AI quality inspection analysis method and system compatible with different complex materials

Abstract

The invention relates to the technical field of quality detection of plastic raw materials, in particular to an AI quality inspection analysis method and system compatible with different complex materials. The method comprises the following steps: determining a raw material category adopted by a to-be-detected plastic raw material according to order information, and carrying out batch identification on target raw materials according to the raw material category; calling a corresponding detection strategy to perform batch detection on the target raw materials under the condition that the category of the raw materials to be adopted is identified to be the same as that of the target raw materials; the detection strategy comprises a detection mode and a detection standard; and in response to the condition that the target raw material does not reach the corresponding detection standard, outputting the detection disqualification prompt information, thereby realizing full-process automatic detection starting from the material order information input, and effectively solving the problem of relatively low detection efficiency caused by the fact that the quality inspection of the plastic raw material mostly depends on manual judgment.

Description

Technical Field

[0001] The present application relates to the technical field of quality inspection of plastic raw materials, and in particular to an AI quality inspection and analysis method and system that is compatible with different complex materials. Background Art

[0002] Plastic plays an extremely important role in modern life. It is an indispensable material that is widely used in many fields such as industry, agriculture, packaging, construction, and medical treatment due to its lightness, durability, and strong plasticity. As the first link in the quality of plastic finished products, plastic raw materials are particularly important for quality control.

[0003] At present, when the types of plastic raw materials are complex, quality inspection mostly relies on manual judgment, and the detection efficiency is low. Summary of the invention

[0004] Based on this, it is necessary to provide an AI quality inspection and analysis method and system that is compatible with different complex materials to address the above technical issues.

[0005] In the first aspect, the present application provides an AI quality inspection and analysis method that is compatible with different complex materials, the method comprising:

[0006] Determine the raw material category that should be used for the plastic raw materials to be tested according to the order information, and perform batch identification of the target raw materials based on the raw material category;

[0007] When it is identified that the type of raw material to be used is the same as the target raw material, the corresponding detection strategy is called to perform batch detection on the target raw material; the detection strategy includes detection method and detection standard;

[0008] In response to the target raw material not meeting the corresponding detection standard, a detection failure prompt message is output.

[0009] In one embodiment, the method further comprises:

[0010] Determine the target product and the corresponding product use according to the order information, and analyze the characteristic levels required by the target product and the product use; the characteristic levels include multiple mechanical strength levels, multiple toughness levels, multiple pH application levels, and multiple temperature application levels corresponding to the raw material categories;

[0011] Based on the analysis results, the corresponding characteristic level of the target product is determined, and based on the corresponding characteristic level, the raw material category that should be used for the plastic raw material to be tested is determined.

[0012] In one embodiment, the raw material categories include HDPE, LDPE and LLDPE; and the step of batch identifying the target raw material according to the raw material category includes:

[0013] Randomly selecting plastic raw material samples at multiple points in the target raw materials of this batch, and performing a first pretreatment operation on the plastic raw material samples to obtain pretreated samples; the first pretreatment operation includes performing a compression and expansion operation on the plastic raw material samples according to a preset pressure intensity;

[0014] Irradiating the plastic raw material sample after the compression and spreading operation according to a preset light intensity, and obtaining the light transmittance of the plastic raw material sample during the irradiation process;

[0015] The pre-stored database is called according to the transmittance of the plastic raw material sample and the rebound rate of the pre-treated sample after the compression and expansion operation to obtain the raw material category of the plastic raw material sample; the pre-stored database includes data corresponding to the rebound rate under preset pressure of HDPE, LDPE and LLDPE respectively, and the transmittance of HDPE, LDPE and LLDPE respectively.

[0016] In one embodiment, the method further comprises:

[0017] In response to the presence of a plurality of plastic raw material samples with different light transmittances and rebound rates, determining the raw material category of each plastic raw material sample based on a pre-stored database;

[0018] If there are multiple raw material categories, a prompt message indicating that the target raw material is not single is output; otherwise, a prompt message indicating impurity particles is output.

[0019] In one embodiment, the method further comprises:

[0020] Acquire image data of the target raw material collected in a preset manner and perform a second preprocessing operation; the preset manner includes selecting a preset number of plastic raw material samples and laying them on a background plate with a preset light intensity, and collecting image data of the target raw material; the preset light intensity corresponds to the light transmittance of each plastic raw material;

[0021] Performing a second preprocessing operation on the image data to obtain preprocessed image data; the second preprocessing operation includes denoising, enhancement and grayscale processing;

[0022] Extracting impurity information from the preprocessed image based on a preset grayscale value;

[0023] In response to determining based on the impurity information that the amount of raw materials containing impurities in the target raw materials exceeds a first preset value, outputting warning prompt information.

[0024] In one embodiment, the step of calling the corresponding detection strategy to perform batch detection on the target raw material further includes:

[0025] In response to the target raw material corresponding to the early warning prompt information being HDPE, a sample of the target raw material of HDPE is tested according to a first preset pressure strength, a first preset tensile strength, and a first preset impact strength; if the test passes, a detection qualified prompt information is output, otherwise, a detection unqualified prompt information is output;

[0026] In response to the target raw material corresponding to the early warning prompt information being LDPE, a sample of the target raw material of LDPE is tested according to the second preset pressure strength, the second preset tensile strength and the second preset impact strength; if the test passes, a detection qualified prompt information is output, otherwise, a detection unqualified prompt information is output;

[0027] In response to the target raw material corresponding to the early warning prompt information being LLDPE, samples of the target raw material of LLDPE are tested according to the first preset pressure strength, the third preset tensile strength and the first preset impact strength; if the test passes, a detection qualified prompt information is output, otherwise a detection unqualified prompt information is output.

[0028] In the second aspect, the present application provides an AI quality inspection and analysis system that is compatible with different complex materials, and the system includes:

[0029] An identification module is used to determine the raw material category that should be used for the plastic raw materials to be tested according to the order information, and to perform batch identification of the target raw materials according to the raw material category;

[0030] A calling module is used to call a corresponding detection strategy to perform batch detection on the target raw materials when it is identified that the type of the raw materials to be used is the same as the target raw materials; the detection strategy includes a detection method and a detection standard;

[0031] The output module is used to output detection failure prompt information in response to the target raw material failing to meet the corresponding detection standard.

[0032] In a third aspect, the present application provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the method provided in the first aspect of the present application are implemented.

[0033] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method provided in the first aspect of the present application.

[0034] In a fifth aspect, the present application provides a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of the method provided in the first aspect of the present application.

[0035] The above-mentioned AI quality inspection and analysis method and system that is compatible with different complex materials can reversely infer the raw material category required in this batch of orders based on the order information, and judge whether the target raw materials are the same according to the raw material category required to be used, so as to ensure the accuracy of plastic raw material supply; when they are identified to be the same, the target raw materials are tested in accordance with the detection method and detection standard corresponding to the target raw materials, so as to ensure targeted testing in the environment of multi-material production lines and ensure the accuracy of the detection; if the targeted detection fails, a prompt message of unqualified detection is output; and full automated detection is realized starting from the input of material order information, effectively solving the problem of low detection efficiency caused by the reliance on manual judgment for quality inspection of plastic raw materials. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0037] Figure 1 A schematic diagram of the steps of batch identification of target raw materials in one embodiment;

[0038] Figure 2 A schematic diagram of the steps for determining the type of raw material to be used based on the required characteristic level in one embodiment;

[0039] Figure 3 A schematic diagram of the steps of analyzing the raw material type of a plastic raw material sample in one embodiment;

[0040] Figure 4 A schematic diagram of the steps for determining the homogeneity of a target raw material in one embodiment;

[0041] Figure 5 A schematic diagram of the steps for determining impurities in a target raw material in one embodiment;

[0042] Figure 6 The present invention is a framework diagram of an AI quality inspection and analysis system that is compatible with materials of different complexities in one embodiment. DETAILED DESCRIPTION

[0043] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are described in detail below in conjunction with the accompanying drawings. In the following description, many specific details are set forth to facilitate a full understanding of the present application. However, the present application can be implemented in many other ways different from those described herein, and those skilled in the art can make similar improvements without violating the connotation of the present application, so the present application is not limited by the specific embodiments disclosed below.

[0044] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, "plurality" means at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0045] In an exemplary embodiment, Figure 1 As shown, the present application provides an AI quality inspection and analysis method that is compatible with different complex materials, and the method includes the following steps S102 to S106. Among them:

[0046] Step S102, determining the raw material category that should be used for the plastic raw material to be inspected according to the order information, and performing batch identification of the target raw material according to the raw material category.

[0047] The order information may include the product name, specifications and application requirements of the plastic raw material to be tested; based on the order information, the raw material category that should be used for the plastic raw material to be tested can be determined.

[0048] Specifically, when the type of raw materials to be used is determined, batch type identification of the target raw materials at the raw material supply end entering the production line can effectively ensure that the products produced based on the target raw materials can meet the order requirements.

[0049] Step S104, when it is identified that the type of raw material to be used is the same as the target raw material, the corresponding detection strategy is called to perform batch detection on the target raw material; the detection strategy includes a detection method and a detection standard.

[0050] Specifically, the detection strategy can be multiple different strategies corresponding to the raw material type of the target raw material. After identifying the raw material type, by selecting the corresponding detection strategy, it can effectively ensure that in the face of complex detection conditions of multiple materials, the target material can be accurately detected through the corresponding detection strategy.

[0051] It is understandable that different target materials may have different mechanical strength, tensile strength or corrosion resistance, and in some application scenarios, it is not important whether certain materials have corrosion resistance. Therefore, if corrosion resistance testing is still performed when the same testing strategy is adopted, it is a redundant step. On this basis, the use of targeted raw material testing methods can improve testing efficiency and improve testing accuracy.

[0052] Step S106, in response to the target raw material not meeting the corresponding detection standard, outputting detection failure prompt information.

[0053] The detection failure prompt information may include the raw material type, test items and test results of the target raw material.

[0054] The embodiment of the present application provides an AI quality inspection and analysis method that is compatible with different complex materials. It can reversely infer the raw material category required in this batch of orders based on the order information, and judge whether the target raw materials are the same according to the raw material category required to be used, so as to ensure the accuracy of plastic raw material supply; when they are identified to be the same, the target raw materials are inspected according to the inspection method and inspection standard corresponding to the target raw materials, so as to ensure that targeted inspection can be carried out in the environment of a multi-material production line to ensure the accuracy of the inspection; if the targeted inspection fails, an inspection failure prompt message is output; and full automated inspection starting from the input of material order information is realized, effectively solving the problem of low inspection efficiency caused by the reliance on manual judgment for quality inspection of plastic raw materials.

[0055] In one embodiment, if Figure 2 As shown, the method also includes the following steps S202 to S204.

[0056] in:

[0057] Step S202, determining the target product and the corresponding product use according to the order information, and analyzing the characteristic levels required by the target product and the product use; the characteristic levels include multiple mechanical strength levels, multiple toughness levels, multiple pH application levels, and multiple temperature application levels corresponding to the raw material categories.

[0058] Specifically, according to the design specifications and structure of the target product itself, it is possible to know the ductility, toughness and mechanical strength that the target product needs to have. For example, if the target product is a plastic film, the highest mechanical strength and lower toughness are required.

[0059] Furthermore, according to whether the product is used as a seasoning box or an organic solvent container, the acid resistance, alkali resistance and salt resistance required by the target product can be determined, thereby effectively determining the characteristic level of the target product for the target product and the corresponding use.

[0060] In the specific implementation process, the target raw materials can be divided into multiple characteristic levels according to the requirements of the target products and the raw material types; each characteristic level corresponds to multiple mechanical strength levels, multiple toughness levels, multiple pH application levels and multiple temperature application levels of the raw material category, which can provide a basis for the selection of raw material types.

[0061] Step S204, determining the characteristic level corresponding to the target product based on the analysis result, and determining the raw material category that should be used for the plastic raw material to be tested based on the corresponding characteristic level.

[0062] In an exemplary embodiment, the target raw material may include HDPE, LDPE and LLDPE, where HDPE (high-density polyethylene), LDPE (low-density polyethylene) and LLDPE (linear low-density polyethylene) are three main types of polyethylene, which differ in density, crystallinity, molecular structure, mechanical properties, heat resistance, chemical resistance, etc. Specific parameters include:

[0063] HDPE (high-density polyethylene): density, 0.940 ~ 0.976g / cm3; crystallinity, 85-65%; softening point, 125-135℃, resistant to acid, alkali and various salts; insoluble in any organic solvents. LDPE (low-density polyethylene): density: 0.910 ~ 0.940g / cm3 crystallinity: 45-65%; softening point: 90-100℃; resistant to acid, alkali and salt solution corrosion, but poor solvent resistance. LLDPE (linear low-density polyethylene) density: 0.915 ~ 0.935g / cm3 crystallinity: 55-65%; softening point: 94-108℃: resistant to acid, alkali and organic solvents.

[0064] Furthermore, the mechanical strength of HDPE is higher than that of LLDPE, and the mechanical strength of LLDPE is higher than that of LDPE; the toughness of LLDPE is higher than that of HDPE, and the toughness of HDPE is higher than that of LDPE;

[0065] Furthermore, the temperature range that HDPE can withstand is -40°C to 90°C; the temperature range that LLDPE can withstand is -40°C to 90°C; and the temperature range that LDPE can withstand is -60°C to 80°C.

[0066] Based on the multiple mechanical strength levels, multiple toughness levels, multiple pH application levels, and multiple temperature application levels of each raw material category determined in the above specific implementation process, the corresponding raw material category can be effectively selected according to the required characteristic level.

[0067] In one embodiment, the raw material category includes HDPE, LDPE and LLDPE; Figure 3As shown, batch identification of target raw materials according to raw material categories includes the following steps S1022 to S1026.

[0068] in:

[0069] Step S1022, randomly selecting plastic raw material samples at multiple points in the target raw material of this batch, and performing a first pretreatment operation on the plastic raw material samples to obtain pretreated samples; the first pretreatment operation includes performing a compression and expansion operation on the plastic raw material samples according to a preset pressure intensity.

[0070] Specifically, since HDPE, LDPE and LLDPE have different toughness and mechanical strength, they have different rebound rates when subjected to compression and stretching operations. The rebound rate corresponding to the specific raw material type is not specifically limited herein.

[0071] Step S1024, irradiating the plastic raw material sample after the compression and expansion operation according to a preset light intensity, and obtaining the light transmittance of the plastic raw material sample during the irradiation process.

[0072] Specifically, different transmittances can be produced based on different rebound rates after the pretreatment operation. In addition, HDPE, LDPE and LLDPE themselves have different transmittances, but there is a certain degree of overlap. However, in combination with the compression and expansion operation, the transmittances of raw material types with different rebound rates can be effectively distinguished.

[0073] Step S1026, calling the pre-stored database according to the transmittance of the plastic raw material sample and the rebound rate of the pre-treated sample after the compression and expansion operation to obtain the raw material category of the plastic raw material sample; the pre-stored database includes data corresponding to the rebound rate under preset pressure of HDPE, LDPE and LLDPE respectively, and the transmittance of HDPE, LDPE and LLDPE respectively.

[0074] In one embodiment, if Figure 4 As shown, the method also includes the following steps S302 to S304.

[0075] in:

[0076] Step S302 , in response to the presence of a plurality of plastic raw material samples with different light transmittances and rebound rates, determining the material category of each plastic raw material sample based on a pre-stored database.

[0077] Step S304: if there are multiple raw material categories, output prompt information that the target raw material is not single, otherwise output impurity particle prompt information.

[0078] Specifically, during the specific production process, the raw materials may contain other types of raw materials due to human error, thus affecting the product quality, or the raw materials themselves may contain certain product impurities. Therefore, raw material sample testing through transmittance and rebound rate can identify mixed materials and impurities.

[0079] In one embodiment, if Figure 5 As shown, the method also includes the following steps S402 to S408.

[0080] in:

[0081] Step S402, obtaining image data of the target raw material collected according to a preset method and performing a second preprocessing operation; the preset method includes selecting a preset number of plastic raw material samples and laying them on a background plate with a preset light intensity, and collecting image data of the target raw material; the preset light intensity corresponds to the transmittance of each plastic raw material.

[0082] Specifically, since the transmittance of each plastic raw material sample is not the same, such as the transmittance of HDPE is significantly lower than that of LDPE, when judging the internal impurities of the plastic raw material sample through image recognition, it is easy to fail to obtain a clear image due to the low transmittance; in this case, by increasing the transmittance of a background plate with a preset light intensity, the internal impurities of the plastic raw material can be effectively obtained.

[0083] Step S404, performing a second preprocessing operation on the image data to obtain preprocessed image data; the second preprocessing operation includes denoising, enhancement and grayscale processing.

[0084] Specifically, denoising and enhancement can effectively increase image clarity, while grayscale processing can effectively increase image contrast, making it easier to detect impurities.

[0085] Step S406: extracting impurity information in the preprocessed image based on a preset grayscale value.

[0086] Specifically, since impurities are mostly dark or even black and have obvious characteristics compared to the raw material itself, by setting the grayscale value corresponding to the impurity, the overall image remains clearer and the impurity contrast is higher, thereby extracting the impurity information.

[0087] Furthermore, in the process of extracting impurity information, an impurity extraction threshold may be set for a preset grayscale value, thereby extracting impurity information.

[0088] Step S408: in response to determining based on the impurity information that the amount of raw materials containing impurities in the target raw materials exceeds a first preset value, outputting a warning prompt message.

[0089] Specifically, the first preset value may be set based on the product requirements in the order information.

[0090] In one embodiment, the step of calling the corresponding detection strategy to perform batch detection on the target raw materials also includes the following steps:

[0091] In response to the target raw material corresponding to the early warning prompt information being HDPE, a sample of the target raw material of HDPE is tested according to a first preset pressure strength, a first preset tensile strength, and a first preset impact strength; if the test passes, a detection qualified prompt information is output, otherwise, a detection unqualified prompt information is output;

[0092] In response to the target raw material corresponding to the early warning prompt information being LDPE, a sample of the target raw material of LDPE is tested according to the second preset pressure strength, the second preset tensile strength and the second preset impact strength; if the test passes, a detection qualified prompt information is output, otherwise, a detection unqualified prompt information is output;

[0093] In response to the target raw material corresponding to the early warning prompt information being LLDPE, samples of the target raw material of LLDPE are tested according to the first preset pressure strength, the third preset tensile strength and the first preset impact strength; if the test passes, a detection qualified prompt information is output, otherwise a detection unqualified prompt information is output.

[0094] Specifically, in the case of outputting warning information of impurities, in order to further determine whether the impurities have an impact on the target product and thus cause the target product to fail to meet the standards, the detection strategy corresponding to the target raw material can be called.

[0095] Further, in the case of determining the characteristics of the target raw material, specific compressive strength, tensile strength, and impact strength may be set to determine the loss of characteristics of the target raw material when impurities are included.

[0096] Specifically, since the pressure strength of HDPE is similar to that of LLDPE, the first preset pressure strength can be used to test HDPE and LLDPE, and since the pressure strength of LDPE is lower than that of HDPE and LLDPE, the second preset pressure strength can be used to test LDPE, wherein the first preset pressure strength is greater than the second preset pressure strength.

[0097] Furthermore, since the tensile strength of HDPE is greater than that of LDPE and greater than that of LLDPE, HDPE is tested according to the first preset tensile strength, LDPE is tested according to the second preset tensile strength, and LLDPE is tested according to the third tensile strength, wherein the first preset tensile strength is greater than the second preset tensile strength and greater than the third preset tensile strength.

[0098] Furthermore, since the impact strength of HDPE is similar to that of LLDPE, the first preset impact strength can be used to test HDPE and LLDPE, and since the impact strength of LDPE is lower than that of HDPE and LLDPE, the second preset impact strength can be used to test LDPE, wherein the first preset impact strength is greater than the second preset impact strength.

[0099] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indications of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless there is a clear description in this article, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0100] Based on the same inventive concept, the embodiment of the present application also provides an AI quality inspection and analysis system compatible with different complex materials for implementing the above-mentioned AI quality inspection and analysis method compatible with different complex materials. The implementation solution provided by the system to solve the problem is similar to the implementation solution recorded in the above method, so the specific limitations in one or more embodiments of the AI ​​quality inspection and analysis system compatible with different complex materials provided below can be referred to the above limitations on an AI quality inspection and analysis method compatible with different complex materials, and will not be repeated here.

[0101] Second, as Figure 6 As shown, the present application also provides an AI quality inspection and analysis system that is compatible with different complex materials, and the system includes:

[0102] The identification module 601 is used to determine the raw material category that should be used for the plastic raw material to be tested according to the order information, and to perform batch identification of the target raw material according to the raw material category;

[0103] The calling module 602 is used to call the corresponding detection strategy to perform batch detection on the target raw materials when it is identified that the type of the raw materials to be used is the same as the target raw materials; the detection strategy includes the detection method and the detection standard;

[0104] The output module 603 is used to output detection failure prompt information in response to the target raw material failing to meet the corresponding detection standard.

[0105] On the third aspect, the present application also provides a computer device including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, it implements the steps of an AI quality inspection and analysis method as described above that is compatible with different complex materials.

[0106] In a fourth aspect, the present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of an AI quality inspection and analysis method as described above that is compatible with different complex materials are implemented.

[0107] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of an AI quality inspection and analysis method as described above that is compatible with different complex materials.

[0108] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0109] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0110] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. An AI quality inspection and analysis method compatible with different complex materials, characterized in that: The method comprises: Determine the raw material category that should be used for the plastic raw materials to be tested according to the order information, and perform batch identification of the target raw materials according to the raw material category; When it is identified that the type of the raw material to be used is the same as the target raw material, calling a corresponding detection strategy to perform batch detection on the target raw material; the detection strategy includes a detection method and a detection standard; In response to the target raw material failing to meet the corresponding detection standard, outputting detection failure prompt information.

2. The method according to claim 1, characterized in that The method further comprises: Determine the target product and the corresponding product use according to the order information, and analyze the characteristic levels required by the target product and the product use; the characteristic levels include multiple mechanical strength levels, multiple toughness levels, multiple pH application levels, and multiple temperature application levels corresponding to the raw material category; The characteristic level corresponding to the target product is determined based on the analysis result, and the raw material category that should be used for the plastic raw material to be tested is determined based on the corresponding characteristic level.

3. The method according to claim 2, characterized in that The raw material categories include HDPE, LDPE and LLDPE; the step of batch identifying the target raw material according to the raw material categories includes: Randomly selecting plastic raw material samples at multiple points in the target raw material of this batch, and performing a first pretreatment operation on the plastic raw material samples to obtain pretreated samples; the first pretreatment operation includes performing a compression and expansion operation on the plastic raw material samples according to a preset pressure intensity; Irradiating the plastic raw material sample after the compression and spreading operation according to a preset light intensity, and obtaining the light transmittance of the plastic raw material sample during the irradiation process; According to the transmittance of the plastic raw material sample and the rebound rate of the pretreated sample after the compression and expansion operation, the pre-stored database is called to obtain the raw material category of the plastic raw material sample; the pre-stored database includes data corresponding to the rebound rate under the preset pressure of the HDPE, the LDPE and the LLDPE respectively, and the transmittance corresponding to the HDPE, the LDPE and the LLDPE respectively.

4. The method according to claim 3, characterized in that The method further comprises: In response to the presence of a plurality of plastic raw material samples having different light transmittances and rebound rates, determining the raw material category of each of the plastic raw material samples based on the pre-stored database; If there are multiple types of raw materials, prompt information indicating that the target raw material is not unique is output; otherwise, prompt information indicating impurity particles is output.

5. The method according to claim 3, characterized in that: The method further comprises: Acquire the image data of the target raw material collected in a preset manner and perform a second preprocessing operation; the preset manner includes selecting a preset number of the plastic raw material samples and laying them on a background plate with a preset light intensity, and collecting the image data of the target raw material; the preset light intensity corresponds to the transmittance of each of the plastic raw materials; Performing a second preprocessing operation on the image data to obtain preprocessed image data; the second preprocessing operation includes denoising, enhancement and grayscale processing; Extracting impurity information in the preprocessed image based on a preset grayscale value; In response to determining based on the impurity information that the amount of raw materials containing impurities in the target raw material exceeds a first preset value, outputting warning prompt information.

6. The method according to claim 5, characterized in that The step of calling the corresponding detection strategy to perform batch detection on the target raw materials also includes: In response to the target raw material corresponding to the early warning prompt information being the HDPE, a sample of the target raw material of the HDPE is tested according to a first preset pressure strength, a first preset tensile strength, and a first preset impact strength; if the test passes, a qualified detection prompt information is output; otherwise, a failed detection prompt information is output; In response to the target raw material corresponding to the early warning prompt information being the LDPE, a sample of the target raw material of the LDPE is tested according to the second preset pressure strength, the second preset tensile strength and the second preset impact strength; if the test passes, a qualified detection prompt information is output, otherwise, the unqualified detection prompt information is output; In response to the target raw material corresponding to the early warning prompt information being the LLDPE, samples of the target raw material of the LLDPE are tested according to the first preset pressure strength, the third preset tensile strength and the first preset impact strength; if the test passes, a qualified test prompt information is output, otherwise, the unqualified test prompt information is output.

7. An AI quality inspection and analysis system compatible with different complex materials, characterized in that: The system comprises: An identification module, used to determine the raw material category that should be used for the plastic raw material to be tested according to the order information, and to perform batch identification of the target raw material according to the raw material category; A calling module, for calling a corresponding detection strategy to perform batch detection on the target raw materials when it is identified that the type of the raw materials to be used is the same as the target raw materials; the detection strategy includes a detection method and a detection standard; The output module is used to output detection failure prompt information in response to the target raw material failing to meet the corresponding detection standard.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

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

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images