An AI analysis-based industrial automation production process optimization method and system

Abstract

The application is suitable for the technical field of electrical cabinet production management and artificial intelligence analysis, and provides an industrial automatic production process optimization method and system based on AI analysis.The method comprises the following steps: sorting samples according to a wire harness stacking parameter, obtaining a sample sequence, and analyzing whether the sample sequence meets a preset specific mode.The preset specific mode comprises the following conditions: the extrusion effect index and the additional energy consumption are in a gentle change state within an initial range of the sample sequence, there is a sample section composed of a preset number of adjacent samples in the sample sequence, and the extrusion effect index and the additional energy consumption synchronously occur a turning point rise in the sample section.The application synchronously models the wire harness stacking state, the extrusion effect index and the terminal crimping energy consumption by using visual recognition and AI analysis, can accurately identify the threshold section with high energy consumption, and generates an executable reference stacking standard.

Description

Technical Field

[0001] This invention relates to the fields of electrical cabinet production management and artificial intelligence analysis technology, and in particular to an industrial automation production process optimization method and system based on AI analysis. Background Technology

[0002] In the field of electrical cabinet production management, with the widespread adoption of automated equipment, the quality of wiring, crimping, and overall energy efficiency control within electrical cabinets have gradually become key factors affecting production efficiency and product consistency. In existing production processes, the wiring process in cable trays is mostly done manually or semi-manually, with operators laying the wire harnesses in the trays based on experience. Subsequently, the electrical cabinet enters the terminal crimping process, where crimping equipment completes the terminal connections. Existing technologies typically possess basic visual inspection or process monitoring methods, but these are largely limited to traditional inspection points such as whether the wiring meets structural requirements and whether the terminal crimping is secure. They struggle to deeply analyze the indirect impact of wiring variations on subsequent processes. Therefore, in most production lines, wiring variations are generally considered normal process fluctuations and are not systematically quantified and managed.

[0003] However, a phenomenon that has long been underrecognized in actual production in this field is that some electrical cabinets experience a slight but stable increase in energy consumption during the terminal crimping process. Existing technologies typically attribute such slight deviations to transient fluctuations in the crimping equipment itself, process tolerances, or differences in operating rhythm. Because this energy consumption change does not reach the alarm threshold, it is difficult to identify its true cause using traditional monitoring systems. This prevents the production line from establishing a causal chain from the wiring process to the crimping process, thus hindering the development of effective wiring optimization strategies and the prevention of potential losses caused by slight overloads in the crimping equipment. Simultaneously, existing systems lack in-depth quantitative methods for assessing the stacking state of wire harnesses, failing to identify subsequent compression caused by wiring differences during handling, vibration, or opening / closing operations.

[0004] Based on the above situation, the existing technology has obvious shortcomings in its ability to identify the impact of the wiring process on subsequent energy consumption and equipment load. These shortcomings are mainly reflected in the following aspects: the inability to quantify wiring differences, the inability to identify post-extrusion of wire harnesses, the inability to establish the coupling relationship between extrusion effect and crimping energy consumption, the inability to formulate executable wiring optimization indicators, and the inability to take preventive measures in the early stages of the process to avoid the crimping equipment being in a state of slight overload for a long time. Summary of the Invention

[0005] The purpose of this invention is to provide an AI-based method and system for optimizing industrial automated production processes, aiming to solve the problems mentioned in the background art.

[0006] This invention is implemented as follows: an AI-based method for optimizing industrial automation production processes, the method comprising: Obtain historical processing records of the production line for the target type of electrical cabinet, and select several samples from them where the wiring process conditions are consistent except for the wire harness stacking parameters in the wire tray wiring process. The sample was analyzed to identify the squeezing effect index of the wire harness located in the preset wire trough area before the terminal crimping process, and to identify the additional energy consumption generated by the terminal crimping process relative to the preset energy consumption requirement when performing the crimping operation. The samples are sorted according to the wire harness stacking parameters to obtain a sample sequence, and the sample sequence is analyzed to see if it meets a preset specific pattern. The preset specific pattern includes: the squeezing effect index and the additional energy consumption are in a state of gradual change in the initial range of the sample sequence, and there is a sample segment in the sample sequence consisting of a preset number of adjacent samples, in which the squeezing effect index and the additional energy consumption simultaneously undergo a turning point increase. If the condition is met, a baseline stacking standard for the target type electrical cabinet in the wire tray wiring process is generated based on the wire harness stacking parameters corresponding to the sample section, and subsequent wiring processes are executed according to the baseline stacking standard.

[0007] As a further limitation of the technical solution of the present invention, the calculation of the wire harness stacking parameters includes: based on the wire harness image after the wire grooving process is completed by visual acquisition, identifying the local stacking state features of the wire harness in the preset wire grooving area due to the difference in wire arrangement, the stacking state features include at least one: the degree of fit between wire harnesses, the amount of local compression, the offset of the wire arrangement path or the local density of the wire harness, and generating the wire harness stacking parameters based on the stacking state features.

[0008] As a further limitation of the technical solution of the present invention, the calculation of the squeezing effect index includes: based on the image of the wire harness located in the preset wire groove area before the electrical cabinet enters the terminal crimping process, which is obtained by visual acquisition, identifying the squeezing state characteristics of the wire harness in the preset wire groove area, wherein the squeezing state characteristics include at least one: the degree of deformation of the wire harness cross section, the local height change of the wire harness relative to its reference height in the natural spreading state, or the minimum spacing between the wire harnesses; and generating the squeezing effect index based on the squeezing state characteristics.

[0009] As a further limitation of the technical solution of this embodiment of the invention, the steps of sorting the samples according to the wire harness stacking parameters to obtain a sample sequence and analyzing whether the sample sequence meets a preset specific pattern include: The samples are sorted from smallest to largest according to the bundle stacking parameters to obtain a sample sequence, and the changing trends of the squeezing effect index and the additional energy consumption corresponding to the sample sequence are extracted. The changing trends of the squeezing effect index and the changing trends of the additional energy consumption are analyzed simultaneously to determine whether they meet the preset specific mode.

[0010] As a further limitation of the technical solution of this embodiment of the invention, if it is determined that the conditions are met, then the following steps are taken to generate a reference stacking standard for the target type electrical cabinet in the wire tray wiring process based on the wire harness stacking parameters corresponding to the sample section, and to make the subsequent wiring process perform according to the reference stacking standard: If a preset specific pattern is determined to exist in the sample sequence, select the bundle stacking parameters of all samples corresponding to the sample segment, and calculate the average value of the bundle stacking parameters; The average value is set as the benchmark stacking standard for the wiring process of the target type electrical cabinet in the online trunking, and subsequent wiring processes are performed in accordance with the benchmark stacking standard.

[0011] An AI-based industrial automation production process optimization system, the system comprising: The data acquisition module is used to acquire the historical processing records of the production line of the target type of electrical cabinet, and to select several samples from them in which the wiring process conditions are consistent except for the wire harness stacking parameters. The index recognition module is used to analyze samples, identify the squeezing effect index of the wire harness located in the preset wire trough area before the electrical cabinet enters the terminal crimping process, and identify the additional energy consumption generated by the terminal crimping process relative to the preset energy consumption requirement when performing the crimping operation. The pattern analysis module is used to sort the samples according to the wire harness stacking parameters, obtain the sample sequence, and analyze whether the sample sequence meets the preset specific pattern. The preset specific pattern includes: the squeezing effect index and the additional energy consumption are in a state of gradual change in the initial range of the sample sequence, and there is a sample segment in the sample sequence consisting of a preset number of adjacent samples, in which the squeezing effect index and the additional energy consumption simultaneously undergo a turning point increase. The benchmark generation module is used to generate a benchmark stacking standard for the target type electrical cabinet in the wire tray wiring process based on the wire harness stacking parameters corresponding to the sample section if it is determined that the standard is met, and to make the subsequent wiring process execute according to the benchmark stacking standard.

[0012] As a further limitation of the technical solution of the present invention, the calculation of the wire harness stacking parameters includes: based on the wire harness image after the wire grooving process is completed by visual acquisition, identifying the local stacking state features of the wire harness in the preset wire grooving area due to the difference in wire arrangement, the stacking state features include at least one: the degree of fit between wire harnesses, the amount of local compression, the offset of the wire arrangement path or the local density of the wire harness, and generating the wire harness stacking parameters based on the stacking state features.

[0013] As a further limitation of the technical solution of the present invention, the calculation of the squeezing effect index includes: based on the image of the wire harness located in the preset wire groove area before the electrical cabinet enters the terminal crimping process, which is obtained by visual acquisition, identifying the squeezing state characteristics of the wire harness in the preset wire groove area, wherein the squeezing state characteristics include at least one: the degree of deformation of the wire harness cross section, the local height change of the wire harness relative to its reference height in the natural spreading state, or the minimum spacing between the wire harnesses; and generating the squeezing effect index based on the squeezing state characteristics.

[0014] As a further limitation of the technical solution of this embodiment of the invention, the pattern analysis module specifically includes: The sorting unit is used to sort the samples in ascending order of the wire harness stacking parameters to obtain a sample sequence, and extract the squeezing effect index change trend and the additional energy consumption change trend corresponding to the sample sequence. The trend analysis unit is used to simultaneously analyze the changing trend of the squeezing effect index and the changing trend of the additional energy consumption to determine whether the two meet the preset specific pattern.

[0015] As a further limitation of the technical solution of this embodiment of the invention, the benchmark generation module specifically includes: The parameter acquisition unit is used to select the bundle stacking parameters of all samples corresponding to the sample segment if a preset specific pattern is determined to exist in the sample sequence, and to calculate the average value of the bundle stacking parameters. The reference setting unit is used to set the average value as the reference stacking standard for the wire tray wiring process of the target type electrical cabinet, and to make the subsequent wiring process perform according to the reference stacking standard.

[0016] Compared with the prior art, the present invention has the following beneficial effects: This invention analyzes the energy consumption correlation between the wire harness routing process and the terminal crimping process, identifying that the subsequent wire harness compression caused by routing differences is the true cause of slight energy consumption anomalies in the crimping equipment. Such routing differences have long been considered normal process fluctuations and overlooked in existing technologies. This invention utilizes visual recognition and AI analysis to simultaneously model the wire harness stacking state, compression effect index, and terminal crimping energy consumption. It can accurately identify high-energy-consumption threshold segments and generate executable benchmark stacking standards. By controlling the stacking state in advance during the routing process, the additional energy consumption of the terminal crimping process can be significantly reduced, preventing performance degradation or shortened component lifespan due to repeated slight overload conditions, thus effectively protecting the load equipment. This invention transforms the routing process from being "considered normal" to being "quantifiable and controllable," possessing clear energy-saving effects and equipment protection value. Attached Figure Description

[0017] Figure 1 A flowchart of the method provided in the embodiments of the present invention; Figure 2 This is a flowchart illustrating the synchronous analysis of changing trends in the method provided in this embodiment of the invention; Figure 3 This is a flowchart illustrating the process of establishing a benchmark stacking standard in the method provided by an embodiment of the present invention; Figure 4 Application architecture diagram of the system provided in the embodiments of the present invention; Figure 5 This is a structural block diagram of the pattern analysis module in the system provided in the embodiments of the present invention; Figure 6 This is a structural block diagram of the benchmark generation module in the system provided in the embodiment of the present invention. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0019] Figure 1 A flowchart of the method provided by an embodiment of the present invention is shown.

[0020] Specifically, an AI-based method for optimizing industrial automation production processes includes the following steps: Step S100: Obtain the historical processing records of the production line for the target type of electrical cabinet, and select several samples from them where the wiring process conditions are consistent except for the wire harness stacking parameters.

[0021] The calculation of the wire harness stacking parameters includes: based on the wire harness image after the wire grooving process is completed by visual acquisition, identifying the local stacking state characteristics of the wire harness in the preset wire grooving area due to the difference in wire arrangement, the stacking state characteristics include at least one: the degree of fit between wire harnesses, the amount of local compression, the offset of the wire arrangement path or the local density of the wire harness, and generating the wire harness stacking parameters based on the stacking state characteristics.

[0022] In this embodiment of the invention, the target type electrical cabinet mentioned in step S100 can be a variety of electrical cabinets with different structures and uses, depending on the actual business needs of the production line. For example, it can be a control cabinet suitable for mechanical equipment, a distribution cabinet used in the power industry, an automation control cabinet for building systems, a drive cabinet for industrial robot systems, and other electrical cabinets with dense wiring structures and including cable tray wiring processes. In practical applications, different types of electrical cabinets differ in structural layout, cable tray wiring methods, and wire harness density, but all require manual or semi-automatic wire harness layout in the cable tray wiring process, and therefore can all be considered as target types.

[0023] The wire duct cabling process typically refers to the process of laying multiple wire harnesses vertically or horizontally into the wire duct according to process requirements and fixing them in place during the assembly of electrical cabinets. This process still relies on manual labor in most electrical cabinet production lines because the flexibility, deformability, and susceptibility of wire harnesses to environmental influences make it difficult to fully automate. In this process, wire harnesses need to be organized, stacked, and laid according to specifications, circuits, and uses, and local areas are sealed using wire duct covers to form the initial stacked state of the wire harnesses.

[0024] Terminal crimping is typically performed after the wiring process. In this step, the wire harnesses are led out and their metal terminals are crimped to ensure reliable conductive connections with devices such as relays, contactors, switches, and power modules. Terminal crimping relies on specialized crimping equipment, which requires mechanical force and electrical energy and generates heat during the crimping process. Under normal circumstances, the equipment's energy consumption should remain within the preset energy consumption requirements.

[0025] In this embodiment of the invention, those skilled in the art, through long-term monitoring of the production line and observation of numerous actual assembly samples, discovered a phenomenon that was not fully recognized in the prior art. In the wiring process, due to the limited space in the wire troughs, the high flexibility of the wire harness, and significant differences in the experience of wiring personnel, wiring variations are unavoidable when wiring is done manually. Although the wire harness usually meets process requirements upon completion of the wiring process and does not immediately exhibit compression, for certain types of electrical cabinets with narrow structures and high wire harness density, this wiring variation can lead to the gradual formation of localized compression during subsequent natural changes, processing, handling, vibration, or equipment operation. Therefore, localized compression of the wire harness is a delayed change, not significant at the time of the wiring process but gradually appearing in subsequent processes. Existing manufacturing execution systems typically consider this slight compression as a natural process fluctuation range and do not further track its impact.

[0026] Those skilled in the art have further discovered that during the terminal crimping process, equipment sometimes exhibits a slight increase in additional energy consumption. Existing technologies generally attribute this to fluctuations in equipment performance or process errors in the crimping action itself. However, through long-term accumulation of production samples and trend comparison, those skilled in the art have recognized a clear coupling relationship between this slight increase in additional energy consumption and differences in the wiring process. Specifically, when the wire harness inside the wire trough experiences localized compression due to differences in the preceding wiring, it leads to changes in the mechanical response of the wire harness during the terminal crimping process, resulting in additional energy consumption. However, this relationship has not been identified in existing technologies, and corresponding optimization strategies are lacking. This invention constructs an AI analysis model specifically targeting this coupling relationship, enabling the production line to be optimized in advance during the wiring process. This reduces unnecessary energy consumption in the terminal crimping process while ensuring wiring quality and, to some extent, protects the load equipment.

[0027] The historical processing records of the production line mentioned in step S100 can originate from the production line's manufacturing execution system, quality inspection system, process record system, or equipment monitoring platform. These records may include wire harness image data upon completion of the wiring process, operational data for the wire trough area, equipment parameters, production batch number, operator information, process environment, energy consumption curves and temperature rise curves of the terminal crimping equipment, and various monitoring data. The data acquisition methods are mature existing image acquisition modules, data recording modules, or equipment monitoring modules, thus satisfying feasibility.

[0028] The main reasons for differences in wire harness stacking parameters include variations in operator techniques, differences in wire harness flexibility and resilience, limitations in wire trough space, changes in assembly sequence, and interference from the production environment. In this embodiment of the invention, the wire harness stacking parameters are generated based on visually acquired images of the wire harness after the wire trough wiring process. Stacking state features such as the degree of fit between wire harnesses, local compression, offset of the wiring path, or local density of the wire harness are identified in the image. Key geometric features are extracted using image analysis algorithms or deep learning models, and quantified wire harness stacking parameters are generated based on these features. The aforementioned visual recognition techniques are all existing technologies, such as edge detection, deformation recognition, density estimation, or image feature extraction based on convolutional neural networks. This invention can select any one of these features as the wire harness stacking parameters or obtain comprehensive parameters by weighted combination of multiple features.

[0029] The significance of sample screening lies in the fact that when there is only a single difference between the wiring process and the terminal crimping process, namely the "wire harness stacking parameters", comparing the squeezing effect index and additional energy consumption of different samples in subsequent processes can maximize the elimination of interference from other process conditions on the analysis results. This allows the present invention to accurately identify the coupling relationship between wire harness stacking differences and terminal crimping energy consumption, thereby obtaining a data sequence with statistical significance and process guidance value.

[0030] Furthermore, the AI-based industrial automation production process optimization method also includes the following steps: Step S200: Analyze the sample, identify the squeezing effect index of the wire harness located in the preset wire trough area before the electrical cabinet enters the terminal crimping process, and identify the additional energy consumption generated by the terminal crimping process relative to the preset energy consumption requirement when performing the crimping operation.

[0031] The calculation of the squeezing effect index includes: based on the visually acquired image of the wire harness located in the preset wire groove area before the electrical cabinet enters the terminal crimping process, identifying the squeezing state characteristics of the wire harness in the preset wire groove area, the squeezing state characteristics including at least one: the degree of deformation of the wire harness cross section, the local height change of the wire harness relative to its reference height in its natural spread state, or the minimum spacing between the wire harnesses; and generating the squeezing effect index based on the squeezing state characteristics.

[0032] In this embodiment of the invention, the analytical sample mentioned in step S200 is based on the samples obtained in step S100, and further analysis and identification of the data content of each sample. Specifically, after the wiring process is completed, the electrical cabinet will undergo handling, vibration, opening and closing tests, and other process actions in subsequent processes. These unavoidable physical disturbances will cause the wire harness located in the preset wire trough area to undergo subsequent deformation, causing the compression phenomenon that did not appear at the end of the wiring process to gradually appear at this stage. Before the electrical cabinet enters the terminal crimping process, the actual stacking state of its wire harness in the preset wire trough area is already different from that at the end of the wiring process. Therefore, in this embodiment of the invention, the compression effect index is used to reflect the actual compression state of the wire harness at this time point.

[0033] The squeezing effect index is obtained by identifying wire harness images acquired visually. In a preferred embodiment, a station is set up before the electrical cabinet enters the terminal crimping process. This station is equipped with a handheld or fixed camera to photograph the wire harness in a preset wire groove area to obtain wire harness image data at the current moment. Since the wire harness morphology at this stage already contains information on the subsequent deformation caused by differences in the wiring process, the squeezing effect index calculated based on this image can accurately reflect the actual degree of wire harness squeezing. The identification of the wire harness image can employ existing image processing algorithms or deep learning models to identify the degree of deformation of the wire harness cross-section, the local height change of the wire harness relative to the reference height of the natural spread state, or the minimum spacing between the wire harnesses, and generate a quantified squeezing effect index based on these squeezing state characteristics. The above-mentioned visual calculation method is a technical means that can be implemented by existing technology. Those skilled in the art can complete feature recognition and index generation through conventional image feature extraction methods or neural network models.

[0034] In step S200, it is also necessary to identify the additional energy consumption of the terminal crimping process relative to the preset energy consumption requirement during the crimping operation. The preset energy consumption requirement refers to the standard energy consumption reference value determined during the process design or equipment calibration phase. It is based on the rated parameters of the terminal crimping equipment, the crimping force curve, and normal temperature rise conditions, and represents the electrical energy or energy consumption per unit time that the equipment should consume when performing one standard crimping operation. The preset energy consumption requirement is usually obtained through equipment manufacturer calibration data, production line process settings, or historical average strategies, and therefore falls within the generally accepted normal energy consumption range of existing production lines.

[0035] Additional energy consumption refers to the difference between the energy consumption of a terminal crimping device during actual crimping operations and the preset energy consumption requirement. This difference can be obtained by collecting the energy consumption data of the crimping device in real time, such as through the device's built-in energy consumption monitoring interface, an external power acquisition module, or a temperature rise monitoring module. For crimping devices, their energy consumption curve has a stable fluctuation range under normal operating conditions. Slight energy consumption fluctuations are within the natural fluctuation range of the device's operation and are also within the tolerance range allowed by the process. When the actual energy consumption exceeds this normal range, the production line monitoring system will usually trigger an alarm and indicate that the device may have an abnormality. The additional energy consumption of concern in this embodiment of the invention is a slight increase in energy consumption within the normal fluctuation range but showing an abnormal trend. This type of energy consumption increase usually does not trigger a production line alarm, so it has not been given much attention in the prior art, and its cause cannot be identified through conventional monitoring methods.

[0036] By jointly identifying the extrusion effect index and additional energy consumption, this invention establishes the relationship between differences in the wiring process and changes in energy consumption in the terminal crimping process, providing basic data support for subsequent sample sorting, trend analysis, and recognition of preset specific patterns.

[0037] Furthermore, the AI-based industrial automation production process optimization method also includes the following steps: Step S300: Sort the samples according to the wire harness stacking parameters to obtain the sample sequence, and analyze whether the sample sequence meets the preset specific pattern.

[0038] The preset specific mode includes: within the initial range of the sample sequence, both the squeezing effect index and the additional energy consumption are in a state of gradual change, and there is a sample segment in the sample sequence consisting of a preset number of adjacent samples, in which the squeezing effect index and the additional energy consumption simultaneously undergo a turning point increase.

[0039] Specifically, Figure 2 A flowchart illustrating the synchronous analysis of changing trends is shown.

[0040] The process of sorting samples according to harness stacking parameters to obtain sample sequences and analyzing whether the sample sequences meet a preset specific pattern includes the following steps: Step S301: Sort the samples in ascending order of wire harness stacking parameters to obtain a sample sequence, and extract the squeezing effect index change trend and additional energy consumption change trend corresponding to the sample sequence. Step S302: Simultaneously analyze the changing trend of the squeezing effect index and the changing trend of the additional energy consumption to determine whether they meet the preset specific mode.

[0041] In this embodiment of the invention, the execution of step S300 is one of the core steps. Its purpose is to establish comparability between different samples, enabling the system to identify whether a slight increase in energy consumption during the terminal crimping process is coupled with differences in the wiring process. In step S300, the samples are first sorted according to the wire harness stacking parameters to obtain a sample sequence. The wire harness stacking parameters reflect the actual stacking state differences of the wire harness within the preset wire groove area after the wiring process. Only this parameter differs between samples, while other wiring process conditions remain consistent. Therefore, after obtaining the sample sequence, the relationship between wiring differences and subsequent extrusion effect index and additional energy consumption can be expanded according to the continuity of stacking differences, thereby eliminating the interference of other process factors on the results.

[0042] After obtaining the sample sequences, the trends of the squeezing effect index and additional energy consumption corresponding to the sample sequences were extracted. The squeezing effect index characterizes the degree of squeezing of the wire harness within the preset slot area before entering the terminal crimping process, while the additional energy consumption reflects the deviation of the actual energy consumption in the terminal crimping process from the preset energy consumption requirement. Since the sample sequences are arranged according to the wire harness stacking parameters from small to large, both trends should show a gradual change as the difference in stacking state increases. In the initial range of the sample sequences, due to the small wire harness stacking parameters, the actual stacking difference between samples is not significant, so the corresponding squeezing effect index is usually in a flat state; similarly, the additional energy consumption in the terminal crimping process also remains within the natural fluctuation range, and the change tends to be stable. The flat trend in this stage reflects that samples with small differences in wire harness stacking will not cause obvious squeezing deformation before entering the terminal crimping process, nor will they have a significant impact on the crimping energy consumption, which is a natural and reasonable process range.

[0043] As the wire harness stacking parameters gradually increase, some samples are more prone to localized compression during subsequent changes. When the stacking differences reach a certain level, a sample segment consisting of a predetermined number of adjacent samples appears in the sample sequence. Within this segment, the compression effect index shows a significant abrupt increase, meaning the compression level suddenly shifts from a gradual state to a substantial increase. This change reflects how the natural differences between samples during the wiring process are amplified in subsequent processes, leading to localized deformation of the wire harness within the predetermined groove area. Simultaneously with the compression effect index, the additional energy consumption of the terminal crimping process also shows a trend of gradual increase followed by a sharp rise within this sample segment. This indicates that the wire harness compression state has affected the energy consumption of the crimping process, requiring the equipment to consume more energy than normal to complete the crimping action.

[0044] The simultaneous abrupt increase in both trends within the same narrow sample segment indicates a strong coupling between the significant change in the squeezing effect index and the increase in additional energy consumption. This means that the slightly abnormal energy consumption changes in the terminal crimping process are related to differences in the wiring process, rather than random deviations caused by equipment or processes. This coupling determination is crucial for production line optimization. By identifying the coupling relationship, the true cause of the slight increase in energy consumption in the terminal crimping process can be confirmed and traced back to the wiring process. This allows the system to optimize the stacking state in advance during the wiring stage, ensuring that subsequent crimping processes maintain a stable energy consumption range, avoiding unnecessary energy losses, and ensuring equipment reliability.

[0045] Figure 2The process of sequencing, trend extraction, and synchronous analysis is illustrated. Step S301 is used to obtain the sample sequence and the corresponding two types of trends. Step S302 is used to synchronously analyze the trend of the squeezing effect index and the trend of additional energy consumption, and to determine whether the trend meets the preset specific pattern based on whether the trend has the characteristics of "initially flat and then synchronously rising in a turning point within a preset number of adjacent sample segments". In this embodiment of the invention, this trend analysis step enables the production line to identify the true extent of the impact of wiring differences on the energy consumption of the terminal crimping process, providing a reliable basis for the subsequent generation of benchmark stacking standards.

[0046] Furthermore, the AI-based industrial automation production process optimization method also includes the following steps: Step S400: If the condition is met, a reference stacking standard for the target type electrical cabinet in the wire trough wiring process is generated based on the wire harness stacking parameters corresponding to the sample section, and subsequent wiring processes are executed according to the reference stacking standard.

[0047] Specifically, Figure 3 A flowchart for developing a benchmark stacking standard is shown.

[0048] If the condition is met, a baseline stacking standard for the wire harness stacking process of the target type electrical cabinet in the wire trough wiring procedure is generated based on the wire harness stacking parameters corresponding to the sample section, and subsequent wiring procedures are executed according to the baseline stacking standard. This includes the following steps: Step S401: If it is determined that a preset specific pattern exists in the sample sequence, select the bundle stacking parameters of all samples corresponding to the sample segment, and calculate the average value of the bundle stacking parameters. Step S402: Set the average value as the benchmark stacking standard for the wire tray wiring process of the target type electrical cabinet, and make the subsequent wiring process perform according to the benchmark stacking standard.

[0049] In this embodiment of the invention, the execution of step S400 is a key step in achieving optimized closed-loop control. Its purpose is to apply the coupling information between wiring differences and terminal crimping energy consumption reflected by the identified specific patterns in the sample sequence to the actual production process. By generating a benchmark stacking standard for the target type electrical cabinet in the wire trough wiring process based on the wire harness stacking parameters corresponding to the sample segment, the wiring process is transformed from a traditional method relying on manual experience to a quantifiable control method based on data analysis. This reduces the subsequent negative impacts of wiring differences and establishes a process control system that links the entire production line.

[0050] In step S401, by selecting the wire harness stacking parameters of all samples corresponding to the sample segment and calculating their average value, the core characteristics of the wire harness stacking state in that sample segment can be effectively extracted. Since this segment precisely corresponds to the position where the squeezing effect index and additional energy consumption simultaneously experience a turning point increase, the wire harness stacking parameters contained in this segment can represent the "threshold range where the wiring process has an adverse effect." Using the average value can obtain the central parameter that best reflects the changing trend in different batches, different production shifts, and multiple wiring differences, making the determined benchmark stacking standard have wider adaptability and stability.

[0051] Since this benchmark stacking standard originates from the threshold point of the squeezing effect and energy consumption variation, it is essentially an acceptable boundary parameter rather than an extremely demanding ideal wiring state. Therefore, it is less affected by differences in the operational proficiency of different wiring operators. Operators are more likely to understand and accept this type of threshold standard in actual operations, and their wiring behavior will more naturally approach this range, thus ensuring that the benchmark stacking standard can be stably implemented on the production line. At the same time, provided that the squeezing and energy consumption transition zone is not entered, a parameter range with a better stacking state after the transition zone can be selected as an alternative standard, giving the wiring process more operational space and further improving the overall product quality. The average value can avoid the occasional deviation caused by a single sample and also take into account the overall characteristics of each sample within the section, thus it is a natural, effective, and feasible method.

[0052] As described in step S402, this average value is set as the baseline stacking standard for the wire harness wiring process of the target type electrical cabinet, and subsequent wiring processes are executed according to this standard. In actual operation, the baseline stacking standard can be presented to the wiring personnel through wiring operation instructions, machine operation interface prompts, visual assistance systems, or wiring auxiliary tooling, allowing operators to lay and organize wire harnesses by referring to the stacking height, fit, or path offset range corresponding to the baseline stacking standard. For example, a real-time visual prompt screen can be equipped at the wiring station to estimate the wire harness stacking parameters in real time and provide deviation reminders during the wiring process, enabling wiring personnel to adjust for deviations from the standard in actual operation. In addition, training programs can also be used to enable wiring personnel to develop a stable judgment of the wire harness stacking status in actual operation, thereby effectively reducing subsequent compression problems caused by operational differences.

[0053] After the baseline stacking standard is implemented, the energy consumption of the terminal crimping process continues to be monitored in this embodiment of the invention, and the difference between the actual energy consumption data and the preset energy consumption requirements is recorded and analyzed. When some batches of cabling still show slight energy consumption anomalies, the cabling stacking parameters of these batches can be reintroduced into the sample sequence to update the sample segments and the new average value, so that the baseline stacking standard can be dynamically adjusted according to production conditions, thereby forming a data-driven continuous optimization mechanism. In this way, the present invention can not only reduce the immediate impact of cabling differences, but also achieve long-term system optimization, forming a stable positive feedback loop between the cabling process and the terminal crimping process.

[0054] In this embodiment of the invention, a correlation between differences in the wiring process and terminal crimping energy consumption was successfully established by sorting samples, extracting trends, recognizing patterns, and generating benchmark stacking standards. The overall beneficial effects of this invention are: it can identify potential problems in the wiring process in advance and perform parameterized control during the wiring stage, keeping the energy consumption of subsequent terminal crimping processes within a normal range; it can reduce excessive energy consumption caused by extrusion, thereby reducing equipment load and improving the overall energy efficiency of the production line; and it can improve the consistency of wire harness layout, making the quality of electrical cabinet products more stable.

[0055] This invention has broad application prospects. First, it is applicable to various types of electrical cabinet production lines with wire tray wiring processes, especially in production environments with high wire harness density, limited wire tray space, and a high proportion of manual wiring. Second, based on visual recognition technology and AI analysis models, this invention does not rely on specific equipment and can therefore be quickly deployed to existing production lines through software upgrades and system integration. Third, as sample data accumulates, this invention can further optimize benchmark stacking standards, making wiring quality more stable, and can be extended to other inter-process correlation analysis scenarios with coupling phenomena, such as welding processes and wiring testing processes, demonstrating scalability and portability. Therefore, this invention not only solves the current problem of difficulty in identifying the coupling relationship between wiring and crimping, but also provides a continuously optimized technical foundation for future intelligent manufacturing.

[0056] Furthermore, Figure 4 An application architecture diagram of the system provided in an embodiment of the present invention is shown.

[0057] In another preferred embodiment of the present invention, an industrial automation production process optimization system based on AI analysis includes: The data acquisition module 100 is used to acquire the historical processing records of the production line of the target type of electrical cabinet, and to select several samples from them in which the wiring process conditions are consistent except for the wire harness stacking parameters.

[0058] The calculation of the wire harness stacking parameters includes: based on the wire harness image after the wire grooving process is completed by visual acquisition, identifying the local stacking state characteristics of the wire harness in the preset wire grooving area due to the difference in wire arrangement, the stacking state characteristics include at least one: the degree of fit between wire harnesses, the amount of local compression, the offset of the wire arrangement path or the local density of the wire harness, and generating the wire harness stacking parameters based on the stacking state characteristics.

[0059] Furthermore, the AI-based industrial automation production process optimization system also includes: The indicator recognition module 200 is used to analyze samples, identify the squeezing effect index of the wire harness located in the preset wire trough area before the electrical cabinet enters the terminal crimping process, and identify the additional energy consumption generated by the terminal crimping process relative to the preset energy consumption requirement when performing the crimping operation.

[0060] The calculation of the squeezing effect index includes: based on the visually acquired image of the wire harness located in the preset wire groove area before the electrical cabinet enters the terminal crimping process, identifying the squeezing state characteristics of the wire harness in the preset wire groove area, the squeezing state characteristics including at least one: the degree of deformation of the wire harness cross section, the local height change of the wire harness relative to its reference height in its natural spread state, or the minimum spacing between the wire harnesses; and generating the squeezing effect index based on the squeezing state characteristics.

[0061] Furthermore, the AI-based industrial automation production process optimization system also includes: The pattern analysis module 300 is used to sort the samples according to the wire harness stacking parameters, obtain the sample sequence, and analyze whether the sample sequence meets the preset specific pattern.

[0062] The preset specific mode includes: within the initial range of the sample sequence, both the squeezing effect index and the additional energy consumption are in a state of gradual change, and there is a sample segment in the sample sequence consisting of a preset number of adjacent samples, in which the squeezing effect index and the additional energy consumption simultaneously undergo a turning point increase.

[0063] Specifically, Figure 5 A structural block diagram of the pattern analysis module 300 in the system provided in an embodiment of the present invention is shown.

[0064] In a preferred embodiment provided by the present invention, the pattern analysis module 300 specifically includes: The sorting unit 301 is used to sort the samples in ascending order of the wire harness stacking parameters to obtain a sample sequence, and extract the squeezing effect index change trend and the additional energy consumption change trend corresponding to the sample sequence. The trend analysis unit 302 is used to simultaneously analyze the changing trend of the squeezing effect index and the changing trend of the additional energy consumption to determine whether the two meet the preset specific mode.

[0065] Furthermore, the AI-based industrial automation production process optimization system also includes: The benchmark generation module 400 is used to generate a benchmark stacking standard for the target type electrical cabinet in the wire tray wiring process based on the wire harness stacking parameters corresponding to the sample section if it is determined that the standard is met, and to make the subsequent wiring process execute according to the benchmark stacking standard.

[0066] Specifically, Figure 6 A structural block diagram of the benchmark generation module 400 in the system provided in an embodiment of the present invention is shown.

[0067] In a preferred embodiment provided by the present invention, the benchmark generation module 400 specifically includes: The parameter acquisition unit 401 is used to select the bundle stacking parameters of all samples corresponding to the sample segment if it is determined that a preset specific pattern exists in the sample sequence, and to calculate the average value of the bundle stacking parameters. The reference setting unit 402 is used to set the average value as the reference stacking standard in the wire tray wiring process for the target type electrical cabinet, and to make the subsequent wiring process perform according to the reference stacking standard.

[0068] It should be understood that although the steps in the flowcharts of the various embodiments of the present invention are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the various embodiments may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least a portion of the sub-steps or stages of other steps.

[0069] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0070] The technical features of the above embodiments can be combined in any way. For the sake of brevity, 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.

[0071] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention. Therefore, the scope of protection of this patent should be determined by the appended claims.

[0072] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for optimizing industrial automated production processes based on AI analysis, characterized in that, The method includes: Obtain historical processing records of the production line for the target type of electrical cabinet, and select several samples from them where the wiring process conditions are consistent except for the wire harness stacking parameters in the wire tray wiring process. The sample was analyzed to identify the squeezing effect index of the wire harness located in the preset wire trough area before the terminal crimping process, and to identify the additional energy consumption generated by the terminal crimping process relative to the preset energy consumption requirement when performing the crimping operation. The samples are sorted according to the wire harness stacking parameters to obtain a sample sequence, and the sample sequence is analyzed to see if it meets a preset specific pattern. The preset specific pattern includes: the squeezing effect index and the additional energy consumption are in a state of gradual change in the initial range of the sample sequence, and there is a sample segment in the sample sequence consisting of a preset number of adjacent samples, in which the squeezing effect index and the additional energy consumption simultaneously undergo a turning point increase. If the condition is met, a baseline stacking standard for the target type electrical cabinet in the wire tray wiring process is generated based on the wire harness stacking parameters corresponding to the sample section, and subsequent wiring processes are executed according to the baseline stacking standard.

2. The industrial automation production process optimization method based on AI analysis according to claim 1, characterized in that, The calculation of the wire harness stacking parameters includes: based on the wire harness image after the wire grooving process is completed by visual acquisition, identifying the local stacking state characteristics of the wire harness in the preset wire grooving area due to the difference in wire arrangement, the stacking state characteristics include at least one: the degree of fit between wire harnesses, the amount of local compression, the offset of the wire arrangement path or the local density of the wire harness, and generating the wire harness stacking parameters based on the stacking state characteristics.

3. The industrial automation production process optimization method based on AI analysis according to claim 1, characterized in that, The calculation of the squeezing effect index includes: based on the visually acquired image of the wire harness located in the preset wire groove area before the electrical cabinet enters the terminal crimping process, identifying the squeezing state characteristics of the wire harness in the preset wire groove area, the squeezing state characteristics including at least one: the degree of deformation of the wire harness cross section, the local height change of the wire harness relative to its reference height in its natural spread state, or the minimum spacing between the wire harnesses; and generating the squeezing effect index based on the squeezing state characteristics.

4. The industrial automation production process optimization method based on AI analysis according to claim 1, characterized in that, The steps of sorting the samples according to the wire harness stacking parameters to obtain the sample sequence and analyzing whether the sample sequence meets the preset specific pattern include: The samples are sorted from smallest to largest according to the bundle stacking parameters to obtain a sample sequence, and the changing trends of the squeezing effect index and the additional energy consumption corresponding to the sample sequence are extracted. The changing trends of the squeezing effect index and the changing trends of the additional energy consumption are analyzed simultaneously to determine whether they meet the preset specific mode.

5. The industrial automation production process optimization method based on AI analysis according to claim 4, characterized in that, If the condition is met, the following steps are taken to generate a baseline stacking standard for the wire harness stacking process of the target type electrical cabinet in the wire trough wiring procedure based on the wire harness stacking parameters corresponding to the sample section, and to ensure that subsequent wiring procedures are performed according to the baseline stacking standard: If a preset specific pattern is determined to exist in the sample sequence, select the bundle stacking parameters of all samples corresponding to the sample segment, and calculate the average value of the bundle stacking parameters; The average value is set as the benchmark stacking standard for the wiring process of the target type electrical cabinet in the online trunking, and subsequent wiring processes are performed in accordance with the benchmark stacking standard.

6. An industrial automation production process optimization system based on AI analysis, characterized in that, The system includes: The data acquisition module is used to acquire the historical processing records of the production line of the target type of electrical cabinet, and to select several samples from them in which the wiring process conditions are consistent except for the wire harness stacking parameters. The index recognition module is used to analyze samples, identify the squeezing effect index of the wire harness located in the preset wire trough area before the electrical cabinet enters the terminal crimping process, and identify the additional energy consumption generated by the terminal crimping process relative to the preset energy consumption requirement when performing the crimping operation. The pattern analysis module is used to sort the samples according to the wire harness stacking parameters, obtain the sample sequence, and analyze whether the sample sequence meets the preset specific pattern. The preset specific pattern includes: the squeezing effect index and the additional energy consumption are in a state of gradual change in the initial range of the sample sequence, and there is a sample segment in the sample sequence consisting of a preset number of adjacent samples, in which the squeezing effect index and the additional energy consumption simultaneously undergo a turning point increase. The benchmark generation module is used to generate a benchmark stacking standard for the target type electrical cabinet in the wire tray wiring process based on the wire harness stacking parameters corresponding to the sample section if it is determined that the standard is met, and to make the subsequent wiring process execute according to the benchmark stacking standard.

7. The industrial automation production process optimization system based on AI analysis according to claim 6, characterized in that, The calculation of the wire harness stacking parameters includes: based on the wire harness image after the wire grooving process is completed by visual acquisition, identifying the local stacking state characteristics of the wire harness in the preset wire grooving area due to the difference in wire arrangement, the stacking state characteristics include at least one: the degree of fit between wire harnesses, the amount of local compression, the offset of the wire arrangement path or the local density of the wire harness, and generating the wire harness stacking parameters based on the stacking state characteristics.

8. The industrial automation production process optimization system based on AI analysis according to claim 7, characterized in that, The calculation of the squeezing effect index includes: based on the visually acquired image of the wire harness located in the preset wire groove area before the electrical cabinet enters the terminal crimping process, identifying the squeezing state characteristics of the wire harness in the preset wire groove area, the squeezing state characteristics including at least one: the degree of deformation of the wire harness cross section, the local height change of the wire harness relative to its reference height in its natural spread state, or the minimum spacing between the wire harnesses; and generating the squeezing effect index based on the squeezing state characteristics.

9. The industrial automation production process optimization system based on AI analysis according to claim 8, characterized in that, The pattern analysis module specifically includes: The sorting unit is used to sort the samples in ascending order of the wire harness stacking parameters to obtain a sample sequence, and extract the squeezing effect index change trend and the additional energy consumption change trend corresponding to the sample sequence. The trend analysis unit is used to simultaneously analyze the changing trend of the squeezing effect index and the changing trend of the additional energy consumption to determine whether the two meet the preset specific mode.

10. The industrial automation production process optimization system based on AI analysis according to claim 9, characterized in that, The benchmark generation module specifically includes: The parameter acquisition unit is used to select the bundle stacking parameters of all samples corresponding to the sample segment if a preset specific pattern is determined to exist in the sample sequence, and to calculate the average value of the bundle stacking parameters. The reference setting unit is used to set the average value as the reference stacking standard for the wire tray wiring process of the target type electrical cabinet, and to make the subsequent wiring process perform according to the reference stacking standard.

Images