CN114937043B

CN114937043B - Equipment defect detection method, device, equipment and medium based on artificial intelligence

Info

Publication number: CN114937043B
Application number: CN202210881344.2A
Authority: CN
Inventors: 马戈; 朱国伟; 顾维玺; 王青春; 黄启洋
Original assignee: China Industrial Internet Research Institute
Current assignee: China Industrial Internet Research Institute
Priority date: 2022-07-26
Filing date: 2022-07-26
Publication date: 2022-10-25
Anticipated expiration: 2042-07-26
Also published as: CN114937043A

Abstract

The invention discloses an equipment defect detection method, device, equipment and medium based on artificial intelligence. The invention discloses: determining appearance detection items and operation detection items of all parts in the equipment to be detected according to the part information of the equipment to be detected, inputting target image information of all parts into a preset feature extraction model to obtain appearance feature information of all parts, controlling the equipment to be detected to carry out load operation according to the operation detection items, obtaining operation state information of all parts in the load operation process, carrying out fault evaluation on all parts according to the appearance feature information and the operation state information, determining fault parts in all parts according to fault evaluation results, and generating corresponding defect detection results of the equipment to be detected according to the fault part information; the invention can accurately detect the defects of the equipment by respectively evaluating the appearance and the running state of each part in the equipment to be detected, thereby effectively improving the efficiency of detecting the defects of the equipment.

Description

Equipment defect detection method, device, equipment and medium based on artificial intelligence

Technical Field

The invention relates to the technical field of defect detection, in particular to an equipment defect detection method, device, equipment and medium based on artificial intelligence.

Background

With the development of scientific technology, the process of electronic equipment is more and more complex, so that the integration level of components inside the electronic equipment is higher and higher, and when the electronic equipment has defects, the specific reasons of the defects of the equipment cannot be accurately detected at present, so that the defects of the equipment cannot be effectively repaired.

The above is only for the purpose of assisting understanding of the technical aspects of the present invention, and does not represent an admission that the above is prior art.

Disclosure of Invention

The invention mainly aims to provide an equipment defect detection method, device, equipment and medium based on artificial intelligence, and aims to solve the technical problem that the defects of the equipment cannot be effectively repaired due to the fact that the specific reasons of the equipment defects cannot be accurately detected in the prior art.

In order to achieve the above object, the present invention provides an apparatus defect detecting method based on artificial intelligence, the method comprising the steps of:

determining appearance detection items and operation detection items of all parts in the equipment to be detected according to the part information of the equipment to be detected;

acquiring target image information of each part according to the appearance detection items, inputting the target image information into a preset feature extraction model, and acquiring appearance feature information of each part;

controlling the equipment to be detected to carry out load operation according to the operation detection items, and acquiring the operation state information of each part in the load operation process;

performing fault evaluation on each part according to the appearance characteristic information and the running state information;

determining fault parts in all parts according to the fault evaluation result, and acquiring fault part information of the fault parts;

and generating a defect detection result corresponding to the equipment to be detected according to the information of the fault part.

Optionally, the controlling the device to be detected to perform load operation according to the operation detection item, and acquiring operation state information of each part in the load operation process includes:

determining the fault weight of each part according to the part information;

generating a load operation control strategy of the equipment to be detected according to the fault weight and the operation detection item;

and controlling the equipment to be detected to carry out load operation according to the load operation control strategy, and acquiring the operation state information of each part in the load operation process.

Optionally, the determining the failure weight of each part according to the part information includes:

determining an operation module corresponding to each part according to the part information;

acquiring compatibility information corresponding to the operating module;

performing compatibility test on the operation module according to the compatibility information;

and determining the fault weight of each part according to the compatibility test result.

Optionally, the generating a load operation control strategy of the device to be detected according to the fault weight and the operation detection item includes:

determining the troubleshooting sequence of each part according to the fault weight;

carrying out load operation sequencing on each part according to the sequencing sequence;

and generating a load operation control strategy of the equipment to be detected according to the load operation sequencing result and the operation detection items.

Optionally, the obtaining target image information of each part according to the appearance detection item, inputting the target image information to a preset feature extraction model, and obtaining appearance feature information of each part includes:

acquiring images of all parts according to the appearance detection items to obtain initial image information of all parts;

carrying out gray level processing on the initial image information to obtain candidate image information after gray level processing;

inputting the candidate image information into a preset noise reduction model for noise reduction processing to obtain target image information;

and inputting the target image information into a preset feature extraction model to obtain the appearance feature information of each part.

Optionally, the inputting the candidate image information into a preset noise reduction model for performing noise reduction processing to obtain target image information includes:

inputting the candidate image information into a preset noise reduction model for noise reduction treatment;

determining a region to be identified of each part and edge information of the region to be identified according to the candidate image information subjected to noise reduction processing;

and performing edge enhancement on the candidate image information subjected to noise reduction processing according to the edge information to obtain target image information.

Optionally, the performing fault evaluation on each part according to the appearance characteristic information and the operation state information includes:

inputting the appearance characteristic information into a preset welding spot marking model to obtain the current welding spot information of each part;

acquiring standard welding spot information of each part according to the part information;

performing similarity matching on the current welding spot information and the standard welding spot information;

and performing fault evaluation on each part according to the similarity matching result and the running state information.

In addition, in order to achieve the above object, the present invention further provides an apparatus for detecting defects of devices based on artificial intelligence, including:

the item acquisition module is used for determining appearance detection items and operation detection items of all parts in the equipment to be detected according to the part information of the equipment to be detected;

the appearance detection module is used for acquiring target image information of each part according to the appearance detection items, inputting the target image information into a preset feature extraction model and acquiring appearance feature information of each part;

the operation detection module is used for controlling the equipment to be detected to carry out load operation according to the operation detection items and acquiring the operation state information of each part in the load operation process;

the part evaluation module is used for carrying out fault evaluation on each part according to the appearance characteristic information and the running state information;

the fault determining module is used for determining fault parts in all the parts according to the fault evaluation result and acquiring fault part information of the fault parts;

and the defect detection module is used for generating a defect detection result corresponding to the equipment to be detected according to the fault part information.

In addition, in order to achieve the above object, the present invention further provides an artificial intelligence based device defect detecting device, including: a memory, a processor, and an artificial intelligence based device defect detection program stored on the memory and executable on the processor, the artificial intelligence based device defect detection program configured to implement the steps of the artificial intelligence based device defect detection method as described above.

In addition, to achieve the above object, the present invention further provides a storage medium having an artificial intelligence based device defect detecting program stored thereon, wherein the artificial intelligence based device defect detecting program, when executed by a processor, implements the steps of the artificial intelligence based device defect detecting method as described above.

The method comprises the steps of determining appearance detection items and operation detection items of all parts in equipment to be detected according to part information of the equipment to be detected, obtaining target image information of all parts according to the appearance detection items, inputting the target image information to a preset feature extraction model, obtaining appearance feature information of all parts, controlling the equipment to be detected to carry out load operation according to the operation detection items, obtaining operation state information of all parts in the load operation process, carrying out fault evaluation on all parts according to the appearance feature information and the operation state information, determining fault parts in all parts according to fault evaluation results, obtaining fault part information of the fault parts, and generating corresponding defect detection results of the equipment to be detected according to the fault part information; according to the invention, the appearance detection and the running state detection are respectively carried out on each part in the equipment to be detected, so that the appearance characteristic information and the running state information of each part are accurately obtained, the fault evaluation is carried out on each part according to the appearance characteristic information and the running state information, the fault part with a fault in each part is accurately determined according to the fault evaluation result, the fault part information of the fault part is obtained, and the defect detection result corresponding to the equipment to be detected is generated according to the fault part information, so that the accurate detection of the defect reason of the equipment to be detected is realized, the detection efficiency of the equipment defect is effectively improved, and the equipment can be effectively repaired by a user aiming at the defect reason.

Drawings

FIG. 1 is a schematic structural diagram of an artificial intelligence-based device defect detection device in a hardware operating environment according to an embodiment of the present invention;

FIG. 2 is a schematic flow chart of a first embodiment of the method for detecting device defects based on artificial intelligence according to the present invention;

FIG. 3 is a schematic flow chart of a second embodiment of the method for detecting defects of an apparatus based on artificial intelligence according to the present invention;

FIG. 4 is a schematic flow chart of a third embodiment of the method for detecting device defects based on artificial intelligence of the present invention;

fig. 5 is a block diagram of a first embodiment of an apparatus for detecting device defects based on artificial intelligence according to the present invention.

The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.

Detailed Description

It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

Referring to fig. 1, fig. 1 is a schematic structural diagram of an artificial intelligence-based device defect detecting device in a hardware operating environment according to an embodiment of the present invention.

As shown in fig. 1, the artificial intelligence based device defect detecting device may include: a processor 1001, such as a Central Processing Unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may include a Display screen (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a Wireless interface (e.g., a Wireless-Fidelity (Wi-Fi) interface). The Memory 1005 may be a Random Access Memory (RAM) or a Non-Volatile Memory (NVM), such as a disk Memory. The memory 1005 may alternatively be a storage device separate from the processor 1001.

Those skilled in the art will appreciate that the configuration shown in FIG. 1 does not constitute a limitation of an artificial intelligence based device defect detection device and may include more or fewer components than shown, or some components in combination, or a different arrangement of components.

As shown in fig. 1, a memory 1005, which is a storage medium, may include therein an operating system, a network communication module, a user interface module, and an artificial intelligence based device defect detecting program.

In the artificial intelligence based device defect detecting device shown in fig. 1, the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 of the apparatus defect detecting apparatus based on artificial intelligence of the present invention may be disposed in the apparatus defect detecting apparatus based on artificial intelligence, and the apparatus defect detecting apparatus based on artificial intelligence calls the apparatus defect detecting program based on artificial intelligence stored in the memory 1005 through the processor 1001, and executes the apparatus defect detecting method based on artificial intelligence provided by the embodiment of the present invention.

An embodiment of the present invention provides an apparatus defect detection method based on artificial intelligence, and referring to fig. 2, fig. 2 is a flowchart illustrating a first embodiment of the apparatus defect detection method based on artificial intelligence according to the present invention.

In this embodiment, the method for detecting device defects based on artificial intelligence includes the following steps:

step S10: and determining appearance detection items and operation detection items of all parts in the equipment to be detected according to the part information of the equipment to be detected.

It should be noted that, this embodiment is applied to determining, when equipment needs to be detected, appearance detection items and operation detection items of each part in the equipment to be detected according to part information of the equipment to be detected, obtaining target image information of each part according to the appearance detection items, inputting the target image information to a preset feature extraction model, obtaining appearance feature information of each part, controlling the equipment to be detected to perform load operation according to the operation detection items, obtaining operation state information of each part in a load operation process, performing fault evaluation on each part according to the appearance feature information and the operation state information, determining a fault part in each part according to a fault evaluation result, obtaining fault part information of the fault part, and generating a defect detection result corresponding to the equipment to be detected according to the fault part information.

Compared with the prior art that the specific reasons of the equipment defects cannot be accurately detected, and the equipment defects cannot be effectively repaired, the method has the advantages that the appearance detection and the running state detection are respectively carried out on each part in the equipment to be detected, so that the appearance characteristic information and the running state information of each part are accurately obtained, the fault evaluation is carried out on each part according to the appearance characteristic information and the running state information, the fault part with a fault in each part is accurately determined according to the fault evaluation result, the fault part information of the fault part is obtained, the defect detection result corresponding to the equipment to be detected is generated according to the fault part information, so that the accurate detection of the defect reasons of the equipment to be detected is realized, the detection efficiency of the equipment defects is effectively improved, and a user can effectively repair the equipment according to the defect reasons.

It should be understood that the executing body of the method of this embodiment may be an artificial intelligence based device defect detecting device with data processing, network communication and program running functions, such as a computer, or other apparatuses or devices capable of implementing the same or similar functions, and is described here by taking the above artificial intelligence based device defect detecting device (hereinafter referred to as a defect detecting device) as an example.

It should be noted that the device to be detected may be a device suspected of having a defect, or may be a device that needs to perform defect detection. The parts can be components or modules in the equipment to be detected, and a plurality of parts can be integrated in the equipment to be detected, so that in order to accurately detect the defects of the equipment to be detected, the defect detection equipment of the embodiment needs to detect all the parts in the equipment to be detected respectively, and determine the parts with faults in all the parts.

The appearance detection item may be an item for detecting the structural appearance of each part, and the appearance detection item may be an item for detecting the shape of the welding spot, the number of welding spots, and the size of the welding spot of each part, or may be an item for detecting whether the appearance of each part is damaged, which is not limited in this embodiment. The operation detection items can be used for controlling the equipment to be detected to perform simulation operation, and then detecting whether the operation state of each part is abnormal in the operation process, for example, detecting whether each part generates heat abnormally in the operation process or works normally.

It should be understood that, in order to accurately detect the specific defect cause of the apparatus to be detected, the defect detecting apparatus of the present embodiment obtains the apparatus information of the apparatus to be detected, determines the part information of each part in the apparatus to be detected according to the apparatus information, determines the appearance detection item and the operation detection item of each part in the apparatus to be detected according to the part information, and thus detects the appearance and the operation state of each part to determine whether the appearance of each part is normal and whether the operation state in the operation process is abnormal.

Step S20: and acquiring target image information of each part according to the appearance detection items, inputting the target image information into a preset feature extraction model, and acquiring appearance feature information of each part.

It should be noted that the target image information may be appearance image information of a part structure of each part, and the preset feature extraction model may be a neural network model which is constructed in advance and is used for extracting appearance features in the image information of the part. The appearance characteristic information may be an appearance characteristic that needs to be detected in the appearance of each part.

It should be understood that, in order to accurately detect the appearance of the device to be detected, the defect detection device according to the embodiment collects images of the parts according to the appearance detection items, obtains target image information of the parts, inputs the target image information to the preset feature extraction model, extracts features that need to be detected in the target image information, thereby obtaining appearance feature information of the parts, and effectively improving the appearance detection efficiency of the parts.

In specific implementation, the defect detection device determines an image acquisition area of each part according to the appearance detection item, performs image acquisition on each part according to the image acquisition area to obtain target image information of each part, inputs the target image information into a preset feature extraction model, extracts features needing to be detected in the target image information, and thus obtains appearance feature information of each part.

For example, the defect detection device determines an image acquisition area of each part as an area a according to the appearance detection item, performs image acquisition on the area a to obtain target image information of each part, determines to-be-detected appearance features of each part as welding spot feature information according to the appearance detection item, inputs the target image information into a preset feature extraction model, extracts the welding spot feature information in the target image information, and obtains the appearance feature information of the welding spot of each part.

Step S30: and controlling the equipment to be detected to carry out load operation according to the operation detection items, and acquiring the operation state information of each part in the load operation process.

It should be noted that the operation state information may be related information of an actual operation state of each part in an operation process of the device to be detected, for example, the operation state information may be information of an operation power, an operation temperature, an operation voltage, and the like of each part in the operation process.

It should be understood that, in order to accurately detect whether each part has an operation problem, the defect detection device of the embodiment controls the device to be detected to perform load operation according to the operation detection items, and acquires the operation state information of each part in the load operation process, thereby accurately judging whether each part is normal in the operation process.

In specific operation, the defect detection equipment generates an operation control strategy according to operation detection items, controls the equipment to be detected to carry out load operation according to the operation control strategy, and acquires operation state information of each part in the process of load operation.

For example, the defect detection device generates an operation control strategy according to the operation detection item, controls the device to be detected to perform load operation according to the operation control strategy, and obtains the operation power, the operation temperature and the operation voltage of each part in the load operation process, so that whether the power, the temperature and the voltage of each part are abnormal in the operation process can be accurately determined.

Step S40: and performing fault evaluation on each part according to the appearance characteristic information and the running state information.

It should be noted that the failure evaluation may be that the defect detection device separately evaluates the appearance characteristic information and the operation state information of each part, so as to determine whether the appearance characteristic of each part has a failure (for example, whether the appearance is damaged or the welding spot is abnormal or not) and determine whether the operation state of each part is abnormal during the load operation.

Further, in order to accurately evaluate the failure of each part and determine the failed part among the parts, the step S40 may include:

It should be noted that the preset welding point marking model may be a pre-constructed neural network model for marking the welding point of the part. The standard welding spot information may be pre-calibrated correct welding spot information of each part, for example, the standard welding spot information may include information such as a standard welding spot shape, a standard welding spot size, and a standard welding spot number. The current welding spot information may be related information of a currently existing welding spot of each part, for example, the current welding spot information may include information of a current welding spot shape, a current welding spot size, a current welding spot number, and the like. The similarity matching result may be a similarity between the current solder joint information and the standard solder joint information of each part.

It should be understood that, in order to accurately determine a faulty part existing in each part, the defect detection device of this embodiment inputs the appearance characteristic information into a preset welding spot marking model, obtains a welding spot identifier of each part, determines current welding spot information according to the welding spot identifier, obtains standard welding spot information of each part according to the part information, matches the current welding spot information with the standard welding spot information in a similarity manner, thereby determining a difference degree and a similarity degree between the current welding spot information and the standard welding spot information of each part, and performs fault evaluation on each part according to a similarity matching result and the operating state information.

Step S50: and determining fault parts in the parts according to the fault evaluation result, and acquiring fault part information of the fault parts.

The failure evaluation result may be a result of evaluating appearance characteristic information and an operation state of each part, and the defect detection device may determine a failed part having an appearance failure or/and an operation failure among the parts based on the failure evaluation result. The faulty component may be a component with an appearance or/and operation fault in each component, and the faulty component information may be component information corresponding to the faulty component, for example, the faulty component information may be information such as a component code and a component type of the faulty component.

In a specific implementation, the defect detection equipment determines an appearance evaluation strategy and an operation evaluation strategy of each part according to the part information, performs appearance evaluation on appearance characteristic information of each part according to the appearance evaluation strategy so as to determine the part with an appearance fault in each part, evaluates operation state information of each part according to the operation evaluation strategy so as to determine the part with an operation fault in each part, takes the part with the appearance fault and the part with the operation fault as fault parts, and acquires fault part information of the fault part.

Step S60: and generating a defect detection result corresponding to the equipment to be detected according to the information of the fault part.

It should be noted that the defect detection result may be a detection result generated by the defect detection device after evaluating a defect existing in the device to be detected, and the defect detection result may include faulty part information of a faulty part in the device to be detected, where the faulty part has a fault, and a defect cause.

In the specific implementation, the defect detection equipment determines module information corresponding to the fault part according to the fault part information, determines a fault module with a defect in the equipment to be detected according to the module information, and evaluates the defect of the equipment to be detected according to the module information of the fault module and the fault module, so as to obtain a defect detection result of the equipment to be detected.

For example, the defect detection device determines the fault part as the part a in the module C according to the fault part information, evaluates the defect of the device to be detected according to the module information of the module C, thereby obtaining the defect detection result of the device to be detected, and determines that the part a in the module C of the device to be detected has the defect.

The method comprises the steps of determining appearance detection items and operation detection items of all parts in equipment to be detected according to part information of the equipment to be detected, obtaining target image information of all parts according to the appearance detection items, inputting the target image information to a preset feature extraction model, obtaining appearance feature information of all parts, controlling the equipment to be detected to carry out load operation according to the operation detection items, obtaining operation state information of all parts in a load operation process, carrying out fault evaluation on all parts according to the appearance feature information and the operation state information, determining fault parts in all parts according to fault evaluation results, obtaining fault part information of the fault parts, and generating a fault detection result corresponding to the equipment to be detected according to the fault part information; according to the invention, the appearance detection and the running state detection are respectively carried out on each part in the equipment to be detected, so that the appearance characteristic information and the running state information of each part are accurately obtained, the fault evaluation is carried out on each part according to the appearance characteristic information and the running state information, the fault part with a fault in each part is accurately determined according to the fault evaluation result, the fault part information of the fault part is obtained, and the defect detection result corresponding to the equipment to be detected is generated according to the fault part information, so that the accurate detection of the defect reason of the equipment to be detected is realized, the detection efficiency of the equipment defect is effectively improved, and the equipment can be effectively repaired by a user aiming at the defect reason.

Referring to fig. 3, fig. 3 is a flowchart illustrating a method for detecting device defects based on artificial intelligence according to a second embodiment of the present invention.

Based on the first embodiment, in this embodiment, the step S30 includes:

step S301: and determining the fault weight of each part according to the part information.

It should be noted that the failure weight may be a ratio of probabilities of the components having failures, for example, the component a, the component B, and the component C exist in the device to be detected, where a probability of the component a having a failure is 10%, a probability of the component B having a failure is 30%, and a probability of the component C having a failure is 60%, and thus the failure weights of the components are, respectively, 0.1 for the component a, 0.3 for the component B, and 0.6 for the component C.

In the specific implementation, the defect detection equipment searches a preset part fault database according to the part information, acquires a fault case of each part according to a search result, determines the fault probability of each part according to the fault case, and determines the fault weight of each part according to the fault probability.

Further, in order to accurately obtain the failure weight of each part, the step S301 may include:

step S3011: determining an operation module corresponding to each part according to the part information;

step S3012: acquiring compatibility information corresponding to the operating module;

step S3013: performing compatibility test on the operating module according to the compatibility information;

step S3014: and determining the fault weight of each part according to the compatibility test result.

It should be noted that the operation modules may be modules in the device to be tested, at least one operation module is present in the device to be tested, that is, the device to be tested is composed of at least one operation module, and at least one part is present in the operation module, that is, the operation module is composed of at least one part. The functions of different operation modules may be different, so that the failure of different operation modules may be different, and the probability of failure of different operation modules may also be different.

The compatibility information may be a theoretical compatibility relationship between each operation module and the device to be detected, the lower the compatibility between the operation module and the device to be detected is, the higher the probability of the operation module having a fault is, and conversely, the higher the compatibility between the operation module and the device to be detected is, the lower the probability of the operation module having a fault is. For example, an operation module a, an operation module B and an operation module C exist in the device to be detected, wherein the compatibility between the operation module a and the device to be detected is 90%, the compatibility between the operation module B and the device to be detected is 70%, and the compatibility between the operation module C and the device to be detected is 95%, so that it is determined that the failure probability of the operation module B is the highest, the failure probability of the operation module a is the second, and the failure probability of the operation module C is the lowest. The compatibility test can be used for testing the interaction and operation functions between the operation module and the equipment to be tested, so that the actual compatibility information between the operation module and the equipment to be tested is determined according to the compatibility test result.

Step S302: and generating a load operation control strategy of the equipment to be detected according to the fault weight and the operation detection items.

It should be noted that the load operation control strategy may be a control strategy for controlling the load operation of the device to be detected, in the process of the load operation of the device to be detected, each part may also operate under load, and the defect detection device may determine the operation abnormality of each part in the process of the load operation by acquiring the operation state information of each part in the process of the load operation.

It should be understood that, in order to orderly control each part to perform load operation, so as to improve the efficiency of detecting the operation state of each part, the defect detection device of the present embodiment determines the failure probability of each part according to the failure weight, determines the operation order of each part according to the failure probability, so that the part with the high failure probability preferentially performs load operation, so as to preferentially perform operation state detection on the part with the high failure probability, and generates the load operation control strategy of the device to be detected according to the failure weight and the operation detection items, thereby effectively improving the efficiency of detecting the operation state of each part.

For example, the defect detection equipment determines that the fault weight of a part A is 0.3, the fault weight of a part B is 0.1, the fault weight of a part C is 0.4, the fault weight of a part D is 0.2, the load operation sequence of each part is determined according to the fault weight of each part, the load operation sequence comprises the part C, the part A, the part D and the part B from first to last, and the load operation control strategy of the equipment to be detected is generated according to the load operation sequence and the operation detection items.

Further, in order to accurately generate the load operation control strategy to realize the orderly control of each part, the step S302 may include:

step S3021: determining the troubleshooting sequence of each part according to the fault weight;

step S3022: carrying out load operation sequencing on each part according to the sequencing sequence;

step S3023: and generating a load operation control strategy of the equipment to be detected according to the load operation sequencing result and the operation detection items.

The troubleshooting order may be an arrangement order of performing operation troubleshooting on each part, where the higher the failure weight of the part is, the more advanced the troubleshooting order is, for example, the failure weight of the part a is 0.3, the failure weight of the part B is 0.7, and the troubleshooting order of the part B is advanced after the troubleshooting order of the part a is determined according to the failure weight.

In the specific implementation, the defect detection equipment determines the fault probability of each part according to the fault weight, determines the checking sequence of each part according to the fault probability, and performs load operation sequencing on each part according to the checking sequence, so that the parts with higher fault probability preferentially perform load operation, and generates a load operation control strategy of the equipment to be detected according to the load operation sequencing result and the operation detection items, thereby improving the operation detection efficiency.

Step S303: and controlling the equipment to be detected to carry out load operation according to the load operation control strategy, and acquiring the operation state information of each part in the load operation process.

It should be understood that, in order to accurately detect whether each part has an operation problem, the defect detection apparatus of the present embodiment controls the apparatus to be detected to perform load operation according to the operation detection item, and obtains the operation state information of each part in the load operation process, thereby accurately judging whether each part is normal in the operation process.

In specific operation, the defect detection equipment generates an operation control strategy according to operation detection items, controls the equipment to be detected to carry out load operation according to the operation control strategy, and obtains operation state information of each part in the process of load operation.

In the embodiment, the fault weight of each part is determined according to the part information, the load operation control strategy of the equipment to be detected is generated according to the fault weight and the operation detection item, the equipment to be detected is controlled to carry out load operation according to the load operation control strategy, and the operation state information of each part in the load operation process is acquired; the invention determines the fault weight of each part according to the part information, thereby determining the operation sequence of each part according to the fault weight, generating the load operation control strategy of the equipment to be detected according to the fault weight and the operation detection items, thereby accurately generating the load operation control strategy, improving the operation state detection efficiency of each part, controlling the equipment to be detected to perform load operation according to the load operation control strategy, and acquiring the operation state information of each part in the load operation process, thereby realizing the detection of the operation state of each part and improving the operation state detection efficiency.

Referring to fig. 4, fig. 4 is a flowchart illustrating a third embodiment of an apparatus defect detection method based on artificial intelligence according to the present invention.

Based on the first embodiment, in this embodiment, the step S20 includes:

step S201: and acquiring images of the parts according to the appearance detection items to obtain initial image information of the parts.

It should be noted that the initial image information may be image information of each part that is initially acquired by the defect inspection apparatus through an internally integrated or externally connected image sensor.

It should be understood that, in order to accurately acquire the image of the area of each part that needs to be subjected to the appearance inspection, the defect inspection apparatus of the embodiment determines the area to be inspected of each part according to the appearance inspection item, and acquires the image of the area to be inspected of each part to obtain the initial image information of each part.

Step S202: and carrying out gray level processing on the initial image information to obtain candidate image information after gray level processing.

The candidate image information may be gray-scale image information of each part obtained by subjecting the initial image information to gray-scale processing.

It should be understood that, in order to improve the efficiency of subsequent image processing, the defect detection apparatus of the present embodiment performs gray scale processing on the initial image information, so as to obtain gray scale image information of each part after gray scale processing.

Step S203: and inputting the candidate image information into a preset noise reduction model for noise reduction processing to obtain target image information.

It should be noted that the preset noise reduction model may be a pre-constructed neural network model for eliminating invalid information in the candidate image information. The target image information may be image information of each part, which is obtained by subjecting the candidate image information to noise reduction processing and removing invalid information.

It should be understood that, in order to improve the efficiency of subsequent feature extraction, the defect detection device of the present embodiment inputs the candidate image information into the preset noise reduction model, eliminates invalid information in the candidate image information through the preset noise reduction model, and only retains the key information, thereby obtaining the target image information.

Further, in order to accurately obtain the target image, the step S203 may include:

step S2031: inputting the candidate image information into a preset noise reduction model for noise reduction treatment;

step S2032: determining a region to be identified of each part and edge information of the region to be identified according to the candidate image information after the noise reduction processing;

step S2033: and performing edge enhancement on the candidate image information subjected to noise reduction processing according to the edge information to obtain target image information.

It should be noted that the region to be identified may be a region in the candidate image information that needs to be subjected to appearance detection. The edge information may be information related to a contour edge of the region to be recognized.

It should be understood that, in order to enhance the feature information in the candidate image and reduce the interference information in the candidate image information, the defect detection device of this embodiment inputs the candidate image information into a preset noise reduction model to perform noise reduction processing, determines the region to be identified of each part and the edge information of the region to be identified according to the candidate image information after noise reduction processing, and performs edge enhancement on the candidate image information after noise reduction processing according to the edge information to obtain target image information.

Step S204: and inputting the target image information into a preset feature extraction model to obtain the appearance feature information of each part.

It should be noted that the preset feature extraction model may be a pre-constructed neural network model for extracting appearance features in the target image information. The appearance feature information may be feature information of an appearance structure of each part that needs to be subjected to appearance inspection.

For example, the defect detection equipment determines that the welding spot information of each part needs to be detected according to the appearance detection items, acquires the initial image information of the welding spot area after the image acquisition of the welding spot area of each part, inputs the initial image information into a preset noise reduction model after the gray processing to perform the noise reduction processing to acquire the target image information, inputs the target image information into a preset feature extraction model to acquire the welding spot appearance feature information of each part, such as the welding spot shape, the welding spot number, the welding spot shape and the like.

In the embodiment, the image of each part is acquired according to the appearance detection item to obtain initial image information of each part, the initial image information is subjected to gray processing to obtain candidate image information after gray processing, the candidate image information is input to a preset noise reduction model to be subjected to noise reduction processing to obtain target image information, and the target image information is input to a preset feature extraction model to obtain appearance feature information of each part; according to the invention, the image of each part is acquired according to the appearance detection item, the initial image information of the appearance detection area required to be carried out in each part is obtained, the gray level processing is carried out on the initial image information, the candidate image information after drawing is obtained, the candidate image information is input into the preset noise reduction model to be subjected to the noise reduction processing, and the target image information is obtained, so that the image accuracy of each part is improved, the invalid information in the image is effectively reduced, the feature extraction efficiency is improved, the target image information is input into the preset feature extraction model to obtain the appearance feature information of each part, the appearance feature information of each part is accurately extracted, and the appearance detection efficiency is improved.

In addition, an embodiment of the present invention further provides a storage medium, where an apparatus defect detection program based on artificial intelligence is stored, and when the apparatus defect detection program based on artificial intelligence is executed by a processor, the steps of the apparatus defect detection method based on artificial intelligence as described above are implemented.

Since the storage medium adopts all the technical solutions of all the embodiments, at least all the beneficial effects brought by the technical solutions of the embodiments are provided, and are not described in detail herein.

Referring to fig. 5, fig. 5 is a block diagram illustrating a first embodiment of an apparatus for detecting device defects based on artificial intelligence according to the present invention.

As shown in fig. 5, the apparatus for detecting device defects based on artificial intelligence according to the embodiment of the present invention includes:

the item acquisition module 10 is configured to determine appearance detection items and operation detection items of each part in the device to be detected according to the part information of the device to be detected.

It should be noted that the device to be detected may be a device suspected of having a defect, or may be a device that needs to perform defect detection. The parts can be components or modules in the equipment to be detected, and a plurality of parts can be integrated in the equipment to be detected, so that in order to accurately detect the defects of the equipment to be detected, the item acquisition module of the embodiment needs to detect each part in the equipment to be detected respectively, and accordingly determines the parts with faults in each part.

It should be understood that, in order to accurately detect the specific defect cause of the device to be detected, the item acquisition module in this embodiment acquires the device information of the device to be detected, determines the part information of each part in the device to be detected according to the device information, determines the appearance detection item and the operation detection item of each part in the device to be detected according to the part information, and thus detects the appearance and the operation state of each part to determine whether the appearance of each part is normal and whether the operation state in the operation process is abnormal.

And the appearance detection module 20 is configured to obtain target image information of each part according to the appearance detection item, input the target image information to a preset feature extraction model, and obtain appearance feature information of each part.

It should be noted that the target image information may be appearance image information of a part structure of each part, and the preset feature extraction model may be a neural network model which is constructed in advance and is used for extracting appearance features in the image information of the part. The appearance feature information may be an appearance feature to be detected in the appearance of each part.

It should be understood that, in order to accurately detect the appearance of the device to be detected, the appearance detection module of this embodiment performs image acquisition on each part according to an appearance detection item, obtains target image information of each part, inputs the target image information to the preset feature extraction model, and extracts features that need to be detected in the target image information, so as to obtain appearance feature information of each part, thereby effectively improving the appearance detection efficiency of each part.

In the specific implementation, the appearance detection module determines an image acquisition area of each part according to the appearance detection item, performs image acquisition on each part according to the image acquisition area to obtain target image information of each part, inputs the target image information to the preset feature extraction model, extracts features needing to be detected in the target image information, and thus obtains appearance feature information of each part.

For example, the appearance detection module determines an image acquisition area of each part as an area a according to an appearance detection item, performs image acquisition on the area a to obtain target image information of each part, determines to-be-detected appearance features of each part as welding spot feature information according to the appearance detection item, inputs the target image information into a preset feature extraction model, extracts welding spot feature information in the target image information, and obtains appearance feature information of welding spots of each part.

And the operation detection module 30 is used for controlling the equipment to be detected to perform load operation according to the operation detection items and acquiring the operation state information of each part in the load operation process.

It should be understood that, in order to accurately detect whether each part has an operation problem, the operation detection module of the embodiment controls the device to be detected to perform load operation according to the operation detection item, and obtains the operation state information of each part in the load operation process, thereby accurately judging whether each part is normal in the operation process.

In specific operation, the operation detection module generates an operation control strategy according to the operation detection items, controls the equipment to be detected to carry out load operation according to the operation control strategy, and obtains the operation state information of each part in the process of load operation.

For example, the operation detection module generates an operation control strategy according to the operation detection items, controls the equipment to be detected to perform load operation according to the operation control strategy, and obtains the operation power, the operation temperature and the operation voltage of each part in the load operation process, so that whether each part is abnormal in power, temperature and voltage in the operation process can be accurately determined.

And the part evaluation module 40 is used for carrying out fault evaluation on each part according to the appearance characteristic information and the operation state information.

The failure evaluation may be that the part evaluation module separately evaluates the appearance characteristic information and the operating state information of each part, so as to determine whether the appearance characteristic of each part has a failure (for example, whether the appearance is damaged or the welding spot is abnormal or not), and determine whether the operating state of each part is abnormal during the load operation.

And the fault determining module 50 is used for determining a fault part in each part according to the fault evaluation result and acquiring fault part information of the fault part.

It should be noted that the failure evaluation result may be a result of evaluating appearance characteristic information and an operation state of each part, and the failure determination module may determine a failed part having an appearance failure or/and an operation failure in each part according to the failure evaluation result. The faulty component may be a component with an appearance or/and operation fault in each component, the faulty component information may be component information corresponding to the faulty component, and the faulty component information may be information such as a component code and a component type of the faulty component.

In the specific implementation, the fault determination module determines an appearance evaluation strategy and an operation evaluation strategy of each part according to the part information, performs appearance evaluation on appearance characteristic information of each part according to the appearance evaluation strategy so as to determine the part with the appearance fault in each part, evaluates operation state information of each part according to the operation evaluation strategy so as to determine the part with the operation fault in each part, takes the part with the appearance fault and the part with the operation fault as fault parts, and acquires fault part information of the fault part.

And the defect detection module 60 is used for generating a defect detection result corresponding to the equipment to be detected according to the information of the fault part.

It should be noted that the defect detection result may be a detection result generated by the defect detection module after evaluating a defect of the device to be detected, and the defect detection result may include the faulty part information of the faulty part in the device to be detected, and a defect cause.

In the specific implementation, the defect detection module determines module information corresponding to the fault part according to the fault part information, determines a fault module with a defect in the equipment to be detected according to the module information, and evaluates the defect of the equipment to be detected according to the module information of the fault module and the fault module, so as to obtain a defect detection result of the equipment to be detected.

For example, the defect detection module determines that the fault part is the part a in the module C according to the fault part information, evaluates the defect of the device to be detected according to the module information of the module C, thereby obtaining the defect detection result of the device to be detected, and determines that the part a in the module C of the device to be detected has the defect.

Further, the operation detection module 30 is further configured to determine a failure weight of each part according to the part information; generating a load operation control strategy of the equipment to be detected according to the fault weight and the operation detection item; and controlling the equipment to be detected to carry out load operation according to the load operation control strategy, and acquiring the operation state information of each part in the load operation process.

Further, the operation detection module 30 is further configured to determine an operation module corresponding to each part according to the part information; acquiring compatibility information corresponding to the operating module; performing compatibility test on the operation module according to the compatibility information; and determining the fault weight of each part according to the compatibility test result.

Further, the operation detection module 30 is further configured to determine a checking order of each part according to the failure weight; carrying out load operation sequencing on each part according to the sequencing sequence; and generating a load operation control strategy of the equipment to be detected according to the load operation sequencing result and the operation detection items.

Further, the appearance detection module 20 is further configured to perform image acquisition on each part according to the appearance detection item to obtain initial image information of each part; carrying out gray level processing on the initial image information to obtain candidate image information after gray level processing; inputting the candidate image information into a preset noise reduction model for noise reduction processing to obtain target image information; and inputting the target image information into a preset feature extraction model to obtain the appearance feature information of each part.

Further, the appearance detection module 20 is further configured to input the candidate image information to a preset noise reduction model for noise reduction processing; determining a region to be identified of each part and edge information of the region to be identified according to the candidate image information subjected to noise reduction processing; and performing edge enhancement on the candidate image information subjected to noise reduction processing according to the edge information to obtain target image information.

Further, the part evaluation module 40 is further configured to input the appearance characteristic information to a preset welding spot marking model to obtain current welding spot information of each part; acquiring standard welding spot information of each part according to the part information; performing similarity matching on the current welding spot information and the standard welding spot information; and performing fault evaluation on each part according to the similarity matching result and the running state information.

It should be understood that the above is only an example, and the technical solution of the present invention is not limited in any way, and in a specific application, a person skilled in the art may set the technical solution as needed, and the present invention is not limited thereto.

It should be noted that the above-described work flows are only exemplary, and do not limit the scope of the present invention, and in practical applications, a person skilled in the art may select some or all of them to achieve the purpose of the solution of the embodiment according to actual needs, and the present invention is not limited herein.

In addition, the technical details that are not described in detail in this embodiment may be referred to the method for detecting device defects based on artificial intelligence provided in any embodiment of the present invention, and are not described herein again.

Further, it is to be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising a … …" does not exclude the presence of another identical element in a process, method, article, or system that comprises the element.

The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.

Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present invention or portions thereof that contribute to the prior art may be embodied in the form of a software product, where the computer software product is stored in a storage medium (e.g. a Read Only Memory (ROM)/RAM, a magnetic disk, and an optical disk), and includes several instructions for enabling a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to execute the method according to the embodiments of the present invention.

The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.

Claims

1. An artificial intelligence based equipment defect detection method is characterized in that the artificial intelligence based equipment defect detection method comprises the following steps:

determining a fault part in each part according to the fault evaluation result, and acquiring fault part information of the fault part;

generating a defect detection result corresponding to the equipment to be detected according to the information of the fault part;

the method comprises the following steps of controlling the equipment to be detected to carry out load operation according to the operation detection items and acquiring the operation state information of each part in the load operation process, and comprises the following steps:

determining the fault weight of each part according to the part information;

generating a load operation control strategy of the equipment to be detected according to the fault weight and the operation detection items;

controlling the equipment to be detected to carry out load operation according to the load operation control strategy, and acquiring the operation state information of each part in the load operation process;

determining the failure weight of each part according to the part information comprises the following steps:

acquiring compatibility information corresponding to the operating module;

2. The artificial intelligence based equipment defect detection method of claim 1, wherein the generating of the load operation control strategy of the equipment to be detected according to the fault weight and the operation detection items comprises:

3. The method for detecting the defect of the equipment based on the artificial intelligence as claimed in claim 1, wherein the obtaining of the target image information of each part according to the appearance detection item and the inputting of the target image information to a preset feature extraction model to obtain the appearance feature information of each part comprises:

4. The artificial intelligence based device defect detection method of claim 3, wherein the inputting the candidate image information into a preset noise reduction model for noise reduction processing to obtain target image information comprises:

5. The artificial intelligence based equipment defect detection method of any one of claims 1 to 4, wherein the fault evaluation of each part according to the appearance characteristic information and the operation state information comprises:

6. An apparatus for detecting defects of a device based on artificial intelligence, the apparatus comprising:

the operation detection module is used for controlling the equipment to be detected to perform load operation according to the operation detection items and acquiring the operation state information of each part in the load operation process;

the defect detection module is used for generating a defect detection result corresponding to the equipment to be detected according to the information of the fault part;

the operation detection module is also used for determining the fault weight of each part according to the part information; generating a load operation control strategy of the equipment to be detected according to the fault weight and the operation detection items; controlling the equipment to be detected to carry out load operation according to the load operation control strategy, and acquiring the operation state information of each part in the load operation process;

the operation detection module is also used for determining an operation module corresponding to each part according to the part information; acquiring compatibility information corresponding to the operating module; performing compatibility test on the operation module according to the compatibility information; and determining the fault weight of each part according to the compatibility test result.

7. An artificial intelligence based device defect detecting device, characterized in that the artificial intelligence based device defect detecting device comprises: a memory, a processor, and an artificial intelligence based device defect detection program stored on the memory and executable on the processor, the artificial intelligence based device defect detection program configured to implement the artificial intelligence based device defect detection method of any of claims 1-5.

8. A storage medium having an artificial intelligence based device defect detecting program stored thereon, the artificial intelligence based device defect detecting program when executed by a processor implementing the artificial intelligence based device defect detecting method according to any one of claims 1 to 5.