more accurately judged through the vacuumizing valve state value, the emptying valve state value, the preset pressure upper limit value and pressure lower limit value of the current container and the internal pressure value of the current container.

In one or more embodiments of the present application, preprocessing the pressure parameter corresponding to each working condition to obtain preprocessed feature data, inputting the preprocessed feature data into a pre-training fault prediction model, and obtaining a fault type corresponding to the pressure parameter includes:

preprocessing each internal pressure value corresponding to the normal pressure working condition to obtain preprocessing characteristic data corresponding to the normal pressure working condition; the preprocessing characteristic data comprises at least one of a mean value, a standard deviation, a maximum value and a minimum value corresponding to each internal pressure value and a ratio between the number of positive numerical values and the number of negative numerical values in each internal pressure value; and inputting the preprocessing characteristic data into the pre-training fault prediction model to obtain the fault type corresponding to the pressure parameter of the normal pressure working condition.

Specifically, in this embodiment of the present application, for example, taking the current pressure parameter inside the container at 7200 data collection moments in a history period as an example, it is assumed that the pressure parameter corresponds to 1000 data collection moments under the normal pressure working condition, and then, the average value, standard deviation, maximum value and minimum value corresponding to each internal pressure value and the ratio between the number of positive values and the number of negative values in each internal pressure value are respectively calculated in the pressure parameters at 1000 data collection moments. And inputting the preprocessed data corresponding to the 1000 data acquisition moments into the pre-training fault prediction model, so that the fault type corresponding to the pressure parameter of the normal pressure working condition can be predicted.

In an example, the above-mentioned preprocessed data may also be compared with preprocessed data corresponding to the current container in the history detection period when the current container is operating normally under the normal pressure working condition, to determine whether an outlier exists in the preprocessed data corresponding to the 1000 data acquisition moments, and if the outlier exists, to determine that the pressure sensor of the current container is damaged.

In one or more embodiments of the present application, the pressure parameter includes a vacuum pumping threshold, a vacuum releasing threshold, a preset upper pressure limit and a preset lower pressure limit, and an internal pressure value of the current container; the determining the working condition of the pressure parameter corresponding to each data acquisition time comprises the following steps:

Traversing a vacuumizing threshold state value, a discharging threshold state value, a preset pressure upper limit value, a preset pressure lower limit value and an internal pressure value corresponding to each data acquisition time;

determining a first starting time and a first ending time of a working condition of the current acquisition time according to the state values of the vacuumizing valve and the vacuumizing valve corresponding to the two adjacent acquisition times;

when the vacuumizing valve state value corresponding to the current collection time is a second value, the vacuumizing valve state value is a first value, the preset pressure upper limit value and the pressure lower limit value are smaller than zero, the internal pressure value corresponding to the first starting time is in a first preset range, and the internal pressure value corresponding to the first ending time is in a second preset range, the working condition of the pressure parameter corresponding to the current collection time is determined to be a vacuumizing working condition; the second numerical value is used for indicating that the vacuumizing valve is in a closed state, and the first numerical value is used for indicating that the vacuumizing valve is in an open state.

Specifically, in the embodiment of the present application, for example, taking the current container internal pressure parameter obtained at 7200 data acquisition moments in a history period as an example, traversing the vacuumizing threshold state value, the preset upper pressure limit value and lower pressure limit value and the internal pressure value corresponding to each data acquisition moment; determining a first starting time (corresponding to a point B in fig. 4) of a working condition of the current acquisition time according to the condition that the state value of the vacuumizing valve is 1 and the state value of the vacuumizing valve is 0 corresponding to the two adjacent acquisition times, wherein an inflection point (corresponding to a point C in fig. 4) of the change of the internal pressure value in the stage corresponds to the first ending time; when the state value of the vacuumizing valve corresponding to the current collection time is 1, the state value of the discharging valve is 0, and the internal pressure value corresponding to the point B is within +/-2 kPa as shown in fig. 4, and the internal pressure value corresponding to the point C is within the range of the upper limit value of +/-2 kPa, determining that the working condition to which the pressure parameter corresponding to the current collection time belongs is a vacuumizing working condition; as shown in fig. 4, the working condition to which the pressure parameter belongs between the data acquisition time corresponding to the point B and the data acquisition time corresponding to the point C is a pumping working condition. It should be noted that, the value for indicating that the evacuation valve is in the open state may be configured as 1, and the value for indicating that the evacuation valve is in the closed state may be configured as 0.

preprocessing each internal pressure value corresponding to the pumping working condition to obtain preprocessing characteristic data corresponding to the pumping working condition, wherein the preprocessing characteristic data comprises at least one of the internal pressure values corresponding to the first starting time and the first ending time, the duration between the first starting time and the first ending time and the slope corresponding to each internal pressure value in an internal pressure value change curve in the duration;

and inputting the preprocessing characteristic data into the pre-training fault prediction model, and obtaining the fault type corresponding to the pressure parameter of the pumping working condition.

Specifically, in this embodiment of the present application, for example, taking the obtaining of the pressure parameter inside the current container at 7200 data collection times in the history period as an example, it is assumed that there are 2000 pressure parameters corresponding to the data collection times under the pumping working condition, and then, respectively calculating the internal pressure values corresponding to both the first start time (corresponding to the point B in fig. 4) and the first end time (corresponding to the point C in fig. 4) in the pressure parameters corresponding to the 2000 data collection times, where the duration between the first start time and the first end time, and the slope corresponding to each internal pressure value in the internal pressure value change curve in the duration. And inputting the preprocessed data corresponding to the 2000 data acquisition moments into the pre-training fault prediction model, so that the fault type corresponding to the pressure parameter of the pumping working condition can be predicted.

In one or more embodiments of the present application, the pressure parameter includes a vacuum pumping threshold, a vacuum releasing threshold, preset upper and lower pressure values, and an internal pressure value of the current container; the determining the working condition of the pressure parameter corresponding to each data acquisition time comprises the following steps:

traversing the vacuumizing valve state value, the emptying valve state value, the preset pressure upper limit value, the preset pressure lower limit value and the internal pressure value corresponding to each first data acquisition moment; the first data acquisition time is any data acquisition time except the data acquisition time corresponding to the pumping working condition in the data acquisition times;

when the vacuumizing valve state value corresponding to the current collection time is a second value, the discharging valve state value is a first value, and the preset pressure upper limit value and the pressure lower limit value are smaller than zero, and the internal pressure value corresponding to the current collection time is in a third preset range, determining that the working condition to which the pressure parameter corresponding to the current collection time belongs is a pressure maintaining working condition; the third preset range is a pressure range determined based on the sum of the pressure upper limit values and the pressure lower limit value.

Specifically, in the embodiment of the present application, for example, taking the current container internal pressure parameter obtained at 7200 data collection moments in a history period as an example, traversing the vacuumizing valve state value, the preset upper pressure limit value, the preset lower pressure limit value and the internal pressure value corresponding to 5200 data collection moments except the vacuumizing working condition; under the conditions that the vacuumizing valve state value corresponding to the current collection time is 1, the emptying valve state value is 0, the preset pressure upper limit value and the pressure lower limit value are smaller than 0, and the internal pressure value corresponding to the current collection time is between the pressure ranges determined based on the pressure upper limit value and the pressure lower limit value, the working condition of the pressure parameter corresponding to the current collection time is a pressure maintaining working condition; here, the normal internal pressure values under the pressure maintaining condition are all kept between-80 kPa (pressure upper limit value) and-70 kPa (pressure lower limit value), and in order to be able to obtain the abnormal parameter values under the pressure maintaining condition, the above-mentioned third preset range may be determined by floating up and down the sum of the pressure upper limit value and the pressure lower limit value by preset pressure values.

As shown in fig. 5, the pressure parameter between the data acquisition time corresponding to the point D and the data acquisition time corresponding to the point E is a pressure maintaining condition, and the internal pressure value in the above section is between-80 kPa (upper pressure limit) -5kPa and-70 kPa (lower pressure limit) +2 kPa. It should be noted that, the value for indicating that the evacuation valve is in the open state may be configured as 1, and the value for indicating that the evacuation valve is in the open state may be configured as 0.

preprocessing each internal pressure value corresponding to the pressure maintaining working condition to obtain preprocessing characteristic data corresponding to the pressure maintaining working condition, wherein the preprocessing characteristic data comprises at least one of a mean value, a standard deviation, a maximum value and a minimum value corresponding to each internal pressure value, a ratio of the number exceeding the upper pressure limit value to the number exceeding the lower pressure limit value in each internal pressure value and a maximum value of the change rate of each internal pressure value;

and inputting the preprocessing characteristic data into the pre-training fault prediction model, and obtaining the fault type corresponding to the pressure parameter of the pressure maintaining working condition.

Specifically, in this embodiment of the present application, for example, taking the current pressure parameter inside the container at 7200 data collection times in a history period as an example, it is assumed that there are pressure parameters corresponding to 3000 data collection times under a pressure maintaining working condition, and then, among the pressure parameters corresponding to 3000 data collection times, average values, standard deviations, maximum values, and minimum values corresponding to internal pressure values corresponding to both data collection times corresponding to D point and data collection times corresponding to E point in fig. 5 are calculated respectively, where the ratio between the number of the internal pressure values exceeding the pressure upper limit (-80 kPa) and the number exceeding the pressure lower limit (-70 kPa) is the maximum value of the rate of change of the internal pressure values. And inputting the preprocessing data corresponding to the 3000 data acquisition moments into the pre-training fault prediction model, so that the fault type corresponding to the pressure parameter of the pressure maintaining working condition can be predicted.

traversing a vacuumizing threshold state value, a discharging threshold state value, a preset pressure upper limit value and pressure lower limit value and an internal pressure value corresponding to the second data acquisition time; the second data acquisition time is any data acquisition time except the data acquisition time corresponding to the normal pressure working condition in the data acquisition times;

determining a second starting time and a second ending time of the working condition of the current acquisition time according to the state values of the vacuumizing valve and the vacuumizing valve corresponding to the two adjacent acquisition times;

when the vacuumizing valve state value corresponding to the current collection time is a first value, the vacuumizing valve state value is a second value, the preset pressure upper limit value and the pressure lower limit value are smaller than zero, the internal pressure value corresponding to the second starting time is in a fourth preset range, and the internal pressure value corresponding to the second ending time is in a fifth preset range, the working condition of the pressure parameter corresponding to the current collection time is determined to be a pressure releasing working condition; the first value is used for indicating that the vacuumizing valve is in a closed state, and the second value is used for indicating that the vacuumizing valve is in an open state.

Specifically, in the embodiment of the present application, for example, taking the current container internal pressure parameter at 7200 data acquisition times obtained in a history period as an example, traversing the vacuumizing valve state value, the preset upper pressure limit value and the preset lower pressure limit value and the internal pressure value corresponding to 6200 data acquisition times except the normal pressure working condition; determining a second starting time (corresponding to a point D in fig. 6) and a first ending time (corresponding to a point E in fig. 6) of the working condition of the current acquisition time according to the fact that the state value of the vacuumizing valve corresponding to the two adjacent acquisition times is 0 and the state value of the vacuumizing valve is 1; and under the conditions that the vacuumizing threshold value corresponding to the current acquisition time is 0, the emptying threshold value is 1, the preset pressure upper limit (-80 kPa) and the pressure lower limit (-70 kPa) are smaller than zero, and as shown in fig. 6, the internal pressure value corresponding to the point D is within the pressure lower limit (-70 kPa) +/-2 kPa, and the internal pressure value corresponding to the point E is within the range of +/-2 kPa, the working condition to which the pressure parameter corresponding to the current acquisition time belongs is determined to be the emptying working condition.

Preprocessing each internal pressure value corresponding to the pressure release working condition to obtain preprocessing characteristic data corresponding to the pressure release working condition, wherein the preprocessing characteristic data comprises at least one of duration between the second starting time and the second ending time, the internal pressure value corresponding to the second starting time, the internal pressure value corresponding to the second ending time and the change rate of each pressure value in the duration;

and inputting the preprocessing characteristic data into the pre-training fault prediction model, and obtaining the fault type corresponding to the pressure parameter of the pressure release working condition.

Specifically, in this embodiment of the present application, for example, taking the obtaining of the pressure parameter inside the current container at 7200 data collection moments in the history period as an example, it is assumed that the pressure parameter at 1200 data collection moments corresponds to the normal pressure working condition, and then, the preprocessing feature data corresponding to the pressure release working condition is obtained by respectively calculating the pressure parameters at the 1200 data collection moments, where the preprocessing feature data includes a duration corresponding to both the data collection moment corresponding to the point D and the data collection moment corresponding to the point E in fig. 6, an internal pressure value corresponding to the point D, an internal pressure value corresponding to the point E, and a rate of change of each pressure value in the duration. And inputting the preprocessing data corresponding to the 1200 data acquisition moments into the pre-training fault prediction model, so that the fault type corresponding to the pressure parameter of the pressure release working condition can be predicted.

The embodiment of the invention also provides a method for detecting the abnormal air tightness of the container, as shown in fig. 7, which specifically comprises the following steps:

s701, taking each fault type and the working condition parameters corresponding to each fault type as sample pressure parameters.

S702, training a classification model by using the sample pressure parameters to obtain the pre-training fault prediction model.

S703, obtaining pressure parameters corresponding to each working condition of the current container in the running process.

S704, preprocessing the pressure parameters corresponding to the working conditions to obtain preprocessed characteristic data, inputting the preprocessed characteristic data into a pre-training fault prediction model, and obtaining the fault type corresponding to the pressure parameters.

And S705, outputting the fault type and the maintenance scheme corresponding to the fault type.

TABLE 3 Table 3

Specifically, in this embodiment of the present application, as shown in table 3, each fault type and a working condition parameter corresponding to each fault type may be used as a sample pressure parameter, where the pressure sample parameter includes a normal working condition parameter, a normal identifier is configured for the fault type corresponding to the normal working condition parameter, the fault identifier is set to 0, the maintenance scheme is set to none, an abnormal identifier corresponding to the fault type configuration corresponding to the abnormal working condition parameter, the fault identifier is set to different identifiers from 1 to 5, and each identifier corresponds to a respective maintenance scheme. And training the classification model by using the sample pressure parameters to obtain the pre-training fault prediction model. In one embodiment, the method includes, but is not limited to, training a decision tree, a support vector machine, a K nearest neighbor and the like, and then selecting a classification model with highest fault prediction accuracy as the pre-training fault prediction model.

The above steps S703 to S705 are already described in detail, and are not described here again.

In the related art, whether the air tightness of a valve body of a container is qualified is judged mainly through pointer change of an air pressure display of the container, or the air tightness of the container is detected by installing equipment such as a differential pressure sensor, an air quantity monitoring device and the like, calculating a difference value between measured values of air inlet and outlet and comparing the difference value with a threshold value; however, the stirring tank body has a large volume and complex process, and is in a state of frequent vacuumizing and vacuum release, and whether the air tightness of the stirring tank body is abnormal or not is monitored only by a sensor and other instruments, so that the abnormal detection accuracy of the air tightness of the stirring tank body is lower.

In order to solve the above technical problem, based on the above embodiment, in one or more embodiments of the present application, as shown in fig. 3 and fig. 4, the method for detecting abnormal air tightness of a container further includes:

1, data acquisition and platform access: and acquiring data such as a vacuumizing valve state value, a pressure lower limit value, a pressure upper limit value, an internal pressure value and the like of the container in the stirring process from a programmable logic controller of the container through data acquisition software in an upper computer, and accessing the pressure data into a health management platform of equipment in real time.

2, carrying out working condition segmentation on the collected data: and carrying out working condition segmentation on the pressure related data in the current container vacuumizing process. The working conditions of the container can be divided into normal pressure working conditions, pumping working conditions, pressure maintaining working conditions, pressure releasing working conditions and the like, and the dividing conditions of the working conditions are shown in table 2.

2.1, normal pressure working condition segmentation: as shown in fig. 8, traversing the vacuumizing threshold state value, the discharging threshold state value, the preset upper pressure limit value, the preset lower pressure limit value and the internal pressure value corresponding to each data acquisition time;

and outputting a normal pressure working condition label corresponding to the working condition of the current collection time under the conditions that the state value of the vacuumizing valve corresponding to the current collection time is 0, the state value of the discharging valve is 1, the preset upper pressure limit value and the preset lower pressure limit value are both zero, and the internal pressure value is within +/-2 kPa.

2.2, dividing the pumping working condition: as shown in fig. 9, traversing the vacuumizing threshold state value, the discharging threshold state value, the preset upper pressure limit value, the preset lower pressure limit value and the internal pressure value corresponding to each data acquisition time; determining a first starting time (corresponding to a point B in fig. 4) of a working condition of the current acquisition time according to the fact that the state value of the vacuumizing valve and the state value of the discharging valve corresponding to the two adjacent acquisition times are 1, and an inflection point (corresponding to a point C in fig. 4) of the change of the internal pressure value in the stage is corresponding to the first ending time; and outputting a pumping working condition label corresponding to a working condition to which the current collection time belongs under the condition that the state value of the vacuumizing valve corresponding to the current collection time is 1, the state value of the discharging valve is 0, the internal pressure value corresponding to the point B is within +/-2 kPa and the internal pressure value corresponding to the point C is within the range of the upper pressure limit value +/-2 kPa as shown in figure 4.

2.3, cutting the pressure maintaining working condition: as shown in fig. 10, traversing the vacuumizing valve state value, the discharging valve state value, the preset upper pressure limit value, the preset lower pressure limit value and the internal pressure value corresponding to the data acquisition time except the vacuumizing working condition; and outputting a pressure maintaining working condition label corresponding to the working condition of the current collection time under the conditions that the state value of the vacuumizing valve corresponding to the current collection time is 1, the state value of the discharging valve is 0, the preset upper pressure limit value and the preset lower pressure limit value are smaller than 0, and the internal pressure value corresponding to the current collection time is between the pressure ranges determined based on the upper pressure limit value and the lower pressure limit value.

2.4, cutting off the pressure release working condition: as shown in fig. 11, the state value of the vacuumizing valve, the state value of the discharging valve, the preset upper and lower pressure limit values and the internal pressure value corresponding to each data acquisition time except the normal pressure working condition are traversed; determining a second starting time (corresponding to a point D in fig. 6) and a first ending time (corresponding to a point E in fig. 6) of the working condition of the current acquisition time according to the fact that the state value of the vacuumizing valve corresponding to the two adjacent acquisition times is 0 and the state value of the vacuumizing valve is 1;

and outputting a pressure release working condition label corresponding to a working condition to which the current collection time belongs when the state value of the vacuumizing valve corresponding to the current collection time is 0, the state value of the discharging valve is 1, the preset upper pressure limit (-80 kPa) and the preset lower pressure limit (-70 kPa) are smaller than zero, the internal pressure value corresponding to the point D is within the lower pressure limit (-70 kPa) +/-2 kPa, and the internal pressure value corresponding to the point E is within the range of +/-2 kPa as shown in figure 6.

3. Pressure characteristics (preprocessing characteristic data) are extracted, and in order to monitor whether the stirring tank body is abnormal or not in the stirring process, the abnormal type of the stirring tank body is classified and positioned, and the pressure characteristics of the stirring tank body under various working conditions are required to be extracted.

Under normal pressure working conditions, the characteristics of the average value, standard deviation, maximum value, minimum value, ratio of positive value to negative value and the like corresponding to the internal pressure value at each data acquisition time are extracted. The characteristic can be used as preprocessing characteristic data for judging whether the pressure sensor of the stirring tank body is damaged or not under the normal pressure working condition.

Under the pumping working condition, as shown in fig. 2, extracting the time length characteristics of the state value of the vacuumizing valve corresponding to each data acquisition time being 1, extracting the actual pressure values at the starting point B and the end point C of the time length, and extracting the data characteristics of the slope corresponding to each internal pressure value, the change rate of the internal pressure value and the like under the pumping working condition. The data characteristic can be used as preprocessing characteristic data for judging whether the tank body is blocked, damaged or damaged by the pipeline filter element or the pumping valve body under the pumping working condition.

Under the pressure maintaining working condition, extracting the average value, standard deviation, maximum value and minimum value corresponding to each data acquisition time, calculating the slope corresponding to each internal pressure value between the minimum value and the maximum value of the adjacent internal pressure values according to the ratio of the quantity exceeding the upper pressure limit value to the quantity exceeding the lower pressure limit value, and taking the data characteristics such as the maximum value of the slope. The data characteristic can be used as preprocessing characteristic data for judging whether the pumping valve body and the releasing valve body of the tank body are damaged or not under the pressure maintaining working condition.

Under the pressure release working condition, as shown in fig. 2, the duration characteristic of the vacuum release valve state value 1 corresponding to each data acquisition time is extracted, the internal pressure value characteristic at the starting point D and the end point E, the data characteristic of the slope corresponding to each internal pressure value between the starting point D and the end point E, and the like. The data characteristic can be used as preprocessing characteristic data of whether a pressure release valve body of the tank body is damaged under the pressure release working condition.

4. And monitoring the air tightness of the container in an abnormal manner, obtaining fault types corresponding to the pressure parameters and maintenance schemes corresponding to the fault types, marking the fault types, and manufacturing a fault classification statistical table shown in the table 3. As shown in fig. 12, sample pressure data under each fault type is collected, and classification models such as a decision tree, a support vector machine, a K nearest neighbor and the like are trained, and a classification model with highest fault prediction accuracy is adopted as a pre-training fault prediction model. According to the classification result output by the pre-training fault prediction model, the corresponding fault type of the container can be positioned and the maintenance scheme corresponding to the fault type can be pushed.

The embodiment of the invention also provides a device for detecting abnormal air tightness of a container, which is used for executing the method for detecting abnormal air tightness of the container provided by the above embodiments, as shown in fig. 13, and comprises:

An obtaining unit 1302, configured to obtain pressure parameters corresponding to each working condition of the current container during the operation process;

the prediction unit 1304 is configured to perform preprocessing on pressure parameters corresponding to the working conditions to obtain preprocessed feature data, input the preprocessed feature data into a pre-training fault prediction model, and obtain a fault type corresponding to the pressure parameters;

and the output unit 1306 is used for outputting the fault type and the maintenance scheme corresponding to the fault type.

In the embodiment of the application, the pressure parameters corresponding to various working conditions of the container in the operation process are preprocessed, and then the failure type corresponding to the pressure parameters is predicted based on the preprocessed data by utilizing the pre-training failure prediction model, so that whether the air tightness of the container is abnormal or not can be accurately judged, the failure type of the air tightness and a maintenance scheme corresponding to the failure type can be provided, unexpected shutdown of production line equipment where the container is located is avoided, and the quality of products processed through the container is improved.

In one or more embodiments of the present application, the acquiring unit 1302 includes:

the first acquisition module is used for acquiring pressure parameters in the current container at a plurality of data acquisition moments; the pressure parameters corresponding to the working conditions comprise the pressure parameters in the current container;

And the determining module is used for determining the working condition of the pressure parameter corresponding to each data acquisition time.

In one or more embodiments of the present application, the pressure parameter includes a vacuum pumping threshold, a vacuum releasing threshold, a preset upper pressure limit and a preset lower pressure limit of the current container, and an internal pressure value of the current container; the determining module includes:

the first traversing subunit is used for traversing the vacuumizing valve state value, the preset pressure upper limit value, the preset pressure lower limit value and the internal pressure value corresponding to each data acquisition time; the pressure parameters corresponding to the working conditions comprise the pressure parameters in the current container;

the first determining subunit is configured to determine, when the state value of the vacuumizing valve corresponding to the current collection time is a first value, the state value of the discharging valve is a second value, and the preset pressure upper limit value and the preset pressure lower limit value are both zero, and the internal pressure value is within a first preset range, that the working condition to which the pressure parameter corresponding to the current collection time belongs is a normal pressure working condition; the first value is used for indicating that the vacuumizing valve is in a closed state, and the second value is used for indicating that the vacuumizing valve is in an open state.

In one or more embodiments of the present application, the prediction unit 1304 includes:

the first preprocessing module is used for preprocessing each internal pressure value corresponding to the normal pressure working condition to obtain preprocessing characteristic data corresponding to the normal pressure working condition; the preprocessing characteristic data comprises at least one of a mean value, a standard deviation, a maximum value and a minimum value corresponding to each internal pressure value and a ratio between the number of positive numerical values and the number of negative numerical values in each internal pressure value;

the second acquisition module is used for inputting the preprocessing characteristic data into the pre-training fault prediction model and acquiring the fault type corresponding to the pressure parameter of the normal pressure working condition.

In one or more embodiments of the present application, the pressure parameter includes a vacuum pumping threshold, a vacuum releasing threshold, a preset upper pressure limit and a preset lower pressure limit, and an internal pressure value of the current container; the determining module includes:

the second traversing subunit is used for traversing the vacuumizing valve state value, the preset pressure upper limit value, the preset pressure lower limit value and the internal pressure value corresponding to each data acquisition time;

The second determining subunit is used for determining a first starting time and a first ending time of the working condition of the current acquisition time according to the state values of the vacuumizing valve and the vacuumizing valve corresponding to the two adjacent acquisition times;

the third determining subunit is configured to determine, when the state value of the vacuumizing valve corresponding to the current acquisition time is a second value and the state value of the discharging valve is a first value, and the preset upper pressure limit value and the preset lower pressure limit value are both smaller than zero, that the internal pressure value corresponding to the first starting time is within a first preset range, and that the working condition to which the pressure parameter corresponding to the current acquisition time belongs is a pumping working condition when the internal pressure value corresponding to the first ending time is within a second preset range; the second numerical value is used for indicating that the vacuumizing valve is in a closed state, and the first numerical value is used for indicating that the vacuumizing valve is in an open state.

the second preprocessing module is used for preprocessing each internal pressure value corresponding to the pumping working condition to obtain preprocessing characteristic data corresponding to the pumping working condition, wherein the preprocessing characteristic data comprises at least one of the internal pressure values corresponding to the first starting time and the first ending time, the duration between the first starting time and the first ending time and the slope corresponding to each internal pressure value in the internal pressure value change curve in the duration;

And the third acquisition module is used for inputting the preprocessing characteristic data into the pre-training fault prediction model and acquiring the fault type corresponding to the pressure parameter of the pumping working condition.

In one or more embodiments of the present application, the pressure parameter includes a vacuum pumping threshold, a vacuum releasing threshold, preset upper and lower pressure values, and an internal pressure value of the current container; the determining module includes:

the third traversing subunit is used for traversing the vacuumizing valve state value, the preset pressure upper limit value, the preset pressure lower limit value and the internal pressure value corresponding to each data acquisition time;

and the fourth determining subunit is used for determining the working condition of the pressure parameter corresponding to the current collection time as the pressure maintaining working condition under the conditions that the vacuumizing valve state value corresponding to the current collection time is a second value, the discharging valve state value is a first value, the preset pressure upper limit value and the preset pressure lower limit value are smaller than zero, and the internal pressure value corresponding to the current collection time is between the pressure upper limit value and the pressure lower limit value.

The third preprocessing module is used for preprocessing each internal pressure value corresponding to the pressure maintaining working condition to obtain preprocessing characteristic data corresponding to the pressure maintaining working condition, wherein the preprocessing characteristic data comprises a mean value, a standard deviation, a maximum value and a minimum value corresponding to each internal pressure value, the ratio of the number of the internal pressure values exceeding the upper pressure limit value to the number of the internal pressure values exceeding the lower pressure limit value and at least one of the maximum values of the change rate of the internal pressure values;

and the fourth acquisition module is used for inputting the preprocessing characteristic data into the pre-training fault prediction model and acquiring the fault type corresponding to the pressure parameter of the pressure maintaining working condition.

the fourth traversing subunit is used for traversing the vacuumizing valve state value, the preset pressure upper limit value, the preset pressure lower limit value and the internal pressure value corresponding to each data acquisition time;

A fifth determining subunit, configured to determine a second starting time and a second ending time of the working condition to which the current acquisition time belongs according to the vacuumizing threshold state value and the vacuumizing threshold state value corresponding to the two adjacent acquisition times;

a sixth determining subunit, configured to determine, when the state value of the vacuumizing valve corresponding to the current acquisition time is a first value, the state value of the discharging valve is a second value, the preset upper pressure limit value and the preset lower pressure limit value are both smaller than zero, the internal pressure value corresponding to the second starting time is within a fourth preset range, and the internal pressure value corresponding to the second ending time is within a fifth preset range, that the working condition to which the pressure parameter corresponding to the current acquisition time belongs is a discharging working condition; the first value is used for indicating that the vacuumizing valve is in a closed state, and the second value is used for indicating that the vacuumizing valve is in an open state.

a fourth preprocessing module, configured to preprocess each internal pressure value corresponding to the pressure release working condition to obtain preprocessing feature data corresponding to the pressure release working condition, where the preprocessing feature data includes at least one of a duration between the second start time and the second end time, an internal pressure value corresponding to the second start time, an internal pressure value corresponding to the second end time, and a rate of change of each pressure value within the duration;

And a fifth acquisition module, configured to input the pre-processing feature data into the pre-training fault prediction model, and acquire a fault type corresponding to the pressure parameter of the pressure release working condition.

In one or more embodiments of the present application, the container air tightness abnormality detection device further includes:

the method comprises the steps of obtaining a sample unit, wherein the sample unit is used for taking working condition parameters corresponding to each fault type as sample pressure parameters;

and the training unit is used for training the classification model by utilizing the sample pressure parameters to obtain the pre-training fault prediction model.

Fig. 14 is a block diagram of a logic structure of an electronic device, according to an example embodiment. For example, the electronic device 1400 may be an electronic device provided inside the electric device such as a container air tightness abnormality detecting instrument, a domain controller, or other industrial production equipment.

In an exemplary embodiment, there is also provided a non-transitory computer readable storage medium including instructions, such as a memory including instructions, executable by a battery processor to perform the container gas tightness anomaly detection method described above, the method comprising: acquiring pressure parameters corresponding to working conditions of the current container in the operation process; the pressure parameters corresponding to the working conditions comprise the pressure parameters in the current container; preprocessing the pressure parameters corresponding to the working conditions to obtain preprocessed characteristic data, inputting the preprocessed characteristic data into a pre-training fault prediction model, and obtaining fault types corresponding to the pressure parameters; and outputting the fault type and the maintenance scheme degree corresponding to the fault type. Optionally, the above instructions may also be executed by a processor of the battery to perform other steps involved in the above exemplary embodiments. For example, the non-transitory computer readable storage medium may be ROM, random Access Memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.

In an exemplary embodiment, there is also provided an application/computer program product comprising one or more instructions executable by a processor of a battery to perform the above-described container tightness anomaly detection method, the method comprising: acquiring pressure parameters corresponding to working conditions of a current container in the operation process, wherein the pressure parameters corresponding to the working conditions comprise pressure parameters in the current container; preprocessing the pressure parameters corresponding to the working conditions to obtain preprocessed characteristic data, inputting the preprocessed characteristic data into a pre-training fault prediction model, and obtaining fault types corresponding to the pressure parameters; and outputting the fault type and the maintenance scheme corresponding to the fault type. Optionally, the above instructions may also be executed by a processor of the battery to perform other steps involved in the above exemplary embodiments. Fig. 14 is an example diagram of an electronic device 1400. It will be appreciated by those skilled in the art that the schematic diagram 14 is merely an example of the electronic device 1400 and is not meant to be limiting of the electronic device 1400, and may include more or fewer components than shown, or may combine certain components, or different components, e.g., the electronic device 1400 may also include input-output devices, network access devices, buses, etc.

The processor 1402 may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field-programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor 1402 may be any conventional processor or the like, the processor 1402 being a control center of the electronic device 1400, with various interfaces and lines connecting the various parts of the overall electronic device 1400.

The memory 1401 may be used to store computer readable instructions and the processor 1402 implements the various functions of the electronic device 1400 by executing or executing the computer readable instructions or modules stored within the memory 1401 and invoking data stored within the memory 1401. The memory 1401 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program (such as a sound playing function, an image playing function, etc.) required for at least one function, and the like; the storage data area may store data created according to the use of the electronic device 1400, and the like. Further, the Memory 1401 may include a hard disk, memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash Card (Flash Card), at least one magnetic disk storage device, a Flash Memory device, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), or other nonvolatile/volatile storage device.

The modules integrated with the electronic device 1400 may be stored in a computer-readable storage medium if implemented as software functional modules and sold or used as a stand-alone product. Based on such understanding, the present invention implements all or part of the flow of the method of the above-described embodiments, and computer readable instructions, which may also be implemented by means of hardware associated with the instructions of the computer readable instructions, may be stored in a computer readable storage medium, which when executed by a processor, implement the steps of the various method embodiments described above.

Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the application following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the application pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.

It is to be understood that the present application is not limited to the precise arrangements and instrumentalities shown in the drawings, which have been described above, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the application is limited only by the appended claims.

User information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, presented data, etc.) referred to herein are both user-authorized or fully authorized information and data by parties, and the collection, use and processing of relevant data requires compliance with relevant laws and regulations and standards of the relevant country and region, and is provided with corresponding operation portals for user selection of authorization or denial.

Claims

1. A method for detecting abnormal tightness of a container, comprising:

acquiring pressure parameters corresponding to working conditions of the current container in the operation process; the pressure parameters corresponding to the working conditions comprise the pressure parameters in the current container;

preprocessing the pressure parameters corresponding to the working conditions to obtain preprocessed characteristic data, inputting the preprocessed characteristic data into a pre-training fault prediction model, and obtaining fault types corresponding to the pressure parameters; the pre-training fault prediction model is a model obtained by training a classification model by using each fault type and working condition parameters corresponding to each fault type as sample pressure parameters and utilizing the sample pressure parameters;

And outputting the fault type and the maintenance scheme corresponding to the fault type.

2. The method of claim 1, wherein the obtaining the pressure parameter corresponding to each working condition of the current container during the operation process includes:

acquiring pressure parameters in the current container at a plurality of data acquisition moments;

and determining the working condition of the pressure parameter corresponding to each data acquisition time.

3. The method of claim 2, wherein the pressure parameters include a vacuum threshold, a preset upper and lower pressure limit for the current vessel, and an internal pressure value for the current vessel; the determining the working condition of the pressure parameter corresponding to each data acquisition time comprises the following steps:

when the state value of the vacuumizing valve corresponding to the current collection time is a first value, the state value of the discharging valve is a second value, and the preset upper pressure limit value and the preset lower pressure limit value are both zero, and the internal pressure value is within a first preset range, determining that the working condition of the pressure parameter corresponding to the current collection time is a normal pressure working condition; the first value is used for indicating that the vacuumizing valve is in a closed state, and the second value is used for indicating that the vacuumizing valve is in an open state.

4. The method of claim 3, wherein preprocessing the pressure parameters corresponding to the working conditions to obtain preprocessed feature data, inputting the preprocessed feature data into a pre-training fault prediction model, and obtaining a fault type corresponding to the pressure parameters, includes:

preprocessing each internal pressure value corresponding to the normal pressure working condition to obtain preprocessing characteristic data corresponding to the normal pressure working condition; the preprocessing characteristic data comprises at least one of a mean value, a standard deviation, a maximum value and a minimum value corresponding to each internal pressure value and a ratio between the number of positive numerical values and the number of negative numerical values in each internal pressure value;

and inputting the preprocessing characteristic data into the pre-training fault prediction model to obtain the fault type corresponding to the pressure parameter of the normal pressure working condition.

5. The method of claim 2, wherein the pressure parameters include a vacuum threshold, a preset upper and lower pressure limit, and an internal pressure value of the current vessel; the determining the working condition of the pressure parameter corresponding to each data acquisition time comprises the following steps:

6. The method of claim 5, wherein preprocessing the pressure parameters corresponding to the working conditions to obtain preprocessed feature data, inputting the preprocessed feature data into a pre-training fault prediction model, and obtaining a fault type corresponding to the pressure parameters, includes:

7. The method of claim 2, wherein the pressure parameters include a vacuum valve state value, preset upper and lower pressure values, and an internal pressure value of the current vessel; the determining the working condition of the pressure parameter corresponding to each data acquisition time comprises the following steps:

8. The method of claim 7, wherein preprocessing the pressure parameters corresponding to the working conditions to obtain preprocessed feature data, inputting the preprocessed feature data into a pre-training fault prediction model, and obtaining a fault type corresponding to the pressure parameters, includes:

9. The method of claim 2, wherein the pressure parameters include a vacuum threshold, a preset upper and lower pressure limit, and an internal pressure value of the current vessel; the determining the working condition of the pressure parameter corresponding to each data acquisition time comprises the following steps:

10. The method of claim 9, wherein preprocessing the pressure parameter corresponding to each working condition to obtain preprocessed feature data, inputting the preprocessed feature data into a pre-training fault prediction model, and obtaining a fault type corresponding to the pressure parameter, includes:

preprocessing each internal pressure value corresponding to the pressure release working condition to obtain preprocessing characteristic data corresponding to the pressure release working condition, wherein the preprocessing characteristic data comprises at least one of duration between the second starting time and the second ending time, the internal pressure value corresponding to the second starting time, the internal pressure value corresponding to the second ending time and the change rate of each internal pressure value in the duration;

11. The method according to any one of claims 1 to 10, further comprising:

taking working condition parameters corresponding to each fault type as sample pressure parameters;

and training the classification model by using the sample pressure parameters to obtain the pre-training fault prediction model.

12. A container air tightness abnormality detection device, characterized by comprising:

the acquisition unit is used for acquiring pressure parameters corresponding to working conditions of the current container in the operation process; the pressure parameters corresponding to the working conditions comprise the pressure parameters in the current container;

the prediction unit is used for preprocessing the pressure parameters corresponding to the working conditions to obtain preprocessed characteristic data, inputting the preprocessed characteristic data into a pre-training fault prediction model, and obtaining fault types corresponding to the pressure parameters; the pre-training fault prediction model is a model obtained by training a classification model by using each fault type and working condition parameters corresponding to each fault type as sample pressure parameters and utilizing the sample pressure parameters;

and the output unit is used for outputting the fault type and the maintenance scheme corresponding to the fault type.

13. An electronic device comprising a memory and a processor, characterized in that the memory has stored therein a computer program, the processor being arranged to execute the method according to any of claims 1 to 11 by means of the computer program.

14. A computer readable storage medium, characterized in that the computer readable storage medium comprises a stored program, wherein the program when run performs the method as claimed in any one of claims 1 to 11.