New energy battery pack detection method and system

Abstract

The invention provides a new energy battery pack detection method and system, and the method comprises the steps: carrying out the full scanning of a battery pack through a preset binocular vision system when the battery pack is detected to be located in a target detection region in real time, so as to detect a plurality of target feature points corresponding to the battery pack in real time; acquiring a corresponding ultrasonic signal in real time at each target feature point through a preset ultrasonic composite probe, and generating a corresponding time-frequency spectrogram and an envelope signal in real time according to the ultrasonic signal; calculating a target confidence degree corresponding to each target feature point in real time according to the time-frequency spectrogram and the envelope signal based on a preset rule, and judging whether the target confidence degree is greater than a preset confidence degree threshold value or not in real time; and if the target confidence coefficient is judged to be greater than a preset confidence coefficient threshold value in real time, correspondingly judging that the battery pack does not have defects, and generating a corresponding detection report. According to the invention, the detection of the battery pack can be objectively and accurately completed, and the detection efficiency is correspondingly improved.

Description

Technical Field

[0001] The present invention relates to the technical field of new energy vehicles, and particularly to a method and system for detecting a new energy battery pack. Background Art

[0002] With the progress of technology and the rapid development of productivity, the production technology of new energy vehicles has become increasingly mature, and has been popularized in people's daily lives and recognized by people, correspondingly facilitating people's lives.

[0003] Among them, the battery pack is one of the core components of new energy electric vehicles, and is used to provide electrical energy for the drive motor and other components inside the vehicle. Based on this, in order to ensure the performance of the battery pack, the prior art will perform corresponding inspections before the battery pack leaves the factory to ensure the quality of the battery pack.

[0004] Furthermore, when the prior art inspects the appearance and internal structure of the battery pack, most of them still complete the inspection of the battery pack by manual visual inspection or using corresponding inspection tools. However, the judgment results of this inspection method completely depend on human subjective judgment, so it is easy to miss inspections or misjudgments, correspondingly reducing the detection efficiency of the battery pack. Summary of the Invention

[0005] Based on this, the purpose of the present invention is to provide a method and system for detecting a new energy battery pack to solve the problem that most of the prior art detects the battery pack manually, resulting in easy omission and misjudgment.

[0006] The first aspect of the embodiment of the present invention proposes: A method for detecting a new energy battery pack, wherein the method includes: When it is detected in real time that the battery pack is located in the target detection area, a preset binocular vision system is used to perform a full scan of the battery pack to detect a number of target feature points corresponding to the battery pack in real time; A preset ultrasonic composite probe is used to collect corresponding ultrasonic signals at each of the target feature points in real time, and a corresponding time-frequency spectrum diagram and envelope signal are generated in real time according to the ultrasonic signals; Based on a preset rule, the target confidence corresponding to each of the target feature points is calculated in real time according to the time-frequency spectrum diagram and the envelope signal, and it is determined in real time whether the target confidence is greater than a preset confidence threshold; If it is determined in real time that the target confidence is greater than the preset confidence threshold, it is correspondingly determined that the battery pack has no defects, and a corresponding detection report is generated.

[0007] The beneficial effects of the present invention are as follows: By detecting in real time whether the battery pack falls into the detection area, it is possible to judge in real time whether scanning is required. Based on this, after the battery pack is scanned, the corresponding target feature points can be obtained synchronously. Based on this, the target feature points can accurately reflect whether the battery pack has defects. Thus, the time-frequency spectrum diagram and envelope signal of the current target feature points are obtained in real time, and finally the corresponding target confidence level is calculated, so that the subsequent judgment can be objectively and accurately completed ultimately, thereby eliminating the need for manual participation and correspondingly improving the detection efficiency of the battery pack.

[0008] Further, the step of performing a full scan of the battery pack through a preset binocular vision system to detect in real time a plurality of target feature points corresponding to the battery pack includes: Real-time collect the three-dimensional dimensions corresponding to the battery pack through the preset binocular vision system, and create a target battery pack model adapted to the battery pack in real time according to the three-dimensional dimensions through a preset three-dimensional program; Detect in real time the target model corresponding to the battery pack through a preset database, and detect in real time a plurality of target feature points corresponding to the battery pack according to the target model and the target battery pack model, and each of the target feature points is unique.

[0009] Further, the step of detecting in real time a plurality of target feature points corresponding to the battery pack according to the target model and the target battery pack model includes: When the target model is obtained in real time, determine in real time a plurality of components contained inside the battery pack according to the target model; Create component models corresponding to each of the components inside the target battery pack model in real time, and add corresponding target identifiers respectively; Detect a plurality of the target feature points in the target battery pack model in real time according to the target identifier, and each of the target identifiers is unique.

[0010] Further, the step of detecting in real time a plurality of the target feature points in the target battery pack model according to the target identifier includes: When each of the target identifiers is marked in real time, detect the fixed points and connection points generated inside the target battery pack model corresponding to the component model corresponding to each of the target identifiers respectively; In the target battery pack model, highlight the fixed points and the connection points, and set the fixed points and the connection points as the target feature points respectively, and each of the fixed points and each of the connection points is unique.

[0011] Further, the step of calculating in real time the target confidence corresponding to each of the target feature points according to the preset rules based on the time-frequency spectrogram and the envelope signal includes: When the time-frequency spectrogram is obtained in real time, perform real-time parsing processing on the time-frequency spectrogram to detect in real time the spectral curves included in the time-frequency spectrogram; Detect in real time the starting point and the ending point of the spectral curve, and detect in real time a number of maximum points and a number of minimum points that appear in sequence in the spectral curve within the range of the starting point and the ending point; Set a number of the maximum points and a number of the minimum points as the eigenvalue corresponding to the time-frequency spectrogram, and calculate in real time the target confidence corresponding to each of the target feature points according to the eigenvalue and the envelope signal. Each of the maximum points and each of the minimum points is relatively unique.

[0012] Further, the step of calculating in real time the target confidence corresponding to each of the target feature points according to the eigenvalue and the envelope signal includes: When the envelope signal is obtained in real time, match in real time the envelope value corresponding to each of the target feature points in the envelope signal; Create a corresponding target feature sequence according to the eigenvalue in real time, and create a corresponding target envelope sequence according to the envelope value in real time; Generate the target confidence of the target feature point according to the target feature sequence and the target envelope sequence. Each of the envelope values is unique.

[0013] Further, the step of generating the target confidence of the target feature point according to the target feature sequence and the target envelope sequence includes: When the target feature sequence and the target envelope sequence are obtained respectively, perform interleaving and fusion processing on the target feature sequence and the target envelope sequence to generate a corresponding target confidence sequence in real time; Perform real-time conversion processing on the target confidence sequence through a preset algorithm to generate the target confidence in real time. The target confidence sequence is unique.

[0014] A second aspect of the embodiments of the present invention proposes: A new energy battery pack detection system, wherein the system includes: A scanning module, configured to, when it is detected in real time that the battery pack is located in the target detection area, perform a full scan on the battery pack through a preset binocular vision system to detect in real time a number of target feature points corresponding to the battery pack; The acquisition module is used to collect the corresponding ultrasonic signals at each of the target feature points in real time through a preset ultrasonic composite probe, and generate the corresponding time-frequency spectrogram and envelope signal in real time according to the ultrasonic signals; The calculation module is used to calculate the target confidence corresponding to each of the target feature points in real time based on a preset rule according to the time-frequency spectrogram and the envelope signal, and determine in real time whether the target confidence is greater than a preset confidence threshold; The judgment module is used to, if it is determined in real time that the target confidence is greater than the preset confidence threshold, correspondingly determine that the battery pack has no defects and generate a corresponding detection report.

[0015] Furthermore, the scanning module is specifically used for: Collect the three-dimensional size corresponding to the battery pack in real time through the preset binocular vision system, and create a target battery pack model adapted to the battery pack in real time according to the three-dimensional size through a preset three-dimensional program; Detect the target model corresponding to the battery pack in real time through a preset database, and detect a number of target feature points corresponding to the battery pack in real time according to the target model and the target battery pack model, and each of the target feature points is unique.

[0016] Furthermore, the scanning module is specifically used for: When the target model is obtained in real time, determine in real time a number of components included inside the battery pack according to the target model; Create component models corresponding to each of the components inside the target battery pack model in real time, and add corresponding target identifiers respectively; Detect a number of the target feature points in the target battery pack model in real time according to the target identifier, and each of the target identifiers is unique.

[0017] Furthermore, the scanning module is specifically used for: When each of the target identifiers is marked in real time, detect the fixed points and connection points generated inside the target battery pack model corresponding to the component model corresponding to each of the target identifiers respectively; In the target battery pack model, highlight the fixed points and the connection points, and set the fixed points and the connection points as the target feature points correspondingly, and each of the fixed points and each of the connection points is unique.

[0018] Furthermore, the calculation module is specifically used for: When the time-frequency spectrum diagram is obtained in real time, perform real-time parsing processing on the time-frequency spectrum diagram to detect in real time the spectrum curves contained therein; Detect in real time the starting point and the ending point of the spectrum curve, and detect in real time several maximum points and several minimum points that appear in sequence in the spectrum curve within the range of the starting point and the ending point; Set several of the maximum points and several of the minimum points as the characteristic values corresponding to the time-frequency spectrum diagram, and calculate in real time the target confidence levels corresponding to each of the target feature points according to the characteristic values and the envelope signal. Each of the maximum points and each of the minimum points is relatively unique.

[0019] Further, the calculation module is specifically configured to: When the envelope signal is obtained in real time, match in real time the envelope values corresponding to each of the target feature points in the envelope signal; Create a corresponding target feature sequence according to the characteristic values in real time, and create a corresponding target envelope sequence according to the envelope values in real time; Generate the target confidence levels of the target feature points according to the target feature sequence and the target envelope sequence. Each of the envelope values is unique.

[0020] Further, the calculation module is specifically configured to: When the target feature sequence and the target envelope sequence are respectively obtained, perform an interleaving and fusion process on the target feature sequence and the target envelope sequence to generate a corresponding target confidence level sequence in real time; Perform real-time conversion processing on the target confidence level sequence through a preset algorithm to generate the target confidence levels in real time. The target confidence level sequence is unique.

[0021] The third aspect of the embodiments of the present invention proposes: A computer, including a memory, a processor, and a computer program stored on the memory and executable on the processor. Wherein, when the processor executes the computer program, the new energy battery pack detection method as described above is implemented.

[0022] The fourth aspect of the embodiments of the present invention proposes: A readable storage medium, on which a computer program is stored. Wherein, when the program is executed by a processor, the new energy battery pack detection method as described above is implemented.

[0023] The additional aspects and advantages of the present invention will be partly given in the following description, partly will become obvious from the following description, or will be understood through the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 It is a flowchart of a new energy battery pack detection method provided by the first embodiment of the present invention; Figure 2 It is a structural block diagram of a new energy battery pack detection system provided by the third embodiment of the present invention.

[0025] The following specific embodiments will further illustrate the present invention in conjunction with the above-mentioned drawings. SPECIFIC EMBODIMENTS

[0026] To facilitate the understanding of the present invention, the present invention will be described more comprehensively below with reference to the relevant drawings. Several embodiments of the present invention are given in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, these embodiments are provided to make the disclosure of the present invention more thorough and comprehensive.

[0027] It should be noted that when an element is referred to as being "fixedly provided on" another element, it can be directly on the other element or there can also be an intermediate element. When an element is considered to be "connected" to another element, it can be directly connected to the other element or there may be an intermediate element at the same time. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are only for the purpose of illustration.

[0028] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs. The terms used in the description of the present invention herein are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0029] Please refer to Figure 1 , which shows a new energy battery pack detection method provided by the first embodiment of the present invention. The new energy battery pack detection method provided by this embodiment can objectively and accurately detect whether the battery pack meets the standards, and at the same time can eliminate the participation of manual labor, correspondingly improving the detection efficiency of the battery pack.

[0030] Specifically, this embodiment provides: A new energy battery pack detection method, specifically including the following steps: Step S10, when it is detected in real time that the battery pack is located in the target detection area, the battery pack is scanned in its entirety through a preset binocular vision system to detect a number of target feature points corresponding to the battery pack in real time; Among them, it should be noted that in order to ensure the performance of the battery pack, before the battery pack leaves the factory, it is necessary to conduct corresponding inspections on the structure of the entire battery pack to prevent structural defects in the battery pack. Based on this, in order to improve the inspection efficiency, the present invention will pre-set a target inspection area on the production line. Among them, it should be pointed out that corresponding sensors are provided inside the target inspection area, and the sensors can detect in real time whether the battery pack enters the target inspection area. Specifically, if so, the pre-set binocular vision system will be immediately enabled, and the current battery pack will be scanned in its entirety immediately through the existing binocular vision system, and several target feature points corresponding to the inside of the current battery pack, that is, the positions where structural defects are likely to occur, can be detected in real time, so as to facilitate subsequent processing.

[0031] Step S20: Real-time collect corresponding ultrasonic signals at each of the target feature points through a preset ultrasonic composite probe, and generate corresponding time-frequency spectrograms and envelope signals in real time according to the ultrasonic signals; Among them, it should be noted that in order to objectively and accurately judge whether there are structural defects at each current target feature point, it is necessary to collect corresponding detection data in real time for subsequent judgment. Based on this, the present invention will immediately use the existing ultrasonic composite probe to collect each current target feature point in real time and can synchronously collect the required ultrasonic signals. Among them, it should be pointed out that in order to comprehensively analyze whether there are defects in the current battery pack, the current ultrasonic signal will be split at this time, and the corresponding time-frequency spectrogram and envelope signal can be split, so as to facilitate subsequent processing. Among them, it should be pointed out that the present invention will perform signal splitting processing on the current ultrasonic signal through the existing DTW (dynamic programming) algorithm. During this process, the spectral information and envelope information corresponding to the inside of the current ultrasonic signal can be parsed in real time, so as to generate the required time-frequency spectrogram and envelope signal correspondingly, so as to comprehensively complete subsequent analysis and facilitate subsequent processing.

[0032] Step S30: Based on a preset rule, calculate the target confidence corresponding to each of the target feature points in real time according to the time-frequency spectrogram and the envelope signal, and judge in real time whether the target confidence is greater than a preset confidence threshold; Among them, it should be noted that after the required time-frequency spectrogram and envelope signal are obtained in real time through the above steps, corresponding calculation and processing can be carried out at this time. Specifically, the present invention can immediately calculate the target confidence corresponding to each current target feature point in real time according to the preset calculation rules, that is, the probability that the current target feature point has a structural defect. Based on this, it is necessary to judge in real time whether the target confidence is greater than the preset confidence threshold for subsequent processing. Among them, it should be pointed out that the greater the target confidence, the smaller the probability of corresponding structural defects. Correspondingly, the smaller the target confidence, the greater the probability of corresponding structural defects.

[0033] Step S40, if it is judged in real time that the target confidence is greater than the preset confidence threshold, it is correspondingly judged that the battery pack has no defect, and a corresponding detection report is generated.

[0034] Among them, it should be noted that if it is judged in real time that the current target confidence is greater than the current preset confidence threshold, it can be directly determined that the target feature point corresponding to the current target confidence has no defect. Correspondingly, if the current target confidence is less than the current preset confidence threshold, it can be directly determined that the current target feature point has a defect, and corresponding return-to-factory processing is required, so as to objectively and accurately complete the detection of each battery pack, correspondingly improving the detection efficiency of the battery pack. Among them, it should be pointed out that the preset confidence threshold set by the present invention can be 90% and 95%, etc., and can be changed according to specific situations.

[0035] Second Embodiment Further, the step of performing a full scan of the battery pack through the preset binocular vision system to detect a plurality of target feature points corresponding to the battery pack in real time includes: Real-time collect the three-dimensional size corresponding to the battery pack through the preset binocular vision system, and create a target battery pack model adapted to the battery pack in real time according to the three-dimensional size through a preset three-dimensional program; Detect the target model corresponding to the battery pack in real time through a preset database, and detect a plurality of target feature points corresponding to the battery pack in real time according to the target model and the target battery pack model. Each target feature point is unique.

[0036] Among them, it should be noted that in order to objectively and accurately analyze the target feature points corresponding to the current battery pack, specifically, the present invention will collect the three-dimensional dimensions corresponding to the current battery pack in real time through the above binocular vision system. At the same time, the target battery pack model adapted to the current battery pack can be created in real time according to the current three-dimensional dimensions through existing 3D programs such as ug or solidworks. Based on this, in order to facilitate subsequent judgment, it is also necessary to detect the target model corresponding to the current battery pack in the existing database in real time. Among them, it should be pointed out that there are many types of existing battery packs, and the structures of each type of battery pack are also different. Based on this, by detecting the target model of the battery pack in real time, the subsequent detection can be accurately completed to facilitate subsequent processing.

[0037] Further, the step of detecting a plurality of target feature points corresponding to the battery pack in real time according to the target model and the target battery pack model includes: When the target model is obtained in real time, a plurality of components included inside the battery pack are determined in real time according to the target model; Component models corresponding to each of the components are created in real time inside the target battery pack model, and corresponding target identifiers are added respectively; A plurality of the target feature points are detected in real time in the target battery pack model according to the target identifier, and each target identifier is unique.

[0038] Among them, it should be noted that after the target model of the battery pack is determined in real time, a plurality of components included inside the current battery pack can be detected in real time again according to the existing database. Similarly, in order to truly simulate the current battery pack, component models corresponding to each current component will also be created in real time inside the current target battery pack model. Among them, in order to facilitate subsequent distinction, corresponding target identifiers will also be added respectively for subsequent processing.

[0039] Further, the step of detecting a plurality of the target feature points in real time in the target battery pack model according to the target identifier includes: When each target identifier is marked in real time, the fixed points and connection points generated inside the target battery pack model corresponding to the component model corresponding to each target identifier are detected respectively; In the target battery pack model, the fixed points and the connection points are highlighted, and the fixed points and the connection points are set as the target feature points respectively. Each fixed point and each connection point are unique.

[0040] Among them, it should be noted that after the target identification of each component model is determined in real time through the above steps, at this time, the fixed points and connection points generated corresponding to each other among the current component models can be intuitively detected inside the current target battery pack model. Among them, it should be noted that the fixed points and connection points are the positions most prone to defects. Based on this, the present invention will highlight the current fixed points and connection points and set them as the required target feature points for subsequent processing.

[0041] Further, the step of calculating in real time the target confidence corresponding to each of the target feature points according to the preset rules based on the time-frequency spectrum diagram and the envelope signal includes: When the time-frequency spectrum diagram is obtained in real time, perform real-time analysis processing on the time-frequency spectrum diagram to detect in real time the spectrum curves contained in the time-frequency spectrum diagram; Detect in real time the starting point and the ending point of the spectrum curve, and detect in real time several maximum points and several minimum points that appear in sequence in the spectrum curve within the range between the starting point and the ending point; Set several maximum points and several minimum points as the characteristic values corresponding to the time-frequency spectrum diagram, and calculate in real time the target confidence corresponding to each of the target feature points according to the characteristic values and the envelope signal. Each maximum point and each minimum point are relatively unique.

[0042] Among them, it should be noted that after the target feature points and their corresponding time-frequency spectrum diagrams and envelope signals are determined in real time through the above steps, the final calculation process can be completed at this time. Specifically, the present invention will first analyze the spectrum curves contained inside the current time-frequency spectrum diagram. Among them, it should be noted that the spectrum curve has a certain range and several maximum points and several minimum points that appear in sequence can be detected in real time within this range. Among them, it should be noted that the current maximum points and minimum points can directly reflect the smoothness of the current target feature points, that is, they can reflect the possibility of defects, and are immediately set as the required characteristic values. Then, by combining the characteristic values with the current envelope signal, the required target confidence can be calculated for subsequent processing.

[0043] Further, the step of calculating in real time the target confidence corresponding to each of the target feature points according to the characteristic values and the envelope signal includes: When the envelope signal is obtained in real time, match in real time the envelope values corresponding to each of the target feature points in the envelope signal; Create a corresponding target feature sequence in real time according to the eigenvalue, and create a corresponding target envelope sequence in real time according to the envelope value; Generate the target confidence level of the target feature point corresponding to the target feature sequence and the target envelope sequence, and each envelope value is unique.

[0044] It should be noted that the size of the above envelope signal can intuitively reflect the type of defect that appears at the current target feature point. Based on this, for the convenience of subsequent comprehensive analysis, the present invention will also match in real time the envelope value corresponding to each current target feature point in the current envelope signal. Based on this, a corresponding target feature sequence can be created in real time according to the current respective eigenvalue. Similarly, a corresponding target envelope sequence can be created in real time according to the current respective envelope value, so as to facilitate subsequent processing. It should be pointed out that the type of defect corresponding to the above target feature point can be fracture, gap, shedding, etc., so that subsequent factory repair can be carried out to facilitate subsequent processing.

[0045] Further, the step of generating the target confidence level of the target feature point corresponding to the target feature sequence and the target envelope sequence includes: When the target feature sequence and the target envelope sequence are respectively obtained, perform an interspersed fusion process on the target feature sequence and the target envelope sequence to generate a corresponding target confidence level sequence in real time; Perform a real-time conversion process on the target confidence level sequence through a preset algorithm to generate the target confidence level in real time, and the target confidence level sequence is unique.

[0046] It should be noted that after the required target feature sequence and target envelope sequence are obtained in real time through the above steps, at this time, the current target feature sequence and the current target envelope sequence can be interspersed and fused through an existing interspersed fusion algorithm, and can be fused into a whole, that is, the required target confidence level sequence is generated in real time. Based on this, finally, the current target confidence level sequence is subjected to a real-time conversion process through the existing DTW algorithm, and the above target confidence level can be generated, so that the detection of various types of battery packs can be objectively and accurately completed, and at the same time, the process of manual participation can be omitted, corresponding to improving the detection efficiency of the battery pack.

[0047] Please refer to Figure 2 , the third embodiment of the present invention provides: A new energy battery pack detection system, wherein the system includes: A scanning module, configured to, when it is detected in real time that the battery pack is located in the target detection area, perform a full scan of the battery pack through a preset binocular vision system to detect in real time a plurality of target feature points corresponding to the battery pack; An acquisition module, configured to collect corresponding ultrasonic signals at each of the target feature points through a preset ultrasonic composite probe, and generate corresponding time-frequency spectrograms and envelope signals in real time according to the ultrasonic signals; A calculation module, configured to calculate in real time target confidence levels respectively corresponding to each of the target feature points based on a preset rule according to the time-frequency spectrograms and the envelope signals, and determine in real time whether the target confidence levels are greater than a preset confidence level threshold; A judgment module, configured to, if it is judged in real time that the target confidence level is greater than the preset confidence level threshold, correspondingly judge that the battery pack has no defects, and generate a corresponding detection report.

[0048] Further, the scanning module is specifically configured to: Collect in real time three-dimensional dimensions corresponding to the battery pack through the preset binocular vision system, and create in real time a target battery pack model adapted to the battery pack according to the three-dimensional dimensions through a preset three-dimensional program; Detect in real time a target model number corresponding to the battery pack through a preset database, and detect in real time a plurality of target feature points corresponding to the battery pack according to the target model number and the target battery pack model, and each of the target feature points is unique.

[0049] Further, the scanning module is specifically configured to: When the target model number is obtained in real time, determine in real time a plurality of components correspondingly included inside the battery pack according to the target model number; Create in real time component models respectively corresponding to each of the components inside the target battery pack model, and add corresponding target identifiers respectively; Detect in real time a plurality of the target feature points in the target battery pack model according to the target identifiers, and each of the target identifiers is unique.

[0050] Further, the scanning module is specifically configured to: When each of the target identifiers is marked in real time, detect respectively the fixed points and connection points correspondingly generated inside the target battery pack model by the component models corresponding to the target identifiers; Highlight the fixed points and the connection points in the target battery pack model, and correspondingly set the fixed points and the connection points as the target feature points, and each of the fixed points and each of the connection points is unique.

[0051] Further, the calculation module is specifically configured to: When the time-frequency spectrogram is obtained in real time, perform real-time parsing processing on the time-frequency spectrogram to detect in real time the spectral curves included in the time-frequency spectrogram; Detect in real time the starting point and the ending point of the spectral curve, and detect in real time several maximum points and several minimum points that appear in sequence in the spectral curve within the range of the starting point and the ending point; Set several of the maximum points and several of the minimum points as eigenvalues corresponding to the time-frequency spectrogram, and calculate in real time the target confidence levels corresponding to each of the target feature points according to the eigenvalues and the envelope signal. Each of the maximum points and each of the minimum points is relatively unique.

[0052] Further, the calculation module is specifically configured to: When the envelope signal is obtained in real time, match in real time the envelope values corresponding to each of the target feature points in the envelope signal; Create a corresponding target feature sequence according to the eigenvalues in real time, and create a corresponding target envelope sequence according to the envelope values in real time; Generate the target confidence levels of the target feature points according to the target feature sequence and the target envelope sequence. Each of the envelope values is unique.

[0053] Further, the calculation module is specifically configured to: When the target feature sequence and the target envelope sequence are obtained respectively, perform interleaving and fusion processing on the target feature sequence and the target envelope sequence to generate a corresponding target confidence level sequence in real time; Perform real-time conversion processing on the target confidence level sequence through a preset algorithm to generate the target confidence levels in real time. The target confidence level sequence is unique.

[0054] The fourth embodiment of the present invention provides a computer, including a memory, a processor, and a computer program stored on the memory and executable on the processor. Wherein, when the processor executes the computer program, the new energy battery pack detection method as described above is implemented.

[0055] The fifth embodiment of the present invention provides a readable storage medium, on which a computer program is stored. Wherein, when the program is executed by a processor, the new energy battery pack detection method as described above is implemented.

[0056] In summary, the new energy battery pack detection method and system provided by the above embodiments of the present invention can objectively and accurately complete the detection of the battery pack, and at the same time can eliminate the process of manual participation, correspondingly improving the detection efficiency of the battery pack.

[0057] It should be noted that the above-mentioned each module can be a functional module or a program module, and can be implemented either by software or by hardware. For the modules implemented by hardware, the above-mentioned each module can be located in the same processor; or the above-mentioned each module can also be located in different processors in any combined form.

[0058] The logic and / or steps represented in the flowchart or described in other ways herein, for example, can be considered as a definite sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus or device (such as a computer-based system, a system including a processor, or other systems that can fetch instructions from the instruction execution system, apparatus or device and execute the instructions), or in combination with these instruction execution systems, apparatus or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus or device.

[0059] More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection part with one or more wirings (electronic device), a portable computer diskette (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other media, then editing, interpreting or processing it in other suitable ways if necessary, and then storing it in a computer memory.

[0060] It should be understood that each part of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGA), field programmable gate arrays (FPGA), etc.

[0061] In the description of this specification, the descriptions referring to terms such as "one embodiment", "some embodiments", "examples", "specific examples", or "some examples", etc. mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0062] The above-described embodiments merely represent several implementation manners of the present invention. Their descriptions are relatively specific and detailed, but should not be construed as a limitation on the scope of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the appended claims.

Claims

1. A method for detecting a new energy battery pack, characterized in that, The method includes: When it is detected in real time that the battery pack is located in the target detection area, a full scan of the battery pack is performed through a preset binocular vision system to detect in real time a number of target feature points corresponding to the battery pack; The corresponding ultrasonic signals are collected in real time at each of the target feature points through a preset ultrasonic composite probe, and the corresponding time-frequency spectrogram and envelope signal are generated in real time according to the ultrasonic signals; Based on a preset rule, the target confidence corresponding to each of the target feature points is calculated in real time according to the time-frequency spectrogram and the envelope signal, and it is determined in real time whether the target confidence is greater than a preset confidence threshold; If it is determined in real time that the target confidence is greater than the preset confidence threshold, it is correspondingly determined that the battery pack has no defects, and a corresponding detection report is generated.

2. The new energy battery pack detection method according to claim 1, wherein: The step of performing a full scan of the battery pack through a preset binocular vision system to detect in real time a number of target feature points corresponding to the battery pack includes: The three-dimensional size corresponding to the battery pack is collected in real time through the preset binocular vision system, and a target battery pack model adapted to the battery pack is created in real time according to the three-dimensional size through a preset three-dimensional program; The target model corresponding to the battery pack is detected in real time through a preset database, and a number of target feature points corresponding to the battery pack are detected in real time according to the target model and the target battery pack model, and each of the target feature points is unique.

3. The new energy battery pack detection method according to claim 2, characterized in that: The step of detecting in real time a number of target feature points corresponding to the battery pack according to the target model and the target battery pack model includes: When the target model is obtained in real time, a number of components contained inside the battery pack are determined in real time according to the target model; Component models corresponding to each of the components are created in real time inside the target battery pack model, and corresponding target identifiers are added respectively; A number of the target feature points are detected in real time in the target battery pack model according to the target identifiers, and each of the target identifiers is unique.

4. The new energy battery pack detection method according to claim 3, characterized in that: The step of detecting in real time a number of the target feature points in the target battery pack model according to the target identifiers includes: When each of the target identifiers is marked in real time, the fixed points and connection points generated inside the target battery pack model corresponding to the component model corresponding to each of the target identifiers are detected respectively; In the target battery pack model, the fixed points and the connection points are highlighted, and the fixed points and the connection points are correspondingly set as the target feature points, and each of the fixed points and each of the connection points is unique.

5. The new energy battery pack detection method according to claim 1, characterized in that: The step of calculating in real time the target confidence corresponding to each of the target feature points based on a preset rule according to the time-frequency spectrogram and the envelope signal includes: When the time-frequency spectrogram is obtained in real time, real-time analysis processing is performed on the time-frequency spectrogram to detect in real time the spectral curves contained in the time-frequency spectrogram; The starting point and the ending point of the spectrum curve are detected in real time, and within the range of the starting point and the ending point, several maximum points and several minimum points that appear in sequence in the spectrum curve are detected in real time; Several of the maximum points and several of the minimum points are set as eigenvalues corresponding to the time-frequency spectrum diagram, and the target confidence corresponding to each of the target feature points is calculated in real time according to the eigenvalues and the envelope signal. Each of the maximum points and each of the minimum points is relatively unique.

6. The new energy battery pack detection method according to claim 5, wherein: The step of calculating the target confidence corresponding to each of the target feature points in real time according to the eigenvalues and the envelope signal includes: When the envelope signal is obtained in real time, the envelope value corresponding to each of the target feature points is matched in real time in the envelope signal; According to the eigenvalues, a corresponding target feature sequence is created in real time, and according to the envelope value, a corresponding target envelope sequence is created in real time; The target confidence of the target feature points is generated corresponding to the target feature sequence and the target envelope sequence. Each of the envelope values is unique.

7. The new energy battery pack detection method according to claim 6, wherein: The step of generating the target confidence of the target feature points corresponding to the target feature sequence and the target envelope sequence includes: When the target feature sequence and the target envelope sequence are respectively obtained, an interleaving and fusion process is performed on the target feature sequence and the target envelope sequence to generate a corresponding target confidence sequence in real time; The target confidence sequence is subjected to a real-time conversion process through a preset algorithm to generate the target confidence in real time. The target confidence sequence is unique.

8. A new energy battery pack detection system, characterized in that, The system includes: A scanning module, configured to, when it is detected in real time that the battery pack is located in the target detection area, perform a full scan on the battery pack through a preset binocular vision system to detect several target feature points corresponding to the battery pack in real time; An acquisition module, configured to collect corresponding ultrasonic signals at each of the target feature points through a preset ultrasonic composite probe, and generate a corresponding time-frequency spectrum diagram and envelope signal in real time according to the ultrasonic signals; A calculation module, configured to calculate the target confidence corresponding to each of the target feature points in real time based on a preset rule according to the time-frequency spectrum diagram and the envelope signal, and determine in real time whether the target confidence is greater than a preset confidence threshold; A judgment module, configured to, if it is judged in real time that the target confidence is greater than the preset confidence threshold, correspondingly judge that the battery pack has no defects and generate a corresponding detection report.

9. A computer, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the computer program, the new energy battery pack detection method described in any one of claims 1 to 7 is implemented.

10. A readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, the new energy battery pack detection method described in any one of claims 1 to 7 is implemented.

Images