Automobile wire harness production line monitoring management method and system

Abstract

The application provides a kind of automobile wire harness production line monitoring management method and system, belong to automobile wire harness production monitoring field, for solving the problems of lack of multi-scale collaborative monitoring, micro-defects difficult to identify in time, low process parameter optimization efficiency in related technologies.The scheme constructs quantum-neuromorphic-classical three-level collaborative architecture, calculates the interatomic interaction parameters through quantum microscopic layer, converts into mesoscopic material evolution data by neuromorphic mesoscopic layer, adjusts the process parameters by classical macroscopic layer, each level transmits feedback through cross-scale interaction mechanism, realizes multi-objective optimization combined with quantum optimization algorithm, can realize whole process accurate monitoring, improve quality stability and optimize energy consumption and equipment loss.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of automobile wire harness production monitoring, in particular to an automobile wire harness production line monitoring management method and system. BACKGROUND

[0002] As a core component of automobile circuits, the quality of automobile wire harnesses directly affects the safety, reliability and durability of automobiles. With the rapid development of new energy vehicles and intelligent networked vehicles, the structural complexity and performance requirements of wire harnesses have increased significantly, with the number of terminals on a single vehicle reaching several thousand. The quality control of key processes such as crimping and stripping has become significantly more difficult. Currently, the monitoring and management of automobile wire harness production lines mainly relies on traditional macroscopic parameter detection, such as crimping pressure, temperature, speed, etc., with simple threshold setting for over-limit alarm. This approach has obvious limitations.

[0003] Firstly, existing monitoring methods lack micro-level perception capabilities. The quality of terminal crimping depends on micro-features such as atomic interactions, grain deformation and oxide film state within the material. Traditional methods can only obtain macro-process parameters and cannot capture these micro-changes. For example, when atomic stress concentration occurs within the terminal material, the macroscopic parameters may still be within the normal range, but there is a potential risk of crack initiation. By the time a macroscopic crack appears, an alarm is triggered, often resulting in a large number of defective products. According to industry statistics, more than 60% of total quality problems caused by micro-defects on wire harness production lines using traditional monitoring methods result in significant after-sales costs and reputation losses for vehicle manufacturers.

[0004] Secondly, there is a lack of multi-scale data fusion capability. Wire harness production processes involve multi-scale physical phenomena from atomic level (0.1 Å) to device level (meter level), with strong coupling relationships between scales. For example, micro-level atomic displacement accumulates into meso-level grain deformation, which in turn affects macro-level terminal pull-off force. Existing technologies mostly use single-scale models for analysis, such as simulating the crimping process only through macroscopic dynamics models or simulating material properties only through micro-molecular dynamics simulations. This fragmentation results in low prediction accuracy, such as a prediction error of terminal pull-off force often exceeding 10%, making it difficult to meet high-precision production requirements. Meanwhile, the data formats and time steps of different scales differ greatly (microscale in femtoseconds, macroscale in milliseconds), making it difficult for traditional data processing methods to achieve real-time alignment, with data delays of up to hundreds of milliseconds, which cannot support real-time control decisions.

[0005] Thirdly, the existing optimization algorithm has limitations. Wire harness production needs to consider quality, efficiency and cost as three major goals. For example, under the premise of ensuring that the terminal pull-off force is greater than or equal to 80N, it is necessary to reduce energy consumption and reduce mold wear. Traditional optimization methods mostly use single-objective optimization or fixed-weight multi-objective optimization, which cannot dynamically adapt to changes in production conditions. For example, when the material hardness fluctuates due to changes in raw material batches, a fixed-weight optimization algorithm may produce a non-optimal solution, resulting in increased energy consumption or unstable quality. In addition, the optimization process relies on a large amount of experimental data, and dozens of trial productions are required for each adjustment of process parameters, with a cycle of several days, which seriously affects production efficiency.

[0006] Finally, the hardware architecture of the existing system cannot support the landing of advanced algorithms. The application of frontier technologies such as quantum computing and neuromorphic computing in the industrial field is still in its infancy. The traditional CPU+GPU architecture has insufficient computing power and high energy consumption when processing microscopic quantum simulations and large-scale spiking neural networks. For example, simulating the dynamic behavior of a 10^4 atomic system using a traditional CPU takes several hours for a single simulation, which cannot meet the real-time monitoring requirements. The lack of neuromorphic chips results in insufficient parallel processing capability for multi-scale data fusion, and the data processing delay cannot be controlled within milliseconds. These hardware limitations further restrict the upgrading of monitoring and management methods.

[0007] In summary, the current monitoring and management of automobile wire harness production lines has significant shortcomings in multi-scale perception, data fusion, intelligent optimization and hardware support, and urgently needs a technical solution that can realize cross-scale collaborative monitoring, real-time data interaction and dynamic optimization to improve the quality stability and production efficiency of wire harness production. SUMMARY

[0008] The present application provides a method and system for monitoring and managing automobile wire harness production lines, which can realize full-process monitoring from atomic level to device level through a multi-scale collaborative architecture, improving the quality control accuracy and optimization efficiency of wire harness production.

[0009] In a first aspect, the present application provides a method for monitoring and managing automobile wire harness production lines. A quantum-neuromorphic-classical three-level collaborative architecture is constructed, which includes a quantum microscopic layer for atomic level simulation, a neuromorphic mesoscopic layer for grain scale analysis, and a classical macroscopic layer for device process control; the interatomic interaction parameters of the terminal material are calculated by the quantum microscopic layer; the interatomic interaction parameters are received by the neuromorphic mesoscopic layer and converted into mesoscopic scale material evolution data; the classical macroscopic layer receives the mesoscopic scale material evolution data, constructs a device dynamics model and adjusts the process parameters; the quantum microscopic layer, neuromorphic mesoscopic layer and classical macroscopic layer realize data transmission and feedback through a cross-scale data interaction mechanism.

[0010] By adopting the technical scheme, multi-scale coverage from atomic level to device level is realized through the three-level collaborative architecture, and the limitations of traditional single-scale monitoring are broken through the cross-scale data interaction mechanism, so that micro defects can be captured in time and fed back to macro process adjustment, forming a quality control closed loop throughout the whole process.

[0011] Further, the cross-scale data interaction mechanism comprises: the quantum microscopic layer converts quantum state data into classical characteristic parameters through quantum unit calculation elements; the neuromorphic mesoscopic layer converts pulse encoding signals into mesoscopic characteristic parameters; and the classical macroscopic layer converts process parameters into external field parameters recognizable by the quantum layer.

[0012] By adopting the technical scheme, the format conversion and bidirectional transmission of data of different scales are realized, ensuring the consistency between quantum state data, pulse signals and macro parameters, and providing a data basis for multi-scale collaborative analysis.

[0013] Further, the quantum microscopic layer adopts a variational quantum eigenvalue solver, which includes a quantum bit circuit for solving an electronic structure equation of a terminal material to obtain interatomic bond energy parameters.

[0014] By adopting the technical scheme, the parallelism of quantum computing improves the calculation accuracy and efficiency of interatomic interaction parameters, providing an accurate physical basis for micro defect prediction.

[0015] Further, the neuromorphic mesoscopic layer adopts a spiking neural network, which adjusts weights through synaptic plasticity rules, and the synaptic plasticity rules update weights based on pulse time difference.

[0016] By adopting the technical scheme, the information processing mode of biological neural networks is simulated, improving the processing speed and dynamic adaptability of mesoscopic material evolution data, and enabling rapid response to changes in micro parameters.

[0017] Further, the device dynamics model of the classical macroscopic layer adopts a many-body dynamics equation, which adjusts the crimping pressure, temperature and speed through a closed-loop control algorithm, so that the terminal quality parameters meet the preset threshold.

[0018] By adopting the technical scheme, the mesoscopic analysis results are combined with macro device control, and the process parameters are adjusted in real time through a closed-loop algorithm to ensure that the terminal quality is stable within the preset range.

[0019] Further, the simulation time step of the quantum microscopic layer is femtosecond level, and the interatomic interaction parameters include atomic displacement and local stress value.

[0020] By adopting the technical scheme, atomic-level dynamic changes are captured with femtosecond-level time resolution, and atomic displacement and stress data obtained thereby provide high-precision input for micro-defect initiation prediction.

[0021] Further, the spiking neural network of the neuromorphic mesoscopic layer adopts a neuron model with a membrane time constant, the membrane time constant being a preset millisecond-level value, and synaptic weights are adjusted according to a time difference between pre-synaptic and post-synaptic pulses.

[0022] By adopting the technical scheme, the time characteristics of the spiking neural network are matched with the crimping process cycle, dynamic adjustment of weights is realized through synaptic plasticity, and the real-time performance and accuracy of mesoscopic data processing are improved.

[0023] Further, the simulation step length of the device dynamics model of the classical macroscopic layer is millisecond-level, and the adjustment response time of the process parameters does not exceed a preset millisecond-level threshold.

[0024] By adopting the technical scheme, the real-time performance of macroscopic device control is ensured, the process parameter adjustment can quickly respond to changes at the micro and mesoscopic levels, and quality deviation accumulation is avoided.

[0025] Further, the method further comprises: performing multi-objective optimization on the process parameters through a quantum optimization algorithm, the multi-objective optimization taking terminal quality parameters, energy consumption parameters and device loss parameters as optimization variables, and satisfying a preset threshold condition of the terminal quality parameters.

[0026] By adopting the technical scheme, multi-objective collaborative optimization is realized using the high efficiency of the quantum optimization algorithm, energy consumption and device loss are reduced on the premise of ensuring quality, and the comprehensive benefits of production are improved.

[0027] In a second aspect, the application provides an automobile wire harness production line monitoring management system. The automobile wire harness production line monitoring management system is used to implement any one of the automobile wire harness production line monitoring management methods described above, and comprises: a quantum processing unit configured to construct the quantum microcosmic layer; a neuromorphic processing unit configured to construct the neuromorphic mesoscopic layer; an edge computing unit configured to construct the classical macroscopic layer; and a multi-scale sensing unit comprising a nanometer-level sensor, a spectrum detection device, a distributed optical fiber sensor and a high-frequency pressure sensor; and the quantum processing unit, the neuromorphic processing unit, the edge computing unit and the multi-scale sensing unit are connected through a data transmission protocol.

[0028] By adopting the technical scheme, hardware support is provided for the monitoring management method through the cooperation of the special hardware units and the multi-scale sensing devices, integrated quantum computing, neuromorphic processing and edge computing are realized, and real-time acquisition and processing of multi-scale data are ensured.

[0029] In summary, the application at least has the following beneficial effects:

[0030] A multi-scale cooperative monitoring management scheme is provided to realize full-process quality control from the atomic level to the device level.

[0031] Through cross-scale data interaction and real-time optimization, the quality stability and production efficiency of the wire harness production are improved.

[0032] Combined with quantum computing and neuromorphic technology, a new technical path is provided for intelligent manufacturing of automobile wire harnesses.

[0033] It should be understood that the content described in the summary section is not intended to limit the key or important features of the embodiments of the present application, nor to limit the scope of the present application. Other features of the present application will become apparent through the following description. BRIEF DESCRIPTION OF DRAWINGS

[0034] The above and other features, advantages, and aspects of the embodiments of the present application will become more apparent with reference to the following detailed description when taken in conjunction with the accompanying drawings, in which like reference characters designate like elements in which:

[0035] Figure 1 A schematic diagram of an automobile wire harness production line monitoring management system in an embodiment of the present application is shown.

[0036] Figure 2 A schematic diagram of an automobile wire harness production line monitoring management method in an embodiment of the present application is shown, which can be executed by the system in Figure 1 . DETAILED DESCRIPTION

[0037] To make the purposes, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of protection of the present application.

[0038] In addition, the term "and / or" herein is only a description of the association relationship between the associated objects, which means that there can be three relationships, for example, A and / or B, which can represent the three cases of A alone, A and B together, and B alone. In addition, the character " / " herein generally represents an "or" relationship between the associated objects before and after it.

[0039] The automobile wire harness production line monitoring management method and system provided by the application realize full-process quality control from the atomic level to the device level through multi-scale cooperative monitoring and real-time optimization, improve quality stability, reduce energy consumption and loss, and promote the upgrading of wire harness production to high-precision intelligent manufacturing.

[0040] In a first aspect, the embodiments of the application disclose an automobile wire harness production line monitoring management system.

[0041] Figure 1 A schematic diagram of an automobile wire harness production line monitoring management system in the embodiments of the application is shown.

[0042] Referring to Figure 1 The system comprises a quantum processing unit for constructing the quantum microscopic layer, a neuromorphic processing unit for constructing the neuromorphic mesoscopic layer, an edge computing unit for constructing the classical macroscopic layer, and a multi-scale sensing unit comprising a nanoscale sensor, a spectral detection device, a distributed optical fiber sensor and a high-frequency pressure sensor; the quantum processing unit, the neuromorphic processing unit, the edge computing unit and the multi-scale sensing unit are connected through a data transmission protocol.

[0043] The quantum processing unit comprises a quantum processor and a supporting quantum control module. The quantum processor adopts a multi-qubit architecture and can run a variational quantum eigensolver to solve the electronic structure equation of a terminal material and generate interatomic interaction parameters. The quantum control module is responsible for the initialization, manipulation and measurement of quantum states to ensure the stability of the quantum computing process. The neuromorphic processing unit takes a neuromorphic chip as the core and integrates a spiking neural network operation module. The module can dynamically adjust the connection weights between neurons according to the rules of synaptic plasticity, receive and process the microscopic parameters from the quantum processing unit, and convert them into mesoscopic scale material evolution data such as grain deformation trend and oxidation film state information.

[0044] The edge computing unit is composed of an industrial-grade server and a motion control module. The industrial-grade server is built-in with a multi-body dynamics model, can receive the mesoscopic data output by the neuromorphic processing unit, and combine with the preset process standard to generate adjustment instructions such as crimping pressure, temperature and speed through a closed-loop control algorithm; the motion control module converts the instructions into driving signals to control the execution components of the devices such as the crimping machine. In the multi-scale sensing unit, the nanoscale sensor is deployed at the key contact position of the crimping die to capture atomic-level displacement changes; the spectral detection device obtains molecular structure information by analyzing the scattering spectrum of the terminal material; the distributed optical fiber sensor is laid along the wire to monitor the strain distribution in the mesoscopic scale in real time; the high-frequency pressure sensor is installed on the crimping cylinder to collect macroscopic pressure dynamic data. The data collected by these sensors are preprocessed and sent to the corresponding processing units respectively.

[0045] Data transmission between units adopts a hierarchical protocol architecture. The quantum processing unit and the neuromorphic processing unit communicate through a low-latency quantum-classical interface protocol to ensure efficient transmission of microscopic parameters. The neuromorphic processing unit and the edge computing unit adopt the industrial Ethernet protocol to realize real-time interaction between mesoscopic data and macroscopic control commands. The multi-scale sensing unit and each processing unit are connected through a time-sensitive networking protocol to ensure time synchronization of data acquisition and processing. Through this hardware architecture and collaborative method, a stable operating environment is provided for the realization of monitoring and management methods for automotive wiring harness production lines, supporting full-process monitoring and control from microscopic to macroscopic levels.

[0046] This system is used to execute a method for monitoring and managing an automotive wiring harness production line disclosed in the second aspect of the embodiments of this application, so as to realize the monitoring and management of the automotive wiring harness production line.

[0047] Secondly, embodiments of this application disclose a method for monitoring and managing automotive wiring harness production lines.

[0048] Figure 2 A schematic diagram of a monitoring and management method for an automotive wiring harness production line according to an embodiment of this application is shown. This method can be... Figure 1 The system execution within.

[0049] Reference Figure 2 The method specifically includes the following steps:

[0050] S1: Construct a quantum-neuromorphic-classical three-level collaborative architecture, which includes a quantum microscopic layer for atomic-level simulation, a neuromorphic mesoscopic layer for grain-scale analysis, and a classical macroscopic layer for equipment process control.

[0051] When constructing the quantum microscopic layer, a mathematical model of interatomic interactions is established based on the principles of quantum mechanics. The Hamiltonian is used to describe the energy state of the system, and its expression is: ,in The vacuum permittivity (an artificially set physical constant with a value of...) ), The amount of electron charge (artificially set, value) ), and Atoms and atoms The position vector (obtained prior through quantum mechanics computation). For embedding atomic energy (based on atomic density) It was calculated beforehand. (Determined by the positions of surrounding atoms). This formula is used to calculate the total energy between atoms, supporting atomic-level simulation capabilities at the quantum microscopic level.

[0052] When constructing the neuromorphic mesoscopic layer, a pulse neuron dynamics model is used to describe the information processing process, and the model expression is wherein is a membrane time constant (artificially set, value is 20 ms), is a membrane potential (a state quantity obtained by real-time monitoring), is a synaptic current (determined by the presynaptic pulse and the weight, and the weight is calculated in advance through the STDP rule), is a resting potential (artificially set, value is -70 mV). The model simulates the pulse firing characteristics of neurons, and realizes information integration and transmission at the mesoscopic scale.

[0053] When constructing the classical macroscopic layer, the device motion equation is established based on the many-body dynamics theory, and the Lagrangian equation is used to describe the dynamic behavior of the system, and the expression is wherein is a Lagrangian function (L) is a kinetic energy, is a potential energy, both of which are calculated in advance through device motion parameters), is a generalized coordinate (a parameter describing the position of the device, obtained by real-time acquisition), is a generalized velocity (a time derivative of , calculated in advance), is a generalized force (including driving force and resistance, determined by hydraulic system parameters and friction coefficient, and the friction coefficient is artificially set). The equation is used to describe the motion and force of the device such as the crimping machine, and provides a mathematical basis for macroscopic process control. Through the construction of the above three levels of mathematical models, a complete three-level collaborative architecture is formed, and each level realizes parameter interaction through a data transmission protocol, supporting the calculation of interatomic interaction parameters, the conversion of mesoscopic material evolution data, and the adjustment of macroscopic process parameters in the subsequent steps.

[0054] S2: Calculate the interatomic interaction parameters of the terminal material through the quantum microcosmic layer.

[0055] In the method of this step, the quantum microcosmic layer uses a variational quantum eigen-solver, which includes a quantum bit circuit for solving an electronic structure equation of the terminal material to obtain interatomic bond energy parameters; the simulation time step of the quantum microcosmic layer is femtosecond level (the time step is 1 fs, which is artificially set to match the time scale of atomic level motion), and the interatomic interaction parameters include atomic displacement and local stress value.

[0056] When solving the electronic structure equation, the time-dependent Schrödinger equation is used wherein is a reduced Planck constant (a physical constant artificially set, value is ), is the quantum state wave function (encoded by quantum bit circuit, whose parameters are determined by human-set quantum gate operations), is the Hamiltonian operator (composed of interatomic Coulomb interaction and electron kinetic energy, where atomic position parameters are obtained by multi-scale sensing unit in advance). This equation is used to describe the evolution of the quantum state of electrons and atoms, and is the basis for calculating interatomic bond energy.

[0057] The variational quantum eigen-solver minimizes the energy expectation value Solve the bond energy parameters, where is the parameter of the quantum circuit (initial value is set by human, and is adjusted iteratively by classical optimization algorithm), is the parameterized quantum state (determined by quantum state, which is an intermediate result obtained by prior calculation). The interatomic bond energy parameters obtained by this process reflect the strength of the interaction between atoms.

[0058] The calculation of atomic displacement uses , where is the atomic position vector at time (the position vector is obtained by quantum microscopic simulation, which is a prior calculation result), is the initial position vector of atomic (the lattice equilibrium position set by human), which is used to quantify the position change of atoms during simulation.

[0059] The local stress value is calculated by the stress tensor formula , where is the representative volume element (set by human, corresponding to a spatial volume containing atoms), is the force on atomic in the direction (calculated by the gradient of the Hamiltonian operator, which is a prior calculation result), is the position component of atomic in the direction (real-time output by quantum simulation, which is a prior calculation result). This formula converts atomic-level forces into macroscopically recognizable stress values, which are used to evaluate the stress state inside the material.

[0060] S3: receiving the interatomic interaction parameters through the neuromorphic mesoscopic layer, and converting them into mesoscale material evolution data.

[0061] In the method of the present step, the neuromorphic mesoscopic layer adopts a spiking neural network, the spiking neural network adjusts the weight through a synaptic plasticity rule, the synaptic plasticity rule realizes weight update based on pulse time difference; the spiking neural network of the neuromorphic mesoscopic layer adopts a neuron model with a membrane time constant, the membrane time constant is a preset millisecond level value (the value is artificially set to 20 ms, used to match the time period of the crimping process), and the synaptic weight is adjusted according to the time difference of the pre-synaptic and post-synaptic pulses.

[0062] After the interatomic interaction parameters are received by the spiking neural network, they are converted into input currents of neurons, and the calculation formula of the input current is , wherein is the atomic displacement (calculated in the previous step S2), is the local stress value (calculated in the previous step S2), and is the conversion coefficient (artificially set to and ), and the formula realizes the mapping of micro parameters to neuron input signals.

[0063] The membrane potential evolution of the neuron model follows , wherein is the membrane time constant (i.e. preset 20 ms), is the current membrane potential (a real-time calculated state quantity), is the resting potential (artificially set to -70 mV), is the membrane resistance (artificially set to ), is the input current (calculated by the above formula, which is a previous calculation result), and the model describes the dynamic response of the neuron to the input signal, and generates a pulse output when the membrane potential reaches the threshold (artificially set to -55 mV).

[0064] The synaptic plasticity rule adopts the STDP (spike time-dependent plasticity) mechanism, and the weight update formula is , wherein is the pulse time difference (a real-time monitored time interval) of the post-synaptic neuron and the pre-synaptic neuron , and are learning rates (artificially set to 0.01 and 0.005, respectively), and are time constants (artificially set to 20 ms), For the synaptic weight (initial value set artificially to 50nS, dynamically updated by the formula), the rule enables the neural network to adjust the connection strength according to the time correlation characteristics of the microscopic parameters, realizing the learning and prediction of mesoscopic phenomena such as grain deformation.

[0065] The mesoscale material evolution data (such as the grain deformation rate ) is calculated by the pulse firing rate, and the formula is , wherein is the average pulse firing rate of the neuron (calculated in a 10ms time window, which is a prior calculation result), is the conversion coefficient (set artificially to ), which converts the electrical activity of the neuron into a quantifiable mesoscopic material evolution index, completing the scale conversion from micro to meso.

[0066] S4: receiving the mesoscale material evolution data through the classical macroscopic layer, constructing a device dynamics model and adjusting process parameters.

[0067] In the method of this step, the device dynamics model of the classical macroscopic layer adopts a many-body dynamics equation, and the crimping pressure, temperature and speed are adjusted through a closed-loop control algorithm to make the terminal quality parameters meet the preset threshold; the simulation step of the device dynamics model of the classical macroscopic layer is millisecond level (the step is set artificially to 1ms to match the response frequency of the crimping machine servo system), and the response time of the adjustment of the process parameters does not exceed the preset millisecond level threshold (the threshold is set artificially to 20ms, which is determined based on the mechanical inertia characteristics of the equipment).

[0068] The device dynamics model is constructed based on a modified many-body dynamics equation, and the expression is , wherein is the mass matrix (composed of the mass parameters of the ram, die and other components, and the parameter values are set artificially based on the equipment design drawings), is the damping matrix (calculated in advance through system identification experiments, related to the motion speed), is the stiffness matrix (containing the stiffness parameters converted from the mesoscopic material evolution data, , wherein is the initial stiffness, set artificially to is the conversion coefficient, set artificially to is the mesoscopic grain deformation rate, calculated in advance by the S3 step), is the generalized coordinate (describing the position of the ram, collected in real time by the encoder), is the hydraulic driving force (output by the servo valve control, which is a controlled variable), is the equivalent force fed back at the mesoscopic level (calculated based on the oxide film rupture area, is set artificially The equation is used to describe the dynamic force relationship between the equipment and the workpiece during the crimping process, and provides a mechanical basis for process parameter adjustment.

[0069] The closed-loop control algorithm uses a PID controller, and the core formula is , wherein is the control output (corresponding to the opening of the hydraulic valve or the heating power), is the terminal mass parameter deviation (F is the preset pull-off force threshold, which is artificially set to 20 N, is the real-time pull-off force, which is calculated in advance by the pull force sensor), , , are PID parameters (based on the Ziegler-Nichols method and artificially adjusted). Through this algorithm, the crimping pressure , temperature and speed are adjusted in real time to ensure that is within the allowable range .

[0070] The process parameter adjustment follows the dynamic correlation rule: the crimping pressure , wherein is the reference pressure (artificially set to 20 MPa), is calculated from the PID output (the artificially set value is ); the temperature is the reference temperature (artificially set to is related to the mesoscopic oxide film thickness , the artificially set value is is the target oxide film thickness, is calculated in advance by step S3); the speed is dynamically limited according to the pressure adjustment (the artificially set value is 30 times / min, is the limit pressure, artificially set to 30 MPa), to ensure the coordination of parameter adjustment. Through the above model and algorithm, the classical macroscopic layer realizes the closed-loop conversion of mesoscopic material evolution data to macroscopic process parameters. Under the premise of meeting the terminal quality threshold, the dynamic adaptation of material microcharacteristics changes avoids the quality fluctuations caused by traditional fixed parameter control.

[0071] S5: The quantum microscopic layer, the neuromorphic mesoscopic layer and the classical macroscopic layer realize data transmission and feedback through a cross-scale data interaction mechanism.

[0072] S5: The quantum microscopic layer, the neuromorphic mesoscopic layer and the classical macroscopic layer realize data transmission and feedback through a cross-scale data interaction mechanism.

[0073] ​In the method of the present step, the cross-scale data interaction mechanism comprises: the quantum microscale layer converts quantum state data into classical characteristic parameters through a quantum operator; the neuromorphic mesoscale layer converts pulse coding signals into mesoscale characteristic parameters; and the classical macroscale layer converts process parameters into external field parameters recognizable by the quantum layer.

[0074] The conversion process of the quantum operator is , wherein is a classical characteristic parameter (such as an average atomic spacing), is a probability distribution of a quantum state measurement result (obtained by measuring quantum bits of the quantum microscale layer, and is a prior calculation result), is a physical quantity corresponding to each quantum state (such as an eigenvalue of an atomic position, and is artificially defined based on quantum mechanics theory), is the number of quantum states (artificially set to 64, matching the dimension of a quantum bit circuit). The formula converts the probabilistic description of the quantum state into deterministic classical parameters through statistical averaging, and realizes the conversion of the transmissible format of quantum data to a neuromorphic processing unit.

[0075] The pulse signal conversion of the neuromorphic mesoscale layer adopts and , wherein is the number of pulses in a unit time (output in real time by a pulse neural network, and is a prior calculation result), is a statistical time window (artificially set to 1 ms), is a pulse frequency, is a conversion coefficient (artificially set to ), is a mesoscale characteristic parameter (such as an oxidation film rupture area). The former formula calculates the pulse firing frequency, and the latter formula maps the frequency to a mesoscale physical quantity, realizing the conversion of neuromorphic signals to macroscale material evolution data that can be analyzed.

[0076] The external field parameter conversion from the classical macroscale layer to the quantum layer is , wherein is an external field term in a quantum Hamiltonian (used to correct the energy calculation of the quantum microscale layer), is a crimping pressure (output by a closed-loop control algorithm of the classical macroscale layer, and is a prior calculation result), is a crimping temperature (collected by a sensor of the classical macroscale layer, and is a prior calculation result), and are coupling coefficients (artificially set to and . The formula converts the macroscale process parameters into an external field energy that can be described by quantum mechanics, so that the quantum microscale layer can respond to the macroscale process changes in real time, forming a cross-scale feedback closed loop.

[0077] S6: Multi-objective optimization of the process parameters by a quantum optimization algorithm, the multi-objective optimization taking the terminal quality parameter, the energy consumption parameter and the equipment wear parameter as optimization variables and satisfying a preset threshold condition of the terminal quality parameter.

[0078] In this step, a quantum approximate optimization algorithm (QAOA) is used to realize multi-objective optimization. First, a target function is constructed , wherein is a terminal quality parameter (represented by a pull-off force deviation, , obtained by classical macroscopic layer detection and belonging to a prior calculation result; is a preset threshold value, artificially set as 80N, is an energy consumption parameter (unit time energy consumption, obtained by device sensor collection and belonging to a prior calculation result), is an equipment wear parameter (represented by a die wear amount, calculated based on a running time and a pressure, is a wear coefficient, artificially set as is a running time, obtained by real-time recording; is a crimping pressure, output by a classical macroscopic layer and belonging to a prior calculation result); is a weight coefficient (artificially set to satisfy , wherein is not less than 0.5 to preferentially ensure quality. The target function comprehensively quantifies optimization requirements of quality, energy consumption and wear, and the smaller the value is, the better the comprehensive benefit is.

[0079] The quantum approximate optimization algorithm prepares an optimized state through parameterized quantum circuits. Circuit parameters ( is a circuit layer number, artificially set as 5), and the optimal process parameters are solved by minimizing the expected value of the target function , wherein is a parameterized quantum state (generated by a quantum bit circuit and based on construction). In the optimization process, a constraint condition (i.e., a preset threshold condition of the terminal quality parameter) needs to be satisfied. By introducing a penalty term ( is a penalty coefficient, artificially set as 100) into the target function, the constrained optimization is converted into unconstrained optimization .

[0080] The finally output optimal process parameters include a crimping pressure , a temperature and a speed , which are obtained by decoding quantum measurement results, i.e., and The calculation method is the same, wherein is a preset pressure discrete value (a set of candidate parameters set artificially), is the probability of the quantum state being measured to the state (output by a quantum optimization algorithm, which belongs to the previous calculation result). Through the optimization process, the energy consumption and equipment loss are collaboratively reduced under the premise of ensuring the terminal quality meets the standard.

[0081] By constructing a quantum-neuromorphic-classical three-level collaborative architecture, the quantum micro layer captures atomic-level interaction parameters (such as atomic displacement, local stress) based on a variational quantum eigen-solver, breaking through the perception limitations of traditional macro monitoring of micro features, and identifying potential defect inducements such as stress concentration at the atomic scale; the neuromorphic mesoscopic layer converts micro parameters into mesoscopic material evolution data (such as grain deformation, oxide film state) through pulse neural networks and synaptic plasticity rules, realizing dynamic fusion and efficient processing of cross-scale data, and solving the problem of multi-scale information fragmentation; the classical macro layer adjusts process parameters such as pressure and temperature in real time based on the multi-body dynamics model and closed-loop control algorithm, forming a closed-loop link from micro perception to macro control, and ensuring that the terminal quality parameters are stable within the preset threshold.

[0082] The cross-scale data interaction mechanism realizes the bidirectional transmission of quantum state data, mesoscopic pulse signals, and macro process parameters through quantum unit elements, pulse signal conversion, and external field parameter mapping, ensuring the consistency and real-time of data at each level, and avoiding the "semantic gap" in information transmission; the quantum optimization algorithm performs multi-objective optimization with terminal quality, energy consumption, and equipment loss as the target, realizing collaborative optimization of resource allocation under the premise of meeting the quality threshold.

[0083] In summary, the above technical means expand the defect identification dimension through atomic-level perception, break the information barrier through multi-scale fusion, improve the quality stability through closed-loop control, guarantee system collaboration through cross-scale interaction, and realize efficient resource utilization through quantum optimization. Ultimately, it can be deduced that this method can realize the whole-process precise management from micro defect germination to macro process control, improve the consistency and stability of terminal quality, optimize the energy consumption and equipment loss of the production process, and promote the upgrade of wire harness production from passive detection to active prevention.

[0084] It should be noted that, for each of the foregoing method embodiments, in order to simply describe, it is expressed as a series of action combinations, but those skilled in the art should know that the application is not limited by the order of the described actions, because according to the embodiments of the application, certain steps can be performed in other order or simultaneously. Secondly, those skilled in the art should know that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the application.

[0085] To sum up, the present application at least contains the following beneficial effects:

[0086] 1. Realize the whole-process multi-scale collaborative monitoring from atomic level to device level, break through the limitation of traditional single-scale monitoring, accurately capture the initiation of microscopic defects and correlate the macroscopic quality change;

[0087] 2. Through the cross-scale data interaction mechanism and neuromorphic processing, realize the efficient fusion and real-time transmission of different level data, solve the problem of low prediction accuracy caused by multi-scale information fragmentation;

[0088] 3. Combined with quantum optimization algorithm and closed-loop control, realize the collaborative optimization of energy consumption and equipment loss on the premise of guaranteeing the terminal quality, and improve the comprehensive benefit of production process.

[0089] The above description is only the preferred embodiment of the present application and the explanation of the applied technical principles. Those skilled in the art should understand that the disclosed range in the present application is not limited to the technical solutions formed by the specific combination of the above technical features, and also covers other technical solutions formed by any combination of the above technical features or their equivalent features without deviating from the aforementioned disclosed concept. For example, the technical solutions formed by mutually replacing the above features with the technical features disclosed in the present application (but not limited to) having similar functions.

Claims

1. A method for monitoring and managing an automotive wiring harness production line, characterized in that, include: A three-tiered collaborative architecture of quantum-neuromorphic-classical methods is constructed, comprising a quantum microscopic layer for atomic-level simulation, a neuromorphic mesoscopic layer for grain-scale analysis, and a classical macroscopic layer for equipment process control. The quantum microscopic layer calculates the interatomic interaction parameters of the terminal materials; the neuromorphic mesoscopic layer receives these parameters and converts them into mesoscopic-scale matter evolution data; the classical macroscopic layer receives this mesoscopic-scale matter evolution data, constructs an equipment dynamics model, and adjusts process parameters. The quantum microscopic layer, neuromorphic mesoscopic layer, and classical macroscopic layer achieve data transmission and feedback through a cross-scale data interaction mechanism. The quantum microlayer employs a variable quantum eigenvalue solver, which includes a quantum bit circuit, to solve the electronic structure equation of the terminal material to obtain interatomic bond energy parameters. The cross-scale data interaction mechanism includes: the quantum microscopic layer converts quantum state data into classical feature parameters through a quantum cascade computation unit; The neuromorphic mesoscopic layer converts pulse-coded signals into mesoscopic feature parameters; the classical macroscopic layer converts process parameters into external field parameters that can be recognized by the quantum layer. The neuromorphic mesoscopic layer employs a spiking neural network, which adjusts weights through synaptic plasticity rules, which update weights based on pulse time differences.

2. The method for monitoring and managing automotive wiring harness production lines according to claim 1, characterized in that, The device dynamics model of the classical macroscopic layer adopts multibody dynamics equations and adjusts the crimping pressure, temperature and speed through a closed-loop control algorithm to ensure that the terminal quality parameters meet the preset threshold.

3. The method for monitoring and managing automotive wiring harness production lines according to claim 1, characterized in that, The simulation time step of the quantum microlayer is on the femtosecond scale, and the interatomic interaction parameters include atomic displacement and local stress values.

4. The method for monitoring and managing automotive wiring harness production lines according to claim 1, characterized in that, The neuromorphic mesoscopic layer's spiking neural network employs a neuron model with a membrane time constant, which is a preset millisecond-level value. The synaptic weights are adjusted according to the time difference between the pulses before and after the synapse.

5. The method for monitoring and managing automotive wiring harness production lines according to claim 2, characterized in that, The simulation step size of the device dynamics model in the classical macroscopic layer is in the millisecond range, and the adjustment response time of the process parameters does not exceed a preset millisecond threshold.

6. The method for monitoring and managing automotive wiring harness production lines according to claim 1, characterized in that, Also includes: The process parameters are optimized using a quantum optimization algorithm with multi-objective optimization variables, including terminal quality parameters, energy consumption parameters, and equipment loss parameters, while also satisfying a preset threshold condition for the terminal quality parameters.

7. A monitoring and management system for an automotive wiring harness production line, characterized in that, The method for monitoring and managing an automotive wiring harness production line according to any one of claims 1-6 comprises: a quantum processing unit for constructing the quantum microscopic layer; a neuromorphic processing unit for constructing the neuromorphic mesoscopic layer; an edge computing unit for constructing the classical macroscopic layer; and a multi-scale sensing unit, including a nanoscale sensor, a spectral detection device, a distributed optical fiber sensor, and a high-frequency pressure sensor; wherein the quantum processing unit, the neuromorphic processing unit, the edge computing unit, and the multi-scale sensing unit are connected via a data transmission protocol.

Images