Intelligent wire harness adaptive control method and system

Abstract

The invention provides an intelligent wire harness adaptive control method and system, and the method comprises the steps: S2, extracting a corresponding current range and a communication protocol from an output mode library according to an equipment type judgment result, and determining an initial output parameter; s4, executing the adjusted output parameters through a low-power-consumption communication module, obtaining equipment operation state data, and judging whether the real-time operation requirement is met or not; s6, after the pre-adjustment parameters are executed, equipment response data and energy consumption data are obtained, and whether system overload or power consumption exceeding exists or not is judged; s8, updating the equipment feature database and the output mode library according to the adjusted operation configuration, and obtaining updated collaborative performance indexes and energy consumption indexes; and S9, if the collaborative performance index and the energy consumption index do not reach the performance threshold, repeatedly executing the combined optimization process of the dynamic adjustment algorithm and the feature analysis algorithm. According to the invention, high-efficiency cooperation and energy consumption optimization of the wire harness and the intelligent equipment are realized.

Description

Technical Field

[0001] This invention relates to the field of intelligent manufacturing technology, and in particular to an intelligent wire harness adaptive control method and system. Background Technology

[0002] The integration of smart manufacturing and IoT technology is a core trend in today's industrial sector. Its importance lies in significantly improving equipment connectivity and production efficiency, and driving digital transformation as a key to competitiveness. However, the development of this field has not been without its challenges.

[0003] Currently, many solutions rely on traditional wiring harness designs and communication protocols, which generally suffer from poor connectivity adaptability, insufficient power consumption control, and low data transmission efficiency. These problems limit the inter-device collaboration capabilities and fail to meet the increasingly complex demands of intelligent applications, especially in dynamic environments. Although the industry is exploring more advanced connectivity technologies, the limitations of existing methods remain significant.

[0004] Traditional wire harnesses typically employ fixed current output and a single data transmission mode, lacking the ability to intelligently identify the types of connected devices. This design often leads to performance degradation, or even overload or device damage, when faced with diverse intelligent devices due to its inability to adjust flexibly. Furthermore, the low integration of low-power communication modules results in excessive energy consumption during prolonged operation, limiting its application in resource-sensitive scenarios. These issues expose the shortcomings of existing technologies in terms of adaptability and optimization capabilities. Focusing on specific technical aspects, the core challenges in this field mainly lie in three areas: first, how the wire harness can proactively identify the type of connected device and establish efficient communication; second, how to dynamically adjust the current output and data transmission mode according to device requirements; and third, how to avoid performance trade-offs while integrating low-power communication modules. The lack of effective solutions to these challenges makes it difficult for wire harnesses to achieve performance optimization in complex and ever-changing connection scenarios, while also increasing the risk of system overload, thus creating unique technical difficulties.

[0005] Therefore, designing a wiring harness system that can actively identify device types, dynamically adjust output modes, and optimize power consumption has become a key issue in improving the interconnectivity and reliability of smart devices.

[0006] Solving this problem will directly affect the stability and efficiency of IoT devices in practical applications, and innovative approaches are urgently needed to achieve a breakthrough. Summary of the Invention

[0007] To address the problems mentioned in the background art, a first aspect of the present invention provides an intelligent harness adaptive control method, comprising: S1. Obtain the voltage characteristics and communication signal characteristics of the connected device, and perform pattern matching using a pre-established device characteristic database to obtain the device type judgment result; S2, based on the device type determination result, extract the corresponding current range and communication protocol from the output mode library, and determine the initial output parameters; S3, monitor the current change and data transmission rate of the device in real time, and use a dynamic adjustment algorithm to optimize the initial output parameters and generate adjusted output parameters; S4, execute the adjusted output parameters through the low-power communication module, obtain device operating status data, and determine whether the real-time operating requirements are met; S5. If the real-time operation requirements are not met, then based on the changing trend of the equipment operation status data, a prediction algorithm is used to calculate the peak current demand and bandwidth demand in the future cycle, and generate pre-adjustment parameters. S6. After executing the pre-adjustment parameters, obtain the device response data and energy consumption data, and determine whether there is system overload or excessive power consumption. S7. If there is system overload or excessive power consumption, extract overload characteristic parameters and high power consumption characteristic parameters from historical operating data, and use characteristic analysis algorithm to adjust the operating configuration of the low power communication module. S8. Update the device feature database and output mode library according to the adjusted operating configuration, and obtain the updated collaborative performance indicators and energy consumption indicators. S9. If the collaborative performance index and energy consumption index do not reach the performance threshold, the combined optimization process of the dynamic adjustment algorithm and the feature analysis algorithm is repeated.

[0008] Optionally, step S1 involves acquiring the voltage characteristics and communication signal characteristics of the connected device, performing pattern matching using a pre-established device characteristic database, and obtaining a device type determination result, including: Step S11: Obtain the voltage characteristics and communication signal characteristics of the connected device, and collect raw data through sensors to obtain a preliminary feature set; Step S12: The preliminary feature set is filtered and normalized using preprocessing methods to obtain standardized feature data; Step S13: Using a pre-established device feature database, the standardized feature data is compared to obtain a matching candidate set; Step S14: If the similarity in the candidate set exceeds the similarity threshold, the candidate set is classified using the support vector machine algorithm to determine the device type. Step S15: Perform a secondary verification based on the classification results and the device characteristics in the database to obtain type confirmation data; Step S16: Determine the equipment operating status by analyzing the correlation between type confirmation data and communication signal characteristics; Step S17: Use the decision tree algorithm to comprehensively analyze the changing trends of the operating status and voltage characteristics to obtain the final judgment result.

[0009] Optionally, step S2, based on the device type determination result, extracts the corresponding current range and communication protocol from the output mode library to determine the initial output parameters, including: Step S21: Obtain the judgment result through the device type and determine the type matching content; Step S22: Extract the output pattern from the MySQL pattern library based on the judgment result to obtain the corresponding configuration data; Step S23: Use the output mode and the NumPy library to match the current range and determine the range extraction result; Step S24: Obtain the communication protocol from the Redis cache according to the output mode to get the protocol selection content; Step S25: Determine the initial parameter configuration based on the range extraction results and protocol selection content; Step S26: After obtaining the initial parameter configuration, determine the output configuration data; Step S27: Adjust the device type matching according to the output configuration data to obtain the final output parameters.

[0010] Optionally, in step S3, the current change and data transmission rate of the device are monitored in real time, and the initial output parameters are optimized using a dynamic adjustment algorithm to generate adjusted output parameters, including: Step S31: Obtain real-time data content by collecting the current change and data transmission rate of the device through sensors; Step S32: Extract the change value and transmission rate based on the real-time data content to determine the dynamic adjustment requirements; Step S33: If the change value exceeds the change threshold, the initial parameters are processed by a dynamic adjustment algorithm to obtain the optimized parameter result. Step S34: Based on the optimized parameter results and transmission rate, obtain the adjusted communication configuration and determine the output parameter content; Step S35: Update the device's acquisition rate by outputting the parameter content to obtain the adjusted real-time data; Step S36: Analyze the changing trend based on the adjusted real-time data to determine whether the parameters need to be optimized again; Step S37: If the trend of change is stable, the final operating parameters are obtained by fixing the current output parameters.

[0011] Optionally, step S4, which involves executing the adjusted output parameters through a low-power communication module to obtain device operating status data and determine whether the real-time operating requirements are met, includes: Step S41: Perform parameter adjustment through the low-power communication module and obtain the adjusted output parameter data; Step S42: Extract equipment operating status information from the adjusted output parameter data to obtain an equipment status description; Step S43: Analyze the device status description using a preset status threshold to determine whether it deviates from the normal operating range; Step S44: If the operation deviates from the normal operating range, the output parameters are readjusted through the communication module to obtain the updated status data. Step S45: Based on the updated status data, use the K-means algorithm to cluster the device operation mode and determine the operation trend; Step S46: Based on the operating trend, optimize the parameter adjustment strategy through the low-power communication module to obtain new status data; Step S47: If the new status data does not reach the preset status threshold, adjust the data acquisition frequency and reacquire the device operating status information.

[0012] Optionally, in step S5, if the real-time operation requirement is not met, a prediction algorithm is used to calculate the peak current demand and bandwidth demand in future cycles based on the changing trend of the equipment operation status data, and pre-adjustment parameters are generated, including: Step S51: Obtain the trend of change through equipment operating status data, calculate the trend slope using time series analysis algorithm, and obtain the data change characteristics; Step S52: Determine the trend direction based on the data change characteristics. If the trend slope is greater than the slope threshold, calculate the peak demand in the future period using the prediction algorithm to obtain the peak prediction result. Step S53: Extract the distribution characteristics of current demand and bandwidth demand from the peak prediction results, and use a linear regression algorithm to determine the proportional relationship between the demands to obtain the proportional coefficient. Step S54: Calculate the pre-adjustment parameters using the scaling factor, generate the first adjustment parameter for the current requirement, and generate the second adjustment parameter for the bandwidth requirement to obtain the adjustment parameter set; Step S55: If the adjusted parameter set exceeds the preset range, obtain the abnormal mode through historical state data, determine whether dynamic correction is triggered, and obtain the corrected parameter set. Step S56: Based on the corrected parameter set, use interpolation to calculate the continuous adjustment values ​​in future periods to obtain the final adjustment scheme; Step S57: Update the equipment operating status data through the final adjustment scheme, generate the input data for the next cycle, and obtain the updated status dataset.

[0013] Optionally, step S6, after executing the pre-adjustment parameters, involves acquiring device response data and energy consumption data to determine whether there is system overload or excessive power consumption, including: Step S61: After executing the pre-adjustment parameters, obtain response data and energy consumption data from the device to obtain the initial dataset; Step S62: Extract device response features and energy consumption features from the initial dataset to determine the feature set; Step S63: Use the SVM module in the Scikit-learn library to classify the feature set and determine whether the overload state exists; Step S64: If an overload condition exists, the power consumption characteristics are compared with the preset power consumption threshold to determine whether the power consumption exceeds the standard. Step S65: Based on the comparison between the classification results and the power consumption threshold, obtain the abnormal distribution of the system operating status; Step S66: Analyze the changing trends of the operating status through anomaly distribution analysis to obtain the optimization direction for adjusting parameters; Step S67: Update the pre-adjustment parameters according to the optimization direction to obtain the new parameter configuration.

[0014] Optionally, in step S7, if system overload or power consumption exceeds the limit, overload characteristic parameters and high power consumption characteristic parameters are extracted from historical operating data, and the operating configuration of the low-power communication module is adjusted using a feature analysis algorithm, including: Step S71: If the system overload or power consumption exceeding the limit trigger condition is met, historical data is obtained from the pre-established database, and overload characteristics and high power consumption characteristics are extracted to form a feature set. Step S72: For the feature set, use the K-means clustering algorithm to analyze the distribution patterns of overload features and high power consumption features to obtain the feature distribution results; Step S73: Based on the feature distribution results, use principal component analysis to determine the key parameters affecting the operation of the communication module and form a set of key parameters; Step S74: If the set of key parameters exceeds the parameter threshold, the gradient descent algorithm is used to update the running configuration and generate an adjusted configuration scheme. Step S75: Using the adjusted configuration scheme, real-time operating data is obtained from the sensors of the communication module, and the support vector machine algorithm is used to determine whether the module's operating state is stable, thus obtaining the state evaluation result. Step S76: Based on the state assessment results, if the system is unstable, extract new feature parameters from the real-time running data, use the K-means clustering algorithm to readjust the configuration scheme, and generate an optimized running configuration. Step S77: Using the optimized operating configuration, update the operating status of the communication module and obtain the final module operating data.

[0015] Optionally, step S8 involves updating the device feature database and output mode library according to the adjusted operating configuration, and obtaining updated collaborative performance indicators and energy consumption indicators, including: Step S81: Process the adjusted running configuration through a preset running configuration parsing process to obtain the data set after configuration adjustment; Step S82: Update the device feature database according to the data set after configuration adjustment, and obtain the updated device feature description set; Step S83: Extract key features from the updated device feature description set to obtain a subset of data after feature extraction; Step S84: Adjust the output mode library using the data subset after feature extraction to obtain the adjusted output mode parameter set; Step S85: Execute a performance analysis algorithm on the adjusted output mode parameter set, using the scikit-learn library in Python to perform performance analysis and determine the range of variation of the collaborative performance index. Step S86: By combining the variation range of the collaborative performance index with the energy consumption optimization rules, energy consumption optimization is achieved using the optimization toolbox in MATLAB to obtain the optimized energy consumption index values. Step S87: If the optimized energy consumption index value exceeds the energy consumption index threshold, the running configuration is adjusted using the support vector machine algorithm. The support vector machine algorithm is implemented using the scikit-learn library in Python to obtain new configuration adjustment data.

[0016] A second aspect of the present invention provides an intelligent wire harness adaptive control system, which performs intelligent wire harness adaptive control using the method described above, the system comprising: The device feature matching module is used to acquire the voltage characteristics and communication signal characteristics of the connected devices, and to perform pattern matching using a pre-established device feature database to obtain the device type judgment result. The initial parameter determination module is used to extract the corresponding current range and communication protocol from the output mode library based on the device type determination result, and determine the initial output parameters. The dynamic optimization module is used to monitor the current change and data transmission rate of the device in real time, and to optimize the initial output parameters using a dynamic adjustment algorithm to generate adjusted output parameters. The status monitoring module is used to execute the adjusted output parameters through the low-power communication module, obtain device operating status data, and determine whether the real-time operation requirements are met. The prediction and adjustment module is used to calculate the peak current demand and bandwidth demand in the future period based on the changing trend of the equipment operation status data if the real-time operation demand is not met, and generate pre-adjustment parameters. The overload judgment module is used to obtain device response data and energy consumption data after executing the pre-adjustment parameters, and to determine whether there is system overload or excessive power consumption. The configuration adjustment module is used to extract overload characteristic parameters and high power consumption characteristic parameters from historical operating data if there is system overload or excessive power consumption, and to adjust the operating configuration of the low power communication module using a feature analysis algorithm. The database update module is used to update the device feature database and output mode library according to the adjusted operating configuration, and to obtain the updated collaborative performance indicators and energy consumption indicators. The performance evaluation module is used to repeatedly execute the combined optimization process of the dynamic adjustment algorithm and the feature analysis algorithm if the collaborative performance index and energy consumption index do not reach the performance threshold.

[0017] The present invention provides an intelligent wire harness adaptive control method and system, which can actively establish a connection with intelligent devices and exchange information through a built-in low-power Bluetooth or near-field communication module.

[0018] This invention first acquires the voltage and communication characteristics of the connected device and matches them with a pre-established database to determine the device type. Based on the determination result, the system extracts the corresponding current range and communication protocol from the output mode library to determine the initial output parameters. Subsequently, this invention monitors the device's current changes and data transmission rate in real time and uses a dynamic adjustment algorithm to optimize the output parameters. If the operating requirements are not met, the system predicts future current and bandwidth requirements and generates pre-adjustment parameters. When overload or power consumption exceeds the limit, this invention analyzes the characteristic parameters in historical data and adjusts the communication module configuration. Through continuous optimization and database updates, this invention achieves efficient collaboration and energy consumption optimization between the wiring harness and the intelligent device, improving the system's adaptability and reliability. Attached Figure Description

[0019] Figure 1 This is a flowchart of an intelligent wire harness adaptive control method according to the present invention.

[0020] Figure 2 This is a schematic diagram of the structure of an intelligent wire harness adaptive control system according to the present invention. Detailed Implementation

[0021] The technical solution of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0022] like Figure 1 The first aspect of this invention provides an intelligent harness adaptive control method and system, specifically comprising: S1. Obtain the voltage characteristics and communication signal characteristics of the connected device, and perform pattern matching using a pre-established device characteristic database to obtain the device type judgment result.

[0023] Optionally, this step also includes: Step S11: Obtain the voltage characteristics and communication signal characteristics of the connected device, and collect raw data through sensors to obtain a preliminary feature set.

[0024] Step S12: The preliminary feature set is filtered and normalized using preprocessing methods to obtain standardized feature data.

[0025] Step S13: Using a pre-established device feature database, the standardized feature data is compared to obtain a matching candidate set.

[0026] Step S14: If the similarity in the matching candidate set exceeds the preset similarity threshold, the candidate set is classified using the support vector machine algorithm to determine the device type.

[0027] Step S15: Perform a secondary verification based on the classification results and the device characteristics in the database to obtain type confirmation data.

[0028] Step S16: Determine the operating status of the equipment by analyzing the correlation between the type confirmation data and the characteristics of the communication signal.

[0029] Step S17: Use the decision tree algorithm to comprehensively analyze the changing trends of the operating status and voltage characteristics to obtain the final judgment result.

[0030] Specifically, acquiring the voltage and communication signal characteristics of the connected device is the starting point for collecting raw data through sensors.

[0031] For example, suppose an industrial device monitors its operating voltage and signal waveforms in real time using sensors. The raw data collected might be a sequence of voltage values ​​changing over time, such as 220V, 218V, and 223V, as well as the frequency and amplitude of communication signals. This data constitutes a preliminary set of features, reflecting the device's basic electrical characteristics.

[0032] In one possible implementation, the sensor collects data 10 times per second for one minute, yielding 600 data points, providing sufficient basic information for subsequent analysis. Preprocessing methods to filter and normalize the initial feature set can effectively improve data quality.

[0033] Specifically, filtering removes high-frequency noise from voltage data, such as tiny spikes caused by power grid fluctuations, while preserving the main trend. Normalization scales the data to a range of 0 to 1, for example, mapping voltage values ​​of 200V to 250V to 0 to 1, facilitating subsequent comparisons. This standardized feature data reduces interference from differences in units, significantly improving the accuracy of the algorithm's recognition.

[0034] Using a pre-established database of device characteristics for comparison is a key step in determining the identity of a device.

[0035] For example, the database stores the standard voltage ranges and communication signal patterns of various devices. Device A, for instance, has a voltage range of 210V to 230V and a signal frequency of 50Hz. After matching standardized feature data with these patterns, a similarity score is obtained, such as 0.9 for device A and 0.6 for device B, forming a matching candidate set. This method utilizes historical data to improve recognition efficiency. If the similarity in the matching candidate set exceeds a preset similarity threshold, such as 0.85, the candidate set is classified using a support vector machine algorithm.

[0036] In one embodiment, assuming that the similarity between device A and device C in the candidate set is 0.9 and 0.88 respectively, the support vector machine divides the boundary based on feature vectors (such as mean voltage and signal frequency), and finally determines it as device A. This classification method performs well in high-dimensional data, ensuring the reliability of type determination.

[0037] A second verification based on the classification results and the database can further reduce the risk of misjudgment.

[0038] Preferably, if classified as device A, its voltage characteristics should be consistent with the 210V to 230V range in the database. If it exceeds this range, such as reaching 240V, a reassessment is required. This verification mechanism enhances the reliability of the results through multiple verifications. By analyzing the correlation between type confirmation data and communication signal characteristics, the device's operating status can be determined.

[0039] For example, if the normal signal frequency of device A is 50Hz, and a frequency drop to 45Hz is detected, it may indicate that the device is overloaded or malfunctioning. This correlation analysis combines multi-dimensional features, enhancing the comprehensiveness of condition monitoring. By employing a decision tree algorithm to comprehensively analyze the changing trends of operating status and voltage characteristics, a final judgment can be obtained.

[0040] In one embodiment, the decision tree determines that the device is in an "imminent failure" state based on a voltage drop trend (e.g., 5V / minute) and frequency anomalies (below 48Hz). This method clearly demonstrates the judgment logic through rule-based reasoning, and is easy to interpret and optimize, thus possessing high practical value.

[0041] S2, based on the device type determination result, extract the corresponding current range and communication protocol from the output mode library to determine the initial output parameters.

[0042] Optionally, this step also includes: Step S21: Obtain the judgment result through the device type and determine the type matching content.

[0043] Step S22: Extract the output pattern from the MySQL pattern library based on the judgment result to obtain the corresponding configuration data.

[0044] Step S23: Use the output mode and the NumPy library to match the current range and determine the range extraction result.

[0045] Step S24: Obtain the communication protocol from the Redis cache according to the output mode to get the protocol selection content.

[0046] Step S25: Determine the initial parameter configuration based on the range extraction results and protocol selection content.

[0047] Step S26: After obtaining the initial parameter configuration, determine the output configuration data.

[0048] Step S27: Adjust the device type matching according to the output configuration data to obtain the final output parameters.

[0049] Specifically, after obtaining the judgment result through the device type, determining the content that matches the type is the core starting point of the entire process.

[0050] For example, in one possible implementation, the system has identified the device as a smart bulb, and the type matching content can be the bulb's basic attributes, such as the supported brightness adjustment range and color temperature range. Then, based on the judgment result, the system extracts the output pattern from the MySQL pattern library to obtain the corresponding configuration data.

[0051] It should be noted that the MySQL schema library stores standard configuration templates for various devices. For example, the template for a smart bulb may include static data such as a brightness range of 0-1000 lumens and a color temperature of 2700K-6500K.

[0052] Specifically, during system queries, the template is quickly located based on the device type field, and the configuration data is extracted for subsequent use. An output mode is adopted, and the NumPy library is used to match the current range to determine the range extraction result. This process emphasizes dynamic data adaptation.

[0053] In one embodiment, the current range of a smart bulb may vary depending on its operating state, for example, 10mA in standby mode and 50mA at maximum brightness. The NumPy library analyzes historical current data to quickly determine a reasonable range for the current device, such as 10-60mA, ensuring stable device operation.

[0054] Preferably, this method can also improve the accuracy of range extraction by smoothing data and removing outliers. For the output mode, the communication protocol is retrieved from the Redis cache to obtain the protocol selection content; this step emphasizes efficiency.

[0055] For example, the Redis cache pre-stores the ZigBee and Wi-Fi protocols commonly used by smart bulbs. The system selects the Wi-Fi protocol based on the device's working environment, with a response time of only milliseconds.

[0056] Understandably, this caching mechanism can significantly reduce query latency and ensure real-time performance. Protocol selection may include packet format and encryption method, directly supporting subsequent communication. The initial parameter configuration is determined by combining the range extraction results and protocol selection content; this process integrates the aforementioned data.

[0057] For example, with a current range of 10-60mA combined with the Wi-Fi protocol, the initial system configuration has a maximum power consumption of 5W and a communication frequency of 2.4GHz. This configuration meets both hardware requirements and is compatible with the network environment.

[0058] In one possible implementation, the initial parameters are also fine-tuned based on the device's historical operating records, such as prioritizing energy-saving modes.

[0059] After obtaining the initial parameter configuration, the output configuration data is determined, and this step forms an executable solution.

[0060] Specifically, the output configuration data may include a complete set of parameters such as a specific operating voltage of 220V and a communication timeout of 500ms. This data provides clear instructions for device operation. The final output parameters are obtained by adjusting the device type matching based on the output configuration data.

[0061] For example, if the system detects that the actual current is slightly higher than expected, it adjusts the brightness limit to 900 lumens to form the final parameters. This adjustment better adapts to the actual scenario.

[0062] For example, when considering the final output parameters of a smart bulb from multiple perspectives, the influence of ambient light can be taken into account. If the ambient light is strong, the final parameter may be a lower color temperature of 3000K to enhance comfort; if the network signal is weak, the communication timeout may be extended to 800ms to ensure connection stability. These aspects support each other and work together to ensure the rationality of the parameters.

[0063] Preferably, such fine-tuning can also extend the lifespan of the device and improve the user experience.

[0064] S3, monitor the current change and data transmission rate of the device in real time, and use a dynamic adjustment algorithm to optimize the initial output parameters and generate adjusted output parameters.

[0065] Optionally, this step also includes: Step S31: Obtain real-time data content by collecting the current change and data transmission rate of the device through sensors.

[0066] Step S32: Extract the change value and transmission rate based on the real-time data content to determine the dynamic adjustment requirements.

[0067] Step S33: If the change value exceeds the preset change threshold, the initial parameters are processed by a dynamic adjustment algorithm to obtain the optimized parameter result.

[0068] Step S34: Based on the optimized parameter results and transmission rate, obtain the adjusted communication configuration and determine the output parameter content.

[0069] Step S35: Update the device's acquisition rate by outputting the parameter content to obtain the adjusted real-time data.

[0070] Step S36: Analyze the changing trend based on the adjusted real-time data to determine whether the parameters need to be optimized again.

[0071] Step S37: If the trend of change is stable, the final operating parameters are obtained by fixing the current output parameters.

[0072] Specifically, acquiring real-time data by collecting changes in the device's current and data transmission rate through sensors is the foundation of the entire process.

[0073] For example, in industrial sensor scenarios, sensors can monitor the operating status of equipment, recording in real time the current as it rises from 5mA under low load to 18mA under high load, while the data transmission rate may fluctuate from 10 times per second to 50 times per second. This acquisition method relies on a high-precision sampling module capable of capturing minute changes.

[0074] Understandably, the collected data directly reflects the working status of the equipment, providing the original basis for subsequent analysis.

[0075] In one possible implementation, the change value and transmission rate are extracted based on the real-time data content to determine whether dynamic adjustment is needed.

[0076] For example, suppose the current changes from 5mA to 18mA, a change of 13mA, and the preset threshold for this change is 10mA. Exceeding this threshold indicates a significant change in the device's operating status. Simultaneously, the transmission rate increases from 10 times per second to 50 times per second, indicating an increase in data volume. At this point, the system will recognize the need to adjust the initial parameters to adapt to the current operational requirements.

[0077] It should be noted that this judgment is based on preset rules and can quickly respond to changes in the device status.

[0078] Specifically, if the change exceeds the change threshold, the dynamic adjustment algorithm will process the initial parameters and generate an optimized result.

[0079] For example, the initial current range is 4-20mA, and the algorithm may adjust the upper limit to 22mA based on real-time data to cover higher load demands. The communication protocol remains ModbusRTU, but the baud rate may be increased from 9600bps to 19200bps. This adjustment is derived by analyzing historical data and current trends to ensure that the parameters match the device status.

[0080] Preferably, the adjusted communication configuration is obtained based on the optimized parameter results and transmission rate.

[0081] For example, when the baud rate is increased to 19200bps, the data bits remain at 8 bits, but the stop bits are adjusted to 2 bits to improve transmission stability. This adjusted configuration will be used as the new output parameters to guide device operation. This configuration takes into account the balance between speed and stability, avoiding data loss due to excessively high speeds.

[0082] In one embodiment, the acquisition rate is updated by updating the output parameter content to obtain adjusted real-time data.

[0083] For example, the sampling frequency was increased from 50 times per second to 80 times per second to accommodate more frequent data changes. The adjusted data can more accurately reflect the transition process of current from 18mA to 22mA. This update improves the real-time performance of data acquisition and provides richer information for subsequent analysis.

[0084] For example, by analyzing the changing trends based on the adjusted real-time data, it can be determined whether further parameter optimization is needed. Suppose the current change becomes gradual, decreasing from 22mA to 20mA and stabilizing, and the transmission rate also drops back to 60 times per second. At this point, the system would consider the current parameters to basically meet the requirements.

[0085] In one embodiment, trend analysis can be combined with a time window, such as observing data fluctuations within 5 minutes, to confirm whether it is stable. Finally, if the trend is stable, the configuration is solidified through the current output parameters to obtain the final operating parameters.

[0086] For example, the current range is locked at 4-22mA, the baud rate is 19200bps, and the stop bits are 2. This fixed configuration ensures efficient operation of the device in its current state while retaining some flexibility to cope with possible future fluctuations.

[0087] Understandably, this approach reduces the resource consumption of frequent adjustments and improves the long-term stability of the system.

[0088] S4, the adjusted output parameters are executed through the low-power communication module to obtain device operating status data and determine whether the real-time operation requirements are met.

[0089] Optionally, this step also includes: Step S41: Perform parameter adjustment through the low-power communication module and obtain the adjusted output parameter data.

[0090] Step S42: Extract the equipment operating status information from the adjusted output parameter data to obtain the equipment status description.

[0091] Step S43: Analyze the device status description using a preset status threshold to determine whether it deviates from the normal operating range.

[0092] In step S44, if the data deviates from the normal operating range, the output parameters are readjusted through the communication module to obtain the updated status data.

[0093] Step S45: Based on the updated status data, use the K-means algorithm to cluster the device operation mode and determine the operation trend.

[0094] Step S46: Based on the operating trend, optimize the parameter adjustment strategy through the low-power communication module to obtain new status data.

[0095] Step S47: If the new status data does not reach the preset status threshold, adjust the data acquisition frequency and reacquire the device operating status information.

[0096] Specifically, the parameter adjustment is performed through the low-power communication module, and the adjusted output parameter data is obtained. This can be understood as a fundamental step in optimizing device operation.

[0097] For example, suppose an industrial device communicates via a Bluetooth Low Energy module, with initial parameters including voltage and signal strength.

[0098] In one possible implementation, the communication module adjusts the voltage from 10 volts to 8 volts while simultaneously increasing the signal transmission power. The adjusted data, including voltage values, power consumption levels, and communication latency, is transmitted back through the module. This approach effectively reduces energy consumption while ensuring reliable data transmission. Device operating status information is extracted from the adjusted output parameter data to obtain a device status description, a process that directly reflects the device's health.

[0099] Specifically, a state description can be generated by analyzing key indicators in the returned data, such as temperature, vibration frequency, and response time.

[0100] For example, with a temperature of 45 degrees Celsius, a vibration frequency of 20 Hz, and a response time of 0.5 seconds, the status description might be "stable operation, normal temperature." This provides an intuitive basis for subsequent judgment. Analyzing the equipment status description using preset status thresholds to determine whether it deviates from the normal operating range is a crucial step in ensuring equipment safety.

[0101] In one embodiment, a temperature threshold of 50 degrees Celsius and a vibration frequency threshold of 25 Hz are set. If the device temperature rises to 52 degrees Celsius, exceeding the threshold, it is considered abnormal. This analysis method is simple and efficient, and can quickly locate potential problems. If it deviates from the normal operating range, the output parameters are readjusted through the communication module to obtain updated status data; this step demonstrates timely response to anomalies.

[0102] Preferably, if the temperature is too high, the device power can be reduced to 70% and the fan speed increased via a module. Updated status data may show the temperature dropping to 48 degrees Celsius, returning to the normal range. This dynamic adjustment significantly improves device stability. Based on the updated status data, the K-means algorithm is used to cluster device operating patterns and determine operating trends; this technique aims to uncover patterns behind the data.

[0103] For example, temperature, vibration, and power data are categorized into three operating modes: low load, medium load, and high load. Analysis reveals that the equipment mostly operates in medium load mode, with a stable operating trend. Such clustering analysis helps predict equipment behavior. Based on the operating trend, parameter adjustment strategies are optimized using a low-power communication module to acquire new state data; this process represents a further iteration of the optimization scheme.

[0104] In one possible implementation, if the trend indicates that the medium-load mode is dominant, the sampling interval of the communication module is adjusted to once every 5 seconds, while the voltage is fine-tuned to 7.5 volts. New data may show further reductions in power consumption and improvements in communication efficiency. This strategy better adapts to the operating characteristics of the device. If the new status data does not reach the preset status threshold, the data acquisition frequency is adjusted to re-acquire the device's operating status information, which serves as a re-verification of the optimization effect.

[0105] For example, if the temperature is still above 50 degrees Celsius, the sampling frequency is adjusted from every 5 seconds to every 2 seconds to obtain more real-time data. This flexible adjustment ensures the accuracy of the status information and supports subsequent optimization.

[0106] It should be noted that each of the above steps is closely interconnected, forming a complete technical chain from parameter adjustment to status analysis and trend judgment. The examples for each step revolve around optimizing the operation of industrial equipment, with logical progression and mutual support, ensuring the practicality and operability of the solution.

[0107] S5. If the real-time operation requirements are not met, then based on the changing trend of the equipment operation status data, a prediction algorithm is used to calculate the peak current demand and bandwidth demand in the future cycle, and generate pre-adjustment parameters.

[0108] Optionally, this step also includes: Step S51: Obtain the trend of change through the equipment operation status data, calculate the trend slope using a time series analysis algorithm, and obtain the data change characteristics.

[0109] Optionally, the overall trend of equipment status changes over time can be calculated using the following formula: ,

[0110] Where S represents the overall slope of the device status change over time, and n represents the number of data points. This represents the device state value at time i. This represents the i-th time point. This represents the average value of the state values. This represents the average value at any given time point.

[0111] Step S52: Determine the trend direction based on the data change characteristics. If the trend slope is greater than the preset slope threshold, calculate the peak demand in the future period through the prediction algorithm to obtain the peak prediction result.

[0112] Step S53: Extract the distribution characteristics of current demand and bandwidth demand from the peak prediction results, and use a linear regression algorithm to determine the proportional relationship between the demands to obtain the proportional coefficient.

[0113] Step S54: Calculate the pre-adjustment parameters using the proportional coefficient, generate the first adjustment parameter for the current requirement, and generate the second adjustment parameter for the bandwidth requirement, thus obtaining the adjustment parameter set.

[0114] Step S55: If the adjusted parameter set exceeds the preset range, obtain the abnormal mode through historical state data, determine whether dynamic correction is triggered, and obtain the corrected parameter set.

[0115] Step S56: Based on the corrected parameter set, use interpolation to calculate the continuous adjustment values ​​in future periods to obtain the final adjustment scheme.

[0116] Step S57: Update the equipment operating status data through the final adjustment scheme, generate the input data for the next cycle, and obtain the updated status dataset.

[0117] Specifically, the trend of change is obtained by acquiring the equipment's operating status data, and the trend slope is calculated by using time series analysis algorithms to obtain the data change characteristics.

[0118] For example, during equipment operation, the system collects current data every 5 minutes and continuously records data points for 10 cycles.

[0119] For example, suppose the current value slowly increases from 100mA to 120mA over a certain period. Through time series analysis, the slope is calculated to be approximately 2mA / cycle, reflecting the gradual increase in equipment load. This method can intuitively reflect the data's changing pattern over time, providing a basis for subsequent predictions. Based on the data's changing characteristics, the trend direction is determined. If the trend slope is greater than a preset slope threshold, the peak demand in future cycles is calculated using a prediction algorithm, yielding the peak demand prediction result.

[0120] Specifically, assuming the preset slope threshold is 1.5mA / cycle, the system starts prediction when the detected slope is 2mA / cycle.

[0121] For example, using a simple moving average method, the peak value for the next cycle can be predicted based on data from the past five cycles, resulting in a potential current of 130mA. This prediction helps identify potential high load conditions in advance. The distribution characteristics of current demand and bandwidth demand are extracted from the peak value prediction results, and a linear regression algorithm is used to determine the proportional relationship between the demands, yielding a proportionality coefficient.

[0122] In one possible implementation, system analysis revealed that when the current demand is 130mA, the bandwidth demand is 50kbps. Linear regression calculated a scaling factor of 2.6, meaning that for every 1mA increase in current, the bandwidth demand increases by 2.6kbps. This proportional relationship provides data support for parameter adjustment. Pre-adjustment parameters are calculated using the scaling factor; a first adjustment parameter is generated for the current demand, and a second adjustment parameter is generated for the bandwidth demand, resulting in a set of adjustment parameters.

[0123] For example, based on a predicted peak current of 130mA, the first adjustment parameter can be set as a mode switching command to reduce device power consumption; based on a bandwidth requirement of 50kbps, the second adjustment parameter can be set to adjust the communication frequency to a lower rate. This set of adjustment parameters can be optimized for different needs. If the set of adjustment parameters exceeds the preset range, abnormal modes are obtained through historical state data to determine whether dynamic correction is triggered, and a corrected set of parameters is obtained.

[0124] Preferably, if the first adjustment parameter requires a 20% reduction in power consumption, but historical data indicates that a 10% reduction is sufficient in similar scenarios, the system will adjust the parameter to 10%. This dynamic adjustment avoids over-adjustment and ensures device stability. Based on the adjusted parameter set, interpolation methods are used to calculate continuous adjustment values ​​for future periods to obtain the final adjustment scheme.

[0125] In one embodiment, assuming the corrected power consumption reduction is 10%, the system calculates the adjustment values ​​for the next three cycles as 8%, 9%, and 10% using linear interpolation. This smooth transition makes the device operate more smoothly. The device operating status data is updated using the final adjustment scheme to generate the input data for the next cycle, resulting in the updated status dataset.

[0126] Understandably, after the adjustment plan is implemented, the system re-collects data; for example, if the current drops to 115mA and the bandwidth requirement drops to 45kbps, this data serves as input for the next cycle. This closed-loop update mechanism ensures continuous optimization of the equipment's operating status.

[0127] S6. After executing the pre-adjustment parameters, obtain the device response data and energy consumption data, and determine whether there is system overload or excessive power consumption.

[0128] Optionally, this step also includes: Step S61: After executing the pre-adjustment parameters, obtain response data and energy consumption data from the device to obtain the initial dataset.

[0129] Step S62: Extract device response features and energy consumption features from the initial dataset to determine the feature set.

[0130] Step S63: Use the SVM module in the Scikit-learn library to classify the feature set and determine whether the overload state exists.

[0131] Step S64: If an overload condition exists, the power consumption characteristics are compared with the preset power consumption threshold to determine whether the power consumption exceeds the standard.

[0132] Step S65: Based on the comparison between the classification results and the power consumption threshold, obtain the abnormal distribution of the system operating status.

[0133] Step S66: Analyze the changing trends of the operating status through anomaly distribution analysis to obtain the optimization direction for adjusting parameters.

[0134] Step S67: Update the pre-adjustment parameters according to the optimization direction to obtain the new parameter configuration.

[0135] Specifically, after executing the pre-adjustment parameters, obtaining response data and energy consumption data from the device is the crucial first step.

[0136] For example, the system collects response data such as response time and processing latency from the device, as well as energy consumption data such as power consumption and heat generation. Suppose a device's response time increases from 2 seconds to 5 seconds, and its energy consumption rises from 100W to 130W. This data constitutes the initial dataset, laying the foundation for subsequent analysis. The system then extracts device response and energy consumption characteristics from this initial dataset.

[0137] Understandably, response characteristics may include latency volatility, response success rate, etc., while energy consumption characteristics cover peak power consumption, average energy consumption, etc.

[0138] For example, latency fluctuation might manifest as a change of 0.5 seconds per minute, while peak energy consumption might be recorded as 135W. Through feature extraction, the system forms a feature set containing multiple dimensions, facilitating further classification. The SVM module from the Scikit-learn library is then used to classify the feature set.

[0139] Specifically, SVM trains the model based on historical data and divides the feature set into two categories: "normal" and "overloaded".

[0140] In one embodiment, if historical data of a device indicates frequent overloads when latency exceeds 4 seconds and power consumption is above 120W, and current data is close to this range, the SVM can determine that the device is in an overload state. This data-driven approach can quickly identify potential risks. If an overload state exists, power consumption is determined to be excessive by comparing the energy consumption characteristics with a preset power consumption threshold.

[0141] Preferably, the power consumption threshold can be set to a peak power consumption of no more than 125W.

[0142] For example, if the current device's peak power consumption reaches 135W, exceeding the power consumption threshold by 10W, the system can confirm that the power consumption is excessive. This comparison method is simple and efficient, and can detect anomalies in a timely manner. The system obtains the anomaly distribution based on the comparison between the classification results and the power consumption threshold.

[0143] It should be noted that abnormal distribution may manifest as the frequency of overload occurrences or the magnitude of power consumption exceeding the standard.

[0144] In one possible implementation, the system records that the device overloaded three times in the past hour, with a cumulative power consumption exceeding the limit by 15W, forming abnormal distribution data. This provides a basis for subsequent trend analysis. When analyzing the changing trends of operating status through abnormal distribution analysis, the evolution of anomalies can be observed from a time perspective.

[0145] For example, an increase in overload frequency from once per hour to three times per hour indicates a gradual increase in equipment load. Based on this trend, the system derives optimization directions for adjusting parameters, such as lowering the power consumption limit or optimizing resource allocation. This analysis helps to proactively address potential problems. When updating pre-adjusted parameters according to the optimization direction...

[0146] In one embodiment, if a trend indicates that excessive power consumption is related to high load, the system can adjust the power consumption limit from 130W to 120W while increasing cooling resources. This new parameter configuration, through dynamic adjustment, ensures more stable and efficient device operation. The advantage of this approach is its ability to be flexibly optimized according to actual conditions, avoiding resource waste.

[0147] S7. If there is system overload or excessive power consumption, extract overload characteristic parameters and high power consumption characteristic parameters from historical operating data, and use feature analysis algorithms to adjust the operating configuration of the low power communication module.

[0148] Optionally, this step also includes: Step S71: If the system overload or power consumption exceeding the limit trigger condition is met, historical data is obtained from the pre-established database, and overload characteristics and high power consumption characteristics are extracted to form a feature set.

[0149] Step S72: For the feature set, use the K-means clustering algorithm to analyze the distribution patterns of overload features and high power consumption features to obtain the feature distribution results.

[0150] Step S73: Based on the feature distribution results, principal component analysis is used to determine the key parameters affecting the operation of the communication module, forming a set of key parameters.

[0151] Step S74: If the set of key parameters exceeds the preset parameter threshold, the gradient descent algorithm is used to update the running configuration and generate an adjusted configuration scheme.

[0152] Step S75: Using the adjusted configuration scheme, real-time operating data is obtained from the sensors of the communication module, and the support vector machine algorithm is used to determine whether the module's operating state is stable, thus obtaining the state evaluation result.

[0153] Step S76: If the status assessment results are unstable, extract new feature parameters from the real-time running data, use the K-means clustering algorithm to readjust the configuration scheme, and generate an optimized running configuration.

[0154] Step S77: Using the optimized operating configuration, update the operating status of the communication module and obtain the final module operating data.

[0155] In one possible implementation, if the system detects overload or excessive power consumption, retrieving historical data from a pre-established database is a crucial first step.

[0156] For example, the database might store device operation records from the past month, including data such as CPU utilization, memory usage, and current readings. When extracting overload and high-power consumption characteristics, focus can be placed on periods when CPU utilization exceeds 90% or intervals where current consistently exceeds 6A. These characteristics are compiled into a set, for example, recording a specific overload event with 95% CPU utilization, 80% memory usage, and 6.5A current, forming a concrete feature point. The advantage of this method is that it can quickly pinpoint the pattern of problem occurrence, providing a data foundation for subsequent analysis.

[0157] Specifically, when using the K-means clustering algorithm to analyze feature distribution, these feature points are grouped.

[0158] For example, assuming there are 100 overload records in the historical data, the algorithm may divide them into three categories: one is CPU utilization-driven overload, another is abnormally high power consumption with abnormal current values, and the third is a mixed problem with high memory usage.

[0159] In one embodiment, clustering results showed that CPU-dominated overload accounted for 60%, suggesting that the system may be frequently triggering overload due to excessive computational tasks. This distribution pattern intuitively reflects the source of the problem and helps to further focus the analysis.

[0160] It should be noted that when principal component analysis is used to determine key parameters, it selects the most influential factors from multiple features.

[0161] Preferably, the analysis may reveal that changes in CPU utilization and current value have weights of 0.6 and 0.3 respectively on the operation of the communication module, while memory utilization is only 0.1. This means that CPU and current are key parameters, forming a set of key parameters.

[0162] For example, in one analysis, when the CPU utilization reached 88% and the current was 5.8A, the system became noticeably unstable. This screening method effectively simplifies the problem's complexity and improves the focus of subsequent optimizations.

[0163] In one embodiment, if a key parameter exceeds a parameter threshold, such as a CPU utilization limit set to 85% while the actual value is 88%, the configuration is updated using a gradient descent algorithm.

[0164] For example, the system might generate a new configuration scheme by reducing the task scheduling frequency or decreasing the number of parallel threads. The advantage of this approach is that it gradually approaches the optimal solution, ensuring that the adjustment process is smooth and controllable.

[0165] Understandably, after obtaining real-time data through the new configuration scheme, the support vector machine algorithm is used to determine the running status.

[0166] For example, if the sensor shows that the CPU utilization rate drops to 80% and the current value stabilizes at 5.2A after adjustment, the algorithm determines the current state as "stable" based on historical stable samples. This not only verifies the adjustment effect in real time but also provides reliable operational feedback to the system.

[0167] For example, if the system is unstable, extracting new features from real-time data might reveal a sudden spike in memory usage to 85%, a phenomenon previously overlooked. In this case, the K-means clustering algorithm will reanalyze the feature distribution and generate optimized configurations, such as increasing memory allocation or migrating some tasks. This dynamic adjustment allows for rapid response to new problems and improves system adaptability.

[0168] In one possible implementation, after updating the communication module with the optimized configuration, the final operating data might show that the CPU utilization stabilizes at 75% and the current value drops to 5A. The advantage of this approach is that it not only solves the current problem but also provides better baseline parameters for future operation, ensuring long-term stable module operation.

[0169] S8. Update the device feature database and output mode library according to the adjusted operating configuration, and obtain the updated collaborative performance indicators and energy consumption indicators.

[0170] Optionally, this step also includes: Step S81: Process the adjusted running configuration through a preset running configuration parsing process to obtain the data set after configuration adjustment.

[0171] Step S82: Update the device feature database according to the data set after configuration adjustment, and obtain the updated device feature description set.

[0172] Step S83: Extract key features from the updated device feature description set to obtain a subset of data after feature extraction.

[0173] Step S84: Adjust the output mode library using the data subset after feature extraction to obtain the adjusted output mode parameter set.

[0174] Step S85: Execute a performance analysis algorithm on the adjusted output mode parameter set. Use the scikit-learn library in Python to perform the performance analysis and determine the range of variation of the collaborative performance indicators.

[0175] Step S86: By combining the variation range of the collaborative performance index with the energy consumption optimization rules, energy consumption optimization is achieved using the optimization toolbox in MATLAB to obtain the optimized energy consumption index values.

[0176] Step S87: If the optimized energy consumption index value exceeds the preset energy consumption index threshold, the running configuration is adjusted using the support vector machine algorithm. The support vector machine algorithm is implemented using the scikit-learn library in Python to obtain new configuration adjustment data.

[0177] Specifically, the adjusted runtime configuration is processed through a preset runtime configuration parsing process to obtain a set of data with adjusted configuration.

[0178] Understandably, this process is similar to decoding and organizing the adjusted configuration parameters.

[0179] For example, in a low-power communication module, assuming the adjusted configuration includes two parameters: operating frequency and transmission power, the parsing process will convert these parameters into a device-recognizable data format, such as a frequency value of 4GHz and a power value of 15dBm, generating a structured dataset for subsequent processing. This ensures the accuracy of the configuration adjustment and lays the foundation for the next step of analysis. The device feature database is then updated based on the adjusted configuration dataset to obtain the updated set of device feature descriptions.

[0180] Specifically, the device feature database stores historical operating status information of the device, such as CPU utilization and memory usage.

[0181] For example, when the dataset reflects a decrease in frequency, the database records this change and updates the corresponding feature description, such as "system load decreased after frequency adjustment." This update method helps keep the database consistent with the actual operating state, providing reliable data support for subsequent feature extraction. Key features are extracted from the updated set of device feature descriptions to obtain a subset of data after feature extraction.

[0182] In one possible implementation, the key features might be metrics directly related to system load and energy consumption.

[0183] For example, analysis revealed that CPU utilization dropped from 85% to 70% after frequency adjustment, and this change was extracted as a key feature.

[0184] It should be noted that the extraction process focuses on parameters that significantly impact system performance, forming a streamlined subset of data to facilitate further adjustments to the output mode. The extracted data subset is then used to adjust the output mode library, resulting in the adjusted set of output mode parameters.

[0185] Preferably, the output mode library defines multiple operating modes for the communication module, such as "high-performance mode" and "low-power mode".

[0186] In one embodiment, if a subset of data shows a decrease in load, the output mode library may switch the default mode from high performance to low power, with the adjusted parameter set including a frequency of 4 GHz and a power of 15 dBm. This adjustment better suits current operational needs. A performance analysis algorithm is then executed on the adjusted output mode parameter set, using the scikit-learn library in Python to determine the range of variation in co-performance metrics.

[0187] For example, by analyzing historical data and the current parameter set, it can be concluded that a 10% decrease in load leads to a 5ms increase in response time. The range of variation in the collaborative performance indicators reflects the impact of adjustments on the overall system performance, providing a basis for optimization. By combining the range of variation in the collaborative performance indicators with energy consumption optimization rules, energy consumption optimization is implemented using the optimization toolbox in MATLAB, obtaining the optimized energy consumption indicator values.

[0188] Specifically, assuming performance analysis shows a decrease in load but a slight increase in response time, rules can be set in the optimization toolbox, such as "prioritize energy consumption reduction," to adjust the power to 14dBm, ultimately reducing the energy consumption index from 110W to 100W. This approach finds a balance between performance and energy consumption. If the optimized energy consumption index exceeds the preset energy consumption threshold, a support vector machine (SVM) algorithm is used to adjust the runtime configuration. The SVM algorithm is implemented using the scikit-learn library in Python to obtain new configuration adjustment data.

[0189] In one embodiment, if the energy consumption threshold is set to 90W and the current value is 100W, the support vector machine will predict a better configuration based on historical data, such as a frequency of 3.8GHz and a power of 13dBm.

[0190] For example, this adjustment identifies the optimal solution for energy consumption exceeding limits by classifying historical operating states and generating new configuration data. The advantage of this method is that it improves the intelligence of configuration adjustment.

[0191] S9. If the collaborative performance index and energy consumption index do not reach the preset threshold, the combined optimization process of the dynamic adjustment algorithm and the feature analysis algorithm is repeated.

[0192] Optionally, this step also includes: Step S91: If the collaborative performance and energy consumption indicators do not reach the preset performance threshold, the adjusted parameter configuration is obtained through a dynamic adjustment algorithm.

[0193] Step S92: Extract key feature data from the adjusted parameter configuration using a Gaussian mixture model.

[0194] Step S93: Determine the trend of collaborative performance based on key feature data.

[0195] Step S94: If the trend of change does not meet the preset trend threshold, a new adjustment strategy is determined through a combination optimization process.

[0196] Step S95: Obtain the updated parameter set according to the new adjustment strategy.

[0197] Step S96: Using the updated parameter set, repeatedly execute the combination process of dynamically adjusting the algorithm and feature extraction until the collaborative performance and energy consumption indicators reach the preset performance threshold.

[0198] Step S97: Determine the final parameter configuration scheme.

[0199] Specifically, if the collaborative performance and energy consumption indicators do not reach the preset performance threshold, the dynamic adjustment algorithm can be regarded as an adaptive optimization method.

[0200] For example, if the system detects excessively long response times or unexpected energy consumption during equipment operation, it will trigger this algorithm. One possible implementation involves collecting real-time operating data from the equipment, such as current and temperature, and inputting it into the algorithm to automatically adjust parameters, such as increasing the operating frequency from 50Hz to 60Hz. This adjustment is based on trend analysis of historical data to ensure the equipment remains stable under different loads. Extracting key feature data from the adjusted parameter configuration using a Gaussian mixture model can be understood as a data mining process.

[0201] For example, assuming the device has multiple operating states, the model will divide the data into several clusters, such as "low load" and "high load".

[0202] Specifically, representative features are extracted from current values ​​and response times. For example, an increase in average current from 5A to 6A indicates that the device has entered a higher performance state. The advantage of this method is that it can quickly identify key factors affecting performance, providing a basis for subsequent judgments. This is especially useful when judging trends in collaborative performance based on key feature data.

[0203] It should be noted that this step focuses on the dynamic evolution of the data.

[0204] In one embodiment, if the feature data shows that the response time has decreased from 10 seconds to 7 seconds, while the energy consumption has only increased slightly, the trend may be positive.

[0205] Preferably, the change curve can be observed using visualization tools after several hours of continuous operation to determine whether it has stabilized. This helps to predict the adjustment effect in advance and avoid blind optimization. If the change trend does not meet the preset change trend threshold, the combination optimization process becomes the core of determining the new strategy.

[0206] For example, a new solution can be designed by taking into account the equipment's operating cycle and environmental conditions, such as shortening the single run time to 30 minutes while increasing the cooling time. This strategy can effectively balance performance and energy consumption.

[0207] In one embodiment, if the original device overheats after running continuously for 1 hour, the temperature drops by 10 degrees Celsius after segmented operation under the new strategy, while maintaining a high performance level. Obtaining the updated parameter set according to the new strategy can be understood as transforming the optimization results into an executable configuration.

[0208] Specifically, the system might generate a set of parameters, such as a power setting of 1700W and an operating interval of 25 minutes. These parameters directly reflect the intent of the aforementioned strategy, ensuring its effective implementation in actual operation. The advantage of this approach is that parameter adjustments are more closely aligned with real-world needs. The process of dynamically adjusting and extracting features is repeated using the updated parameter set until a preset performance threshold is reached—a process of iterative optimization.

[0209] For example, the first adjustment improved performance by 20%, but energy consumption exceeded the limit. After two rounds of iteration, performance stabilized near the target value, and energy consumption was reduced to a reasonable range.

[0210] Preferably, intermediate results are recorded at each iteration for easy tracking and analysis. The advantage of this iterative approach is that it gradually approaches the optimal solution, avoiding excessive adjustments at once. When determining the final parameter configuration, the focus is on the reliability and reproducibility of the solution.

[0211] In one possible implementation, the final solution might be to fix the power at 1750W and switch the operating mode to "balanced".

[0212] For example, after multiple rounds of testing, the equipment operated continuously for 8 hours under this configuration, maintaining a response time of 6 seconds and energy consumption of 7 kWh. This solution not only meets performance requirements but also extends equipment lifespan, demonstrating its practical technological value.

[0213] Understandably, the final plan will still have some leeway to cope with sudden load changes.

[0214] Please see Figure 2 A second aspect of the present invention provides an intelligent wire harness adaptive control system, which performs adaptive control using the method described above, the system comprising: The device feature matching module is used to acquire the voltage characteristics and communication signal characteristics of the connected devices, and to perform pattern matching using a pre-established device feature database to obtain the device type judgment result. The initial parameter determination module is used to extract the corresponding current range and communication protocol from the output mode library based on the device type determination result, and determine the initial output parameters. The dynamic optimization module is used to monitor the current change and data transmission rate of the device in real time, and to optimize the initial output parameters using a dynamic adjustment algorithm to generate adjusted output parameters. The status monitoring module is used to execute the adjusted output parameters through the low-power communication module, obtain device operating status data, and determine whether the real-time operation requirements are met. The prediction and adjustment module is used to calculate the peak current demand and bandwidth demand in the future period based on the changing trend of the equipment operation status data if the real-time operation demand is not met, and generate pre-adjustment parameters. The overload judgment module is used to obtain device response data and energy consumption data after executing the pre-adjustment parameters, and to determine whether there is system overload or excessive power consumption. The configuration adjustment module is used to extract overload characteristic parameters and high power consumption characteristic parameters from historical operating data if there is system overload or excessive power consumption, and to adjust the operating configuration of the low power communication module using a feature analysis algorithm. The database update module is used to update the device feature database and output mode library according to the adjusted operating configuration, and to obtain the updated collaborative performance indicators and energy consumption indicators. The performance evaluation module is used to repeatedly execute the combined optimization process of the dynamic adjustment algorithm and the feature analysis algorithm if the collaborative performance index and energy consumption index do not reach the preset performance threshold.

[0215] The present invention provides an intelligent wire harness adaptive control method and system, which can actively establish a connection with intelligent devices and exchange information through a built-in low-power Bluetooth or near-field communication module.

[0216] This invention first acquires the voltage and communication characteristics of the connected device and matches them with a pre-established database to determine the device type. Based on the determination result, the system extracts the corresponding current range and communication protocol from the output mode library to determine the initial output parameters. Subsequently, this invention monitors the device's current changes and data transmission rate in real time and uses a dynamic adjustment algorithm to optimize the output parameters. If the operating requirements are not met, the system predicts future current and bandwidth requirements and generates pre-adjustment parameters. When overload or power consumption exceeds the limit, this invention analyzes the characteristic parameters in historical data and adjusts the communication module configuration. Through continuous optimization and database updates, this invention achieves efficient collaboration and energy consumption optimization between the wiring harness and the intelligent device, improving the system's adaptability and reliability.

[0217] The above description is merely a specific implementation of this specification. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, modules, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. It should be understood that the scope of protection of this specification is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this specification, and these modifications or substitutions should all be covered within the scope of protection of this specification.

Claims

1. A smart harness adaptive control method, characterized in that, The method includes: S1. Obtain the voltage characteristics and communication signal characteristics of the connected device, and perform pattern matching using a pre-established device characteristic database to obtain the device type judgment result; S2, based on the device type determination result, extract the corresponding current range and communication protocol from the output mode library, and determine the initial output parameters; S3, monitor the current change and data transmission rate of the device in real time, and use a dynamic adjustment algorithm to optimize the initial output parameters and generate adjusted output parameters; S4, execute the adjusted output parameters through the low-power communication module, obtain device operating status data, and determine whether the real-time operating requirements are met; S5. If the real-time operation requirements are not met, then based on the changing trend of the equipment operation status data, a prediction algorithm is used to calculate the peak current demand and bandwidth demand in the future cycle, and generate pre-adjustment parameters. S6. After executing the pre-adjustment parameters, obtain the device response data and energy consumption data, and determine whether there is system overload or excessive power consumption. S7. If there is system overload or excessive power consumption, extract overload characteristic parameters and high power consumption characteristic parameters from historical operating data, and use characteristic analysis algorithm to adjust the operating configuration of the low power communication module. S8. Update the device feature database and output mode library according to the adjusted operating configuration, and obtain the updated collaborative performance indicators and energy consumption indicators. S9. If the collaborative performance index and energy consumption index do not reach the performance threshold, the combined optimization process of the dynamic adjustment algorithm and the feature analysis algorithm is repeated.

2. The method according to claim 1, characterized in that, Step S1 involves acquiring the voltage and communication signal characteristics of the connected device, performing pattern matching using a pre-established device characteristic database, and obtaining a device type determination result, including: Step S11: Obtain the voltage characteristics and communication signal characteristics of the connected device, and collect raw data through sensors to obtain a preliminary feature set; Step S12: The preliminary feature set is filtered and normalized using preprocessing methods to obtain standardized feature data; Step S13: Using a pre-established device feature database, the standardized feature data is compared to obtain a matching candidate set; Step S14: If the similarity in the candidate set exceeds the similarity threshold, the candidate set is classified using the support vector machine algorithm to determine the device type. Step S15: Perform a secondary verification based on the classification results and the device characteristics in the database to obtain type confirmation data; Step S16: Determine the equipment operating status by analyzing the correlation between type confirmation data and communication signal characteristics; Step S17: Use the decision tree algorithm to comprehensively analyze the changing trends of the operating status and voltage characteristics to obtain the final judgment result.

3. The method according to claim 1, characterized in that, Step S2 involves retrieving the corresponding current range and communication protocol from the output mode library based on the device type determination result, and determining the initial output parameters, including: Step S21: Obtain the judgment result through the device type and determine the type matching content; Step S22: Extract the output pattern from the MySQL pattern library based on the judgment result to obtain the corresponding configuration data; Step S23: Use the output mode and the NumPy library to match the current range and determine the range extraction result; Step S24: Obtain the communication protocol from the Redis cache according to the output mode to get the protocol selection content; Step S25: Determine the initial parameter configuration based on the range extraction results and protocol selection content; Step S26: After obtaining the initial parameter configuration, determine the output configuration data; Step S27: Adjust the device type matching according to the output configuration data to obtain the final output parameters.

4. The method according to claim 1, characterized in that, In step S3, the current change and data transmission rate of the device are monitored in real time, and the initial output parameters are optimized using a dynamic adjustment algorithm to generate adjusted output parameters, including: Step S31: Obtain real-time data content by collecting the current change and data transmission rate of the device through sensors; Step S32: Extract the change value and transmission rate based on the real-time data content to determine the dynamic adjustment requirements; Step S33: If the change value exceeds the change threshold, the initial parameters are processed by a dynamic adjustment algorithm to obtain the optimized parameter result. Step S34: Based on the optimized parameter results and transmission rate, obtain the adjusted communication configuration and determine the output parameter content; Step S35: Update the device's acquisition rate by outputting the parameter content to obtain the adjusted real-time data; Step S36: Analyze the changing trend based on the adjusted real-time data to determine whether the parameters need to be optimized again; Step S37: If the trend of change is stable, the final operating parameters are obtained by fixing the current output parameters.

5. The method according to claim 1, characterized in that, Step S4 involves executing the adjusted output parameters through a low-power communication module, acquiring device operating status data, and determining whether the real-time operating requirements are met, including: Step S41: Perform parameter adjustment through the low-power communication module and obtain the adjusted output parameter data; Step S42: Extract equipment operating status information from the adjusted output parameter data to obtain an equipment status description; Step S43: Analyze the device status description using a preset status threshold to determine whether it deviates from the normal operating range; Step S44: If the operation deviates from the normal operating range, the output parameters are readjusted through the communication module to obtain the updated status data. Step S45: Based on the updated status data, use the K-means algorithm to cluster the device operation mode and determine the operation trend; Step S46: Based on the operating trend, optimize the parameter adjustment strategy through the low-power communication module to obtain new status data; Step S47: If the new status data does not reach the preset status threshold, adjust the data acquisition frequency and reacquire the device operating status information.

6. The method according to claim 1, characterized in that, In step S5, if the real-time operation requirements are not met, then based on the changing trend of the equipment operation status data, a prediction algorithm is used to calculate the peak current demand and bandwidth demand in the future cycle, and pre-adjustment parameters are generated, including: Step S51: Obtain the trend of change through equipment operating status data, calculate the trend slope using time series analysis algorithm, and obtain the data change characteristics; Step S52: Determine the trend direction based on the data change characteristics. If the trend slope is greater than the slope threshold, calculate the peak demand in the future period using the prediction algorithm to obtain the peak prediction result. Step S53: Extract the distribution characteristics of current demand and bandwidth demand from the peak prediction results, and use a linear regression algorithm to determine the proportional relationship between the demands to obtain the proportional coefficient. Step S54: Calculate the pre-adjustment parameters using the proportional coefficient, generate the first adjustment parameter for the current requirement, and generate the second adjustment parameter for the bandwidth requirement to obtain the adjustment parameter set; Step S55: If the adjusted parameter set exceeds the preset range, obtain the abnormal mode through historical state data, determine whether dynamic correction is triggered, and obtain the corrected parameter set. Step S56: Based on the corrected parameter set, use interpolation to calculate the continuous adjustment values ​​in future periods to obtain the final adjustment scheme; Step S57: Update the equipment operating status data through the final adjustment scheme, generate the input data for the next cycle, and obtain the updated status dataset.

7. The method according to claim 1, characterized in that, Step S6, after executing the pre-adjustment parameters, obtains device response data and energy consumption data, and determines whether there is system overload or excessive power consumption, including: Step S61: After executing the pre-adjustment parameters, obtain response data and energy consumption data from the device to obtain the initial dataset; Step S62: Extract device response features and energy consumption features from the initial dataset to determine the feature set; Step S63: Use the SVM module in the Scikit-learn library to classify the feature set and determine whether the overload state exists; Step S64: If an overload condition exists, the power consumption threshold is compared with the energy consumption characteristics to determine whether the power consumption exceeds the standard. Step S65: Based on the comparison between the classification results and the power consumption threshold, obtain the abnormal distribution of the system operating status; Step S66: Analyze the changing trends of the operating status through anomaly distribution analysis to obtain the optimization direction for adjusting parameters; Step S67: Update the pre-adjustment parameters according to the optimization direction to obtain the new parameter configuration.

8. The method according to claim 1, characterized in that, In step S7, if system overload or excessive power consumption exists, overload characteristic parameters and high power consumption characteristic parameters are extracted from historical operating data, and the operating configuration of the low-power communication module is adjusted using a feature analysis algorithm, including: Step S71: If the system overload or power consumption exceeding the limit trigger condition is met, historical data is obtained from the pre-established database, and overload characteristics and high power consumption characteristics are extracted to form a feature set. Step S72: For the feature set, use the K-means clustering algorithm to analyze the distribution patterns of overload features and high power consumption features to obtain the feature distribution results; Step S73: Based on the feature distribution results, use principal component analysis to determine the key parameters affecting the operation of the communication module and form a set of key parameters; Step S74: If the set of key parameters exceeds the parameter threshold, the gradient descent algorithm is used to update the running configuration and generate an adjusted configuration scheme. Step S75: Using the adjusted configuration scheme, real-time operating data is obtained from the sensors of the communication module, and the support vector machine algorithm is used to determine whether the module's operating state is stable, thus obtaining the state evaluation result. Step S76: Based on the state assessment results, if the system is unstable, extract new feature parameters from the real-time running data, use the K-means clustering algorithm to readjust the configuration scheme, and generate an optimized running configuration. Step S77: Using the optimized operating configuration, update the operating status of the communication module and obtain the final module operating data.

9. The method according to claim 1, characterized in that, Step S8 involves updating the device feature database and output mode library according to the adjusted operating configuration, and obtaining updated collaborative performance indicators and energy consumption indicators, including: Step S81: Process the adjusted running configuration through a preset running configuration parsing process to obtain the data set after configuration adjustment; Step S82: Update the device feature database according to the data set after configuration adjustment, and obtain the updated device feature description set; Step S83: Extract key features from the updated device feature description set to obtain a subset of data after feature extraction; Step S84: Adjust the output mode library using the data subset after feature extraction to obtain the adjusted output mode parameter set; Step S85: Execute a performance analysis algorithm on the adjusted output mode parameter set, using the scikit-learn library in Python to perform performance analysis and determine the range of variation of the collaborative performance index. Step S86: By combining the variation range of the collaborative performance index with the energy consumption optimization rules, energy consumption optimization is achieved using the optimization toolbox in MATLAB to obtain the optimized energy consumption index values. Step S87: If the optimized energy consumption index value exceeds the energy consumption index threshold, the running configuration is adjusted using the support vector machine algorithm. The support vector machine algorithm is implemented using the scikit-learn library in Python to obtain new configuration adjustment data.

10. An intelligent wire harness adaptive control system, characterized in that, Intelligent harness adaptive control is performed using the method described in any one of claims 1 to 9, the system comprising: The device feature matching module is used to acquire the voltage characteristics and communication signal characteristics of the connected devices, and to perform pattern matching using a pre-established device feature database to obtain the device type judgment result. The initial parameter determination module is used to extract the corresponding current range and communication protocol from the output mode library based on the device type determination result, and determine the initial output parameters. The dynamic optimization module is used to monitor the current change and data transmission rate of the device in real time, and to optimize the initial output parameters using a dynamic adjustment algorithm to generate adjusted output parameters. The status monitoring module is used to execute the adjusted output parameters through the low-power communication module, obtain device operating status data, and determine whether the real-time operation requirements are met. The prediction and adjustment module is used to calculate the peak current demand and bandwidth demand in the future period based on the changing trend of the equipment operation status data if the real-time operation demand is not met, and generate pre-adjustment parameters. The overload judgment module is used to obtain device response data and energy consumption data after executing the pre-adjustment parameters, and to determine whether there is system overload or excessive power consumption. The configuration adjustment module is used to extract overload characteristic parameters and high power consumption characteristic parameters from historical operating data if there is system overload or excessive power consumption, and to adjust the operating configuration of the low power communication module using a feature analysis algorithm. The database update module is used to update the device feature database and output mode library according to the adjusted operating configuration, and to obtain the updated collaborative performance indicators and energy consumption indicators. The performance evaluation module is used to repeatedly execute the combined optimization process of the dynamic adjustment algorithm and the feature analysis algorithm if the collaborative performance index and energy consumption index do not reach the performance threshold.

Images