Self-adaptive control method and system for photoelectric sensor in extreme environment

Abstract

The invention discloses a self-adaptive control method and system for a photoelectric sensor in an extreme environment, and the method comprises the steps: calculating a signal energy sequence; generating an energy attenuation curve, and detecting an energy abrupt change point; dividing an environment response interval; calculating a fluctuation range; determining dominant environment parameters; extracting change trend characteristics, and determining a reverse compensation trend; setting a compensation parameter of the signal conditioning circuit based on the reverse compensation trend, and performing compensation control on the signal conditioning circuit by using the compensation parameter; recalculating an energy attenuation curve of the compensated signal sequence segment to obtain a compensation energy abrupt change point; when the number of the compensation energy abrupt change points is smaller than that of the energy abrupt change points, the current dominant environment parameters and the compensation parameters are written into an environment parameter priority table; and when the number of the compensation energy abrupt change points is not less than the number of the energy abrupt change points, selecting the environment parameter with the second large fluctuation range as the dominant environment parameter. According to the invention, the detection precision of the photoelectric sensor in an extreme environment is improved.

Description

Technical Field

[0001] The present application belongs to the field of sensor control, and in particular, relates to an adaptive control method and system for a photoelectric sensor in extreme environments. Background Art

[0002] As an important sensor device, photoelectric sensors are widely used in industrial automation, environmental monitoring, intelligent control and other fields. The performance of photoelectric sensors is often affected by factors such as temperature fluctuations and electromagnetic interference, resulting in unstable or distorted output signals.

[0003] In related technologies, environmental parameters (such as temperature and electromagnetic field strength) can be monitored in real time and the operating state of the sensor can be adjusted according to these parameters, such as by adjusting the gain of the amplifier or modifying the parameters of the filter to adapt to the current environment. This control strategy effectively improves the performance stability of the sensor under specific changing conditions.

[0004] However, when extreme environmental conditions change frequently or multiple extreme factors exist at the same time, the relevant technologies may find it difficult to accurately adjust all relevant parameters in real time, resulting in insufficient response speed and adjustment accuracy. Existing control systems may find it difficult to quickly adapt to rapid environmental changes at the same time, thereby reducing the detection accuracy of the sensor. Summary of the invention

[0005] The present application provides an adaptive control method and system for a photoelectric sensor in an extreme environment, which are used to improve the detection accuracy of the photoelectric sensor in an extreme environment.

[0006] In a first aspect, the present application provides an adaptive control method for a photoelectric sensor in an extreme environment, which collects an output signal and an environmental parameter value of the photoelectric sensor, and divides the output signal into a plurality of signal sequence segments in sequence according to a preset time interval; Calculate the signal average energy value of each signal sequence segment to obtain a signal energy sequence; Generate an energy decay curve according to the signal energy sequence, and detect the energy mutation point on the energy decay curve; The signal sequence segment between two adjacent energy mutation points is divided into an environmental response interval; In each environmental response interval, calculate the fluctuation range of each environmental parameter value; The environmental parameter value corresponding to the largest fluctuation range is determined as the dominant environmental parameter, and the dominant environmental parameter of each environmental response interval is obtained; Extract the change trend characteristics of the dominant environmental parameters, and determine the reverse compensation trend based on the change trend characteristics; Setting compensation parameters of the signal conditioning circuit based on the reverse compensation trend, and using the compensation parameters to perform compensation control on the signal conditioning circuit; Recalculate the energy decay curve of the compensated signal sequence segment to obtain the compensation energy mutation point; When the number of compensation energy mutation points is less than the number of energy mutation points, the current dominant environmental parameters and compensation parameters are recorded; Write the current dominant environmental parameters and compensation parameters into the environmental parameter priority table; When the number of compensation energy mutation points is not less than the number of energy mutation points, the environmental parameter with the second largest fluctuation range is selected as the dominant environmental parameter, and the step of setting the compensation parameter of the signal conditioning circuit based on the reverse compensation trend is returned.

[0007] By adopting the above technical solution, the dynamic change characteristics of signal energy can be obtained by collecting the output signal and environmental parameter values ​​of the photoelectric sensor and dividing the signal into sequence segments to calculate the energy value. According to the energy attenuation curve, the mutation point is detected and the environmental response interval is divided. The dominant environmental parameters are determined in combination with the extreme difference of environmental parameter fluctuations, which can accurately identify the key environmental factors affecting signal fluctuations. The reverse compensation trend is set based on the change trend characteristics of the dominant environmental parameters, and compensation control is implemented through the signal conditioning circuit, which can suppress the signal fluctuation caused by environmental changes. Compare the number of energy mutation points before and after compensation, evaluate the compensation effect and update the environmental parameter priority table. When the compensation effect of a certain environmental parameter is not ideal, the system will automatically switch to other candidate environmental parameters for compensation attempts. This iterative optimization method enables the system to continuously adjust the compensation strategy, thereby achieving continuous improvement of signal stability and improving the detection accuracy of photoelectric sensors in extreme environments.

[0008] In conjunction with some embodiments of the first aspect, in some embodiments, generating an energy decay curve according to a signal energy sequence, and detecting an energy mutation point on the energy decay curve specifically includes: The signal energy sequence is averaged within a preset time window to obtain a smoothed energy sequence, where the length of the preset time window is an integer multiple of the time interval between two adjacent signal sequence segments; The energy baseline representing the long-term trend of signal energy is obtained by least square fitting using the smoothed energy sequence. Calculate the difference between the smoothed energy sequence and the energy baseline to obtain the deviation sequence; Perform first-order difference operation on the deviation sequence to obtain the difference sequence; Based on the local mean of the energy baseline, a dynamic threshold proportional to the local mean is calculated; Determine the inflection point of the energy decay curve according to the position where the sign of the differential sequence changes from positive to negative or from negative to positive; When the energy deviation amplitude at the inflection point position exceeds the dynamic threshold, the inflection point corresponding to the inflection point position is determined as the energy mutation point.

[0009] By adopting the above technical solution, the signal energy sequence is processed by sliding average, which can reduce the influence of random noise and improve the smoothness of the energy sequence. The energy baseline is obtained by least squares fitting, which reflects the long-term change trend of the signal energy. Combined with the calculation of the deviation sequence, the short-term fluctuation characteristics can be highlighted. The first-order difference operation of the deviation sequence can enhance the recognition ability of the signal mutation characteristics. The dynamic threshold based on the local mean of the energy baseline is adopted, so that the judgment criteria of the mutation point can be adaptively adjusted with the change of the signal energy level. The energy mutation point is determined by the dual constraints of the difference sequence sign change and the dynamic threshold, which not only ensures the sensitivity of the mutation point detection, but also reduces the situation of misjudging normal fluctuations as mutation points, improves the accuracy of energy mutation point detection, and enhances the system's rapid response ability to environmental changes and anti-interference ability.

[0010] In conjunction with some embodiments of the first aspect, in some embodiments, extracting the change trend characteristics of the dominant environmental parameters, and determining the reverse compensation trend according to the change trend characteristics, specifically includes: Perform wavelet decomposition and reconstruction on the dominant environmental parameters to obtain characteristic waveforms; Calculate energy distribution based on characteristic waveform and extract main feature with maximum energy value; Construct a frequency domain feature matrix based on the main features, and input the frequency domain feature matrix into a preset adaptive neural network to obtain a change trend prediction of the dominant environmental parameters; Generate a compensation basis function based on the change trend prediction, and the change direction of the compensation basis function is opposite to the predicted trend; The compensation basis function is normalized to obtain the reverse compensation trend.

[0011] By adopting the above technical solution, the dominant environmental parameters are analyzed at multiple scales through wavelet decomposition and reconstruction, and the characteristic information of different frequency components can be separated. The main feature of the maximum energy value is extracted based on the energy distribution, and the most significant characteristic components in the change of environmental parameters are retained. The frequency domain feature matrix is ​​input into the adaptive neural network for trend prediction, and the nonlinear mapping ability of the neural network is utilized to improve the accuracy of trend prediction. Based on the predicted trend, the compensation basis function in the opposite direction is generated, and the reverse compensation trend is obtained by normalization. This compensation method that combines time-frequency analysis, feature extraction and intelligent prediction can accurately capture the changing laws of environmental parameters, generate compensation strategies that match them, and improve the accuracy and real-time performance of compensation control.

[0012] In combination with some embodiments of the first aspect, in some embodiments, when the number of compensation energy mutation points is not less than the number of energy mutation points, selecting the environmental parameter with the second largest fluctuation range as the dominant environmental parameter, and returning to execute the step of setting the compensation parameter of the signal conditioning circuit based on the reverse compensation trend, the method further includes: When the number of environmental parameters in the environmental parameter priority table reaches a preset threshold, the environmental parameters are grouped to obtain a number of environmental parameter groups; Establishing priority relationships between groups based on the compensation effects of each environmental parameter group; Determine the master control environment parameter group according to the priority relationship between the groups, and determine the impact of changes in the master control environment parameter group on other environment parameter groups; When the actual changes and impacts of other environmental parameter groups are different, the priority relationship between groups is updated; adjusting compensation parameters based on the updated priority relationship between the groups; The adjusted compensation parameters are used to perform compensation control on the signal conditioning circuit.

[0013] By adopting the above technical solution, the parameters in the environmental parameter priority table are grouped and processed, and the priority relationship between groups based on the compensation effect is established, realizing the hierarchical management of environmental parameters. By determining the influence relationship of the main control environmental parameter group on other environmental parameter groups, a correlation model between environmental parameters is constructed. When the actual change does not match the expected impact, the system can update the priority relationship and adjust the compensation parameters in time, which improves the adaptability of the control strategy, reduces the control complexity under the coupling of multiple environmental parameters, and improves the system's comprehensive processing ability for multiple environmental changes.

[0014] In combination with some embodiments of the first aspect, in some embodiments, the environmental parameters are grouped to obtain several environmental parameter groups, specifically including: Obtain the fluctuation period of each environmental parameter and calculate the correlation coefficient between the environmental parameters; Construct an affinity matrix based on the fluctuation period and correlation coefficient; According to the affinity matrix, the associated environmental parameters are divided into the same environmental parameter group to obtain several environmental parameter groups.

[0015] By adopting the above technical solution, by obtaining the fluctuation period of environmental parameters and calculating the correlation coefficient between parameters, an affinity matrix reflecting the correlation relationship between environmental parameters is constructed, which can accurately identify and quantify the degree of mutual influence between different environmental parameters. Based on the affinity matrix, the environmental parameters with correlation are divided into the same group, so that the environmental parameters in the same group have similar change characteristics and mutual influence mechanisms. By dividing the environmental parameters with strong correlation into the same group, the complexity of compensation control can be reduced, and the number of parameters that need to be independently modeled and controlled can be reduced. At the same time, since the parameters in the same group have similar change characteristics, a unified compensation strategy can be adopted to improve compensation efficiency.

[0016] In combination with some embodiments of the first aspect, in some embodiments, after using the adjusted compensation parameter to perform compensation control on the signal conditioning circuit, the method further includes: Obtain the output signal of the signal conditioning circuit and calculate the fluctuation amplitude of the output signal; When the fluctuation range exceeds a preset threshold, the change trend of the fluctuation range is extracted; The adjustment direction of the compensation parameter is determined based on the change trend, and the priority relationship between the groups is adjusted according to the adjustment direction to obtain the adjusted priority relationship between the groups.

[0017] By adopting the above technical solution, by real-time monitoring the fluctuation amplitude of the output signal of the signal conditioning circuit, when the fluctuation amplitude exceeds the preset threshold, the system can promptly discover the situation where the compensation control effect is poor. By extracting the change trend of the fluctuation amplitude, the system can determine whether the current compensation parameters are reasonable and how to adjust them. Based on the change trend, the adjustment direction of the compensation parameters is determined, and the priority relationship between groups is adjusted accordingly, so that the system can dynamically adapt to changes in the interaction relationship between environmental parameter groups. By establishing a mapping relationship between output signal fluctuations and inter-group priorities, the system can maintain a good compensation effect in complex and changeable extreme environments, and improve the system's ability to adapt to environmental changes.

[0018] In conjunction with some embodiments of the first aspect, in some embodiments, extracting the change trend of the fluctuation amplitude specifically includes: Set the fluctuation trend analysis window and extract the fluctuation extreme points of the fluctuation range within the analysis window; Calculate the slope between adjacent extreme points and statistically analyze the changing pattern of the slope; Determine the changing trend of the fluctuation amplitude based on the law of change.

[0019] By adopting the above technical solution and setting a suitable fluctuation trend analysis window, the system can capture the changing characteristics of the output signal fluctuation amplitude on an appropriate time scale. By extracting the fluctuation extreme points of the fluctuation amplitude within the analysis window, calculating the slope between adjacent extreme points and statistically analyzing the changing law, the changing trend of the fluctuation amplitude over time can be accurately characterized. This trend extraction method based on extreme points and slopes can effectively filter out random fluctuations and noise interference in the signal and extract the real signal change trend. By analyzing the changing law of the slope, the system can determine whether the fluctuation amplitude continues to increase, continues to decrease, or presents periodic changes, so that the system can adapt to the signal characteristics under different working conditions and improve the accuracy and adaptability of compensation control.

[0020] In a second aspect, an embodiment of the present application provides an adaptive control system of a photoelectric sensor in an extreme environment, wherein the adaptive control system of a photoelectric sensor in an extreme environment comprises: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code comprises computer instructions, and one or more processors call the computer instructions so that the system executes the method described in the first aspect and any possible implementation method of the first aspect.

[0021] In a third aspect, an embodiment of the present application provides a computer-readable storage medium, comprising instructions, which, when executed on a system, causes the system to execute the method described in the first aspect and any possible implementation of the first aspect.

[0022] In a fourth aspect, an embodiment of the present application provides a computer program product, characterized in that when the computer program product runs on a system, the system executes the method described in any possible implementation manner in the first aspect.

[0023] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. The present application provides an adaptive control method for photoelectric sensors in extreme environments. By collecting the output signal and environmental parameter values ​​of the photoelectric sensor, and dividing the signal into sequence segments to calculate the energy value, the dynamic change characteristics of the signal energy can be obtained. According to the energy attenuation curve, the mutation point is detected and the environmental response interval is divided. The dominant environmental parameters are determined in combination with the extreme difference of environmental parameter fluctuations, and the key environmental factors affecting signal fluctuations can be accurately identified. The reverse compensation trend is set based on the change trend characteristics of the dominant environmental parameters, and compensation control is implemented through the signal conditioning circuit, which can suppress the signal fluctuations caused by environmental changes. Compare the number of energy mutation points before and after compensation, evaluate the compensation effect and update the environmental parameter priority table. When the compensation effect of a certain environmental parameter is not ideal, the system will automatically switch to other candidate environmental parameters for compensation attempts. This iterative optimization method enables the system to continuously adjust the compensation strategy, thereby achieving continuous improvement in signal stability and improving the detection accuracy of photoelectric sensors in extreme environments.

[0024] 2. The present application provides an adaptive control method for photoelectric sensors in extreme environments. By grouping the parameters in the environmental parameter priority table, an inter-group priority relationship based on the compensation effect is established, and hierarchical management of environmental parameters is realized. By determining the influence of the main control environmental parameter group on other environmental parameter groups, a correlation model between environmental parameters is constructed. When the actual changes do not match the expected impact, the system can update the priority relationship and adjust the compensation parameters in a timely manner, which improves the adaptability of the control strategy, reduces the control complexity under the coupling of multiple environmental parameters, and improves the system's comprehensive processing capabilities for multiple environmental changes.

[0025] 3. The present application provides an adaptive control method for photoelectric sensors in extreme environments. By real-time monitoring of the fluctuation amplitude of the output signal of the signal conditioning circuit, when the fluctuation amplitude exceeds the preset threshold, the system can promptly detect the situation where the compensation control effect is poor. By extracting the changing trend of the fluctuation amplitude, the system can determine whether the current compensation parameters are reasonable and how to adjust them. Based on the changing trend, the adjustment direction of the compensation parameters is determined, and the priority relationship between groups is adjusted accordingly, so that the system can dynamically adapt to changes in the interaction relationship between environmental parameter groups. By establishing a mapping relationship between output signal fluctuations and inter-group priorities, the system can maintain a good compensation effect in complex and changeable extreme environments, and improve the system's ability to adapt to environmental changes. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 It is a flow chart of an adaptive control method of a photoelectric sensor in an extreme environment in an embodiment of the present application.

[0027] Figure 2 This is another flow chart of an adaptive control method of a photoelectric sensor in an extreme environment in an embodiment of the present application.

[0028] Figure 3 It is a schematic diagram of the physical device structure of an adaptive control system of a photoelectric sensor in an extreme environment provided in an embodiment of the present application. DETAILED DESCRIPTION

[0029] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to be used as limitations to the present application. As used in the specification and appended claims of the present application, the singular expressions "one", "a kind of", "said", "above", "the" and "this" are intended to also include plural expressions, unless there is a clear indication to the contrary in the context. It should also be understood that the term "and / or" used in the present application refers to any or all possible combinations comprising one or more listed items.

[0030] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features, and in the description of the embodiments of the present application, unless otherwise specified, "plurality" means two or more.

[0031] The following uses an embodiment and combines Figure 1 , an adaptive control method of a photoelectric sensor in an extreme environment in an embodiment of the present application is described: See also Figure 1 , which is a flow chart of an adaptive control method of a photoelectric sensor in an extreme environment in an embodiment of the present application.

[0032] S101, collecting the output signal and environmental parameter value of the photoelectric sensor, and dividing the output signal into a plurality of signal sequence segments in sequence according to a preset time interval; This step is to obtain the raw data required for subsequent adaptive control. The system collects the output signal of the photoelectric sensor through the sensor, and at the same time obtains the various parameter values ​​of the environment in which the sensor is located, such as temperature, humidity, pressure, etc. To facilitate subsequent processing, the system divides the continuous output signal into multiple discrete signal sequence segments according to the preset time interval.

[0033] In specific implementation, the system can be provided with a data acquisition module, which is connected to the photoelectric sensor and the environmental parameter sensor, synchronously collects the output signal and the environmental parameter value at a certain sampling frequency, and sends them to the data processing module. After receiving the continuous signal data stream, the data processing module divides the data stream according to the preset time interval (such as each sequence segment contains 1 second of data) to generate a series of signal sequence segments.

[0034] S102, calculating the signal average energy value of each signal sequence segment to obtain a signal energy sequence; This step is to extract features from each signal sequence segment, calculate its average energy value, and convert the discrete signal sequence in the time domain into an energy value sequence to facilitate subsequent anomaly detection and judgment.

[0035] Specifically, the system may use a short-time energy function to calculate each signal sequence segment to obtain an average energy value of each sequence segment.

[0036] In practical applications, the calculation method of the average energy of the signal can be improved according to the characteristics of the signal. For example, when the signal contains more high-frequency noise, the system can perform low-pass filtering on the signal before calculation to remove noise interference; when the signal has a large dynamic range, logarithmic energy can be used to replace the average energy to compress the dynamic range of the energy value and improve the detection stability. At the same time, the system can also introduce other characteristic sequences, such as zero-crossing rate sequence, autocorrelation sequence, etc., combined with the energy sequence to comprehensively reflect the changing characteristics of the signal.

[0037] S103, generating an energy decay curve according to the signal energy sequence, and detecting energy mutation points on the energy decay curve; The system generates an energy attenuation curve according to the signal energy sequence, and detects the energy mutation point on the energy attenuation curve. Specifically: the signal energy sequence is sliding averaged within a preset time window to obtain a smoothed energy sequence, and the length of the preset time window is an integer multiple of the time interval between two adjacent signal sequence segments; the smoothed energy sequence is used for least squares fitting to obtain an energy baseline that characterizes the long-term change trend of the signal energy; the difference between the smoothed energy sequence and the energy baseline is calculated to obtain a deviation sequence; the deviation sequence is subjected to a first-order difference operation to obtain a difference sequence; based on the local mean of the energy baseline, a dynamic threshold proportional to the local mean is calculated; the inflection point of the energy attenuation curve is determined according to the position where the sign of the difference sequence changes from positive to negative or from negative to positive; when the energy deviation amplitude at the inflection point position exceeds the dynamic threshold, the inflection point corresponding to the inflection point position is determined as the energy mutation point.

[0038] The system first smoothes the signal energy sequence to reduce short-term disturbances and noise interference in the sequence and obtain a smoothed energy sequence. The smoothing process can be performed using the sliding average method, that is, a time window of a fixed length (such as 10 points) is selected, and the energy average value in the window is calculated as the smoothed energy value of the center point of the window. Then, the smoothed energy sequence is fitted using the least squares method to obtain a smooth energy baseline, which reflects the long-term change trend of the signal energy. The smoothed energy sequence is subtracted from the energy baseline to obtain the energy deviation sequence, which further eliminates the slow drift of the signal energy and highlights the mutation component of the energy. The first-order difference of the deviation sequence is calculated to find the turning point of the change speed, that is, the position where the deviation value changes from positive to negative or from negative to positive, as the candidate point of the energy mutation point. Finally, the system calculates the local mean of the energy baseline, sets a dynamic threshold proportional to the mean, and determines the candidate points exceeding the threshold as true energy mutation points.

[0039] During the implementation process, parameters such as the length of the sliding window, the order of the fitted baseline, and the proportional coefficient of the dynamic threshold can be adjusted according to the signal characteristics and application requirements. For example, when there is a periodic background disturbance in the signal, a window length that matches the disturbance period can be selected to avoid the disturbance being detected as a mutation point. In order to deal with various abnormal signals in complex environments, the system can use multiple detection methods in parallel, such as wavelet analysis, CUSUM detection, etc., and then fuse the detection results to improve the reliability of mutation point detection. In addition, when environmental conditions change, the threshold of the energy mutation point may need to be recalibrated. The system can design an adaptive threshold adjustment mechanism to automatically update the threshold according to the changes in the energy baseline to maintain the stability of the detection effect.

[0040] S104, dividing the signal sequence segment between two adjacent energy mutation points into an environmental response interval; This step is to divide the signal sequence segment into several environmental response intervals according to the location of the energy mutation point. The change trend of the signal energy curve in each interval is relatively stable, representing a complete response process of the sensor to environmental factors.

[0041] In specific implementation, the system starts from the first signal sequence segment and scans the signal energy sequence segment by segment. When an energy mutation point is scanned, all sequence segments between it and the previous mutation point are merged into an environmental response interval; then, the current mutation point is used as a new starting point, and the scanning continues until the next mutation point, and the sequence segments in between are merged to form another environmental response interval. This cycle is repeated until the last sequence segment, completing the division of the entire signal. During the division process, if the time interval between a mutation point and the previous mutation point is less than a preset minimum response time (such as 1 minute), the mutation point can be ignored and merged with the previous and next sequence segments to avoid generating an overly short response interval that affects subsequent analysis.

[0042] S105. Calculate the fluctuation range of each environmental parameter value within each environmental response interval; For each environmental response interval, the system first extracts the time series data of each environmental parameter (such as temperature, humidity, pressure, etc.) collected within the interval. Then, the fluctuation range of each parameter data sequence is calculated, that is, the difference between the maximum and minimum values ​​of the parameter value in the interval. The fluctuation range reflects the amplitude of the parameter change within the response interval. The larger the range, the more drastic the fluctuation of the parameter, and the more significant the impact on the sensor output signal may be. The system arranges the fluctuation range values ​​of each parameter in order from large to small to form a range list, providing a quantitative description of the fluctuation of the environmental parameters in each response interval.

[0043] In the specific implementation, in order to eliminate the influence of different parameter dimensions, the system can normalize the parameter values ​​before calculating the range, and uniformly map them to the interval of [0, 1] to facilitate horizontal comparison of the range size. At the same time, since the sampling frequency of the parameters may be different, resulting in inconsistent lengths of parameter sequences, the system also needs to perform interpolation or downsampling processing to unify the length of each parameter sequence to the same as the signal sequence segment to ensure the consistency of the range calculation.

[0044] S106, determining the environmental parameter value corresponding to the largest fluctuation range as the dominant environmental parameter, and obtaining the dominant environmental parameter of each environmental response interval; The system first selects the environmental parameter with the largest fluctuation range from the range list generated in the previous step and determines it as the dominant environmental parameter of the current response interval. The selection of the dominant parameter is based on the assumption that within a response interval, the environmental parameter with the most violent fluctuation has the most significant impact on the signal output and is the main cause of the output abnormality. Therefore, it should be given priority in the subsequent signal compensation. By selecting the dominant parameter for each response interval, the system can obtain a dominant environmental parameter sequence, which reflects the dynamic changes of environmental interference factors in the entire signal acquisition process and provides environmental background information for adaptive compensation control.

[0045] It should be noted that there may be certain uncertainties and limitations in the selection of dominant environmental parameters. In some cases, the abnormality of signal output may be the result of the combined effect of multiple environmental parameters, and a single dominant parameter is difficult to fully explain the cause of the abnormality. In order to improve the rationality of decision-making, the system can optimize the dominant parameter selection rules. For example, when selecting the dominant parameter, the fluctuation range and the sensitivity of the parameter are comprehensively considered, and the parameter with a large range and high sensitivity is used as the dominant parameter; when the range is close, the parameter with a higher correlation with the signal is selected as the dominant parameter. In addition, when the dominant parameter is difficult to explain a certain abnormal phenomenon, the system can also start the multi-parameter collaborative analysis mechanism, jointly considering the changing trends of multiple parameters, in order to find the compound cause of the abnormality and guide more comprehensive and accurate compensation control.

[0046] S107, extracting the change trend characteristics of the dominant environmental parameters, and determining the reverse compensation trend according to the change trend characteristics; The system extracts the change trend characteristics of the dominant environmental parameters, and determines the reverse compensation trend based on the change trend characteristics. Specifically: the dominant environmental parameters are decomposed and reconstructed by wavelet to obtain a characteristic waveform; the energy distribution is calculated based on the characteristic waveform, and the main feature with the maximum energy value is extracted; the frequency domain feature matrix is ​​constructed according to the main feature, and the frequency domain feature matrix is ​​input into a preset adaptive neural network to obtain a change trend prediction of the dominant environmental parameters; a compensation basis function is generated based on the change trend prediction, and the change direction of the compensation basis function is opposite to the predicted trend; the compensation basis function is normalized to obtain a reverse compensation trend.

[0047] S108, setting compensation parameters of the signal conditioning circuit based on the reverse compensation trend, and using the compensation parameters to perform compensation control on the signal conditioning circuit; The system first preprocesses the time series data of the dominant environmental parameters, and uses the wavelet decomposition method to perform multi-scale decomposition, filter out high-frequency noise, and extract the low-frequency change trend information of the parameters. Then, the decomposed wavelet coefficients are reconstructed to obtain the change trend curve of the dominant parameters. By performing energy analysis on the reconstructed curve, the system can find the main characteristic component with the largest energy as the key information to characterize the parameter change trend. The wavelet coefficients of the main characteristic components are arranged by frequency band to form a frequency domain characteristic matrix as a compact representation of the parameter change trend.

[0048] Next, the system inputs the frequency domain feature matrix into a pre-trained adaptive neural network model to predict the future trend of the dominant parameters. The neural network model can learn the nonlinear mapping relationship between environmental parameters and signal output through historical data training, and predict the abnormal fluctuations that may occur in the signal based on the trend of parameter changes. The output of the model is a set of estimated values ​​of parameter changes at future moments, reflecting the general trend of parameter changes. Based on the prediction results, the system generates an opposite compensation basis function, that is, when the estimated value of the parameter change is large, a larger compensation amplitude is set, and when the estimated value is small, the compensation amplitude is reduced, so that the compensation effect and environmental interference are offset. Finally, the system adjusts the dynamic range and normalizes the compensation basis function to generate the final reverse compensation trend curve, which provides guidance for the next step of signal conditioning circuit parameter setting.

[0049] S109, recalculating the energy attenuation curve of the compensated signal sequence segment to obtain a compensation energy mutation point; The system first divides the compensated sensor output signal into new signal sequence segments according to the original time interval. Then, it recalculates the average energy value for each sequence segment and updates the signal energy sequence. The system uses the same method as in step S103 to smooth the updated energy sequence and fit the energy baseline, generating a new energy decay curve and detecting the positions of the mutation points on it to obtain the compensated energy mutation point sequence. By comparing the number and position distribution of the energy mutation points before and after compensation, the system can intuitively evaluate the effect of the compensation control. If the number of mutation points after compensation is significantly reduced and the mutation amplitude decreases, it indicates that the compensation control effectively suppresses environmental interference and smooths the energy fluctuation of the signal; on the contrary, if the number of mutation points does not change significantly or even new mutation points appear, it indicates that the current compensation strategy may have defects and needs further optimization and improvement.

[0050] In practical applications, due to the complexity and uncertainty of environmental interference, a single compensation control often fails to completely eliminate the abnormal fluctuations of the signal. To achieve long-term stable signal conditioning, the system needs to establish a closed-loop compensation optimization mechanism. According to the results of the compensation effect evaluation, the system can adaptively adjust the compensation control strategy and parameters, such as adjusting the generation algorithm of the reverse compensation trend, optimizing the mapping relationship of the compensation parameters, etc., to continuously improve the compensation accuracy and adaptability. At the same time, the system can also introduce quantitative evaluation indicators of the compensation effect, such as the average amplitude of the energy mutation points, the standard deviation of the mutation point intervals, etc., to guide the compensation optimization process and achieve intelligent parameter adjustment and strategy selection.

[0051] S110. When the number of compensated energy mutation points is less than the number of energy mutation points, record the current dominant environmental parameters and compensation parameters. If the number of energy mutation points after compensation is less than that before compensation, it indicates that the currently selected dominant environmental parameters and compensation parameter settings are effective and can better suppress environmental interference and reduce signal abnormal fluctuations. At this time, the system records the type of the dominant environmental parameters in the current response interval and the compensation parameter values of the signal conditioning circuit (such as gain coefficient, filter parameters, etc.), and saves them together with the start and end times, duration, etc. information corresponding to this response interval into the compensation decision log. These historical decision records can serve as an important reference for optimizing the compensation strategy and provide a reference control scheme for subsequent encounters with similar environmental interference.

[0052] In the specific implementation, the system can organize the compensation decision log into a structured data table, where each record contains fields such as the start and end time of the response interval, the dominant environmental parameter type, the compensation parameter value, and the compensation effect evaluation result. Different data structures and storage formats can be designed for different types of environmental parameters and compensation parameters to facilitate subsequent query and analysis. At the same time, in order to facilitate the management and sharing of decision-making knowledge, the system can also classify and index the compensation decision log according to certain rules, such as classifying by dominant environmental parameter type, sorting by compensation effect evaluation results, etc., to improve the accessibility and usability of the decision knowledge base.

[0053] S111, writing the current dominant environmental parameters and compensation parameters into the environmental parameter priority table; The system first counts the frequency of various environmental parameters being selected as dominant parameters in the compensation decision log. The higher the frequency, the more significant the impact of the parameter on the signal fluctuation and the higher its importance in compensation control. Then, the system comprehensively considers factors such as the frequency of parameters being selected as dominant parameters, compensation effect evaluation results, and the success rate of historical compensation decisions, calculates the priority weights of various environmental parameters, sorts the parameters according to the weight size, and forms an environmental parameter priority table. When encountering complex environmental interference, parameters with high priority will be selected as dominant parameters to guide the generation of compensation control strategies.

[0054] In specific implementation, the system can use a variety of weight calculation models, such as weighted average model, information entropy model, etc., to generate comprehensive priorities of environmental parameters according to different application scenarios and evaluation criteria. For different types of sensors and environmental conditions, the generation strategy of the priority table can be appropriately adjusted to introduce expert knowledge and empirical rules in specific fields to improve the pertinence and effectiveness of priority evaluation. At the same time, since the importance of environmental parameters may change over time, the system also needs to regularly update the priority table to promptly reflect the dynamic changes in the influence of parameters.

[0055] It is worth noting that in actual applications, there may be some important environmental parameters that are not fully recorded in the compensation decision log, resulting in a low ranking in the priority table. To avoid missing key parameters, the system can introduce a priori importance assessment mechanism for parameters during the priority table generation process. Through the analysis of the physical mechanism between environmental parameters and signal anomalies, expert experience judgment, etc., some important parameters are determined in advance, and a higher initial weight is given in the weight calculation to ensure their reasonable ranking in the priority table. In addition, the system can also discover environmental parameters that are not focused on in the compensation decision log but have a significant actual impact through sensitivity analysis, causal relationship mining and other methods, and dynamically adjust their priorities to improve the comprehensiveness and accuracy of the priority table.

[0056] S112. When the number of compensation energy mutation points is not less than the number of energy mutation points, select the environmental parameter with the second largest fluctuation range as the dominant environmental parameter.

[0057] When the number of compensation energy mutation points is not less than the number of energy mutation points, the system selects the environmental parameter with the second largest fluctuation range as the dominant environmental parameter and returns to execute step S108.

[0058] If the number of energy mutation points does not decrease significantly after compensation control, or even new mutation points appear, it means that the currently selected dominant environmental parameters may not be the real cause of the abnormal signal fluctuation, or may be only part of multiple causes. At this time, continuing to use the current compensation strategy may not effectively improve the signal quality, and other dominant parameters need to be tried. The system will go back to step S105, recalculate the fluctuation range of each environmental parameter within the response interval, and select the parameter with the second largest range as the new dominant environmental parameter, return to step S108, generate a reverse compensation trend based on the new parameter, and adjust the compensation parameters of the signal conditioning circuit accordingly, and evaluate the compensation effect again. Iterate in this way until the best dominant parameter combination is found to minimize the number of energy mutation points after compensation.

[0059] In practical applications, due to the complexity and diversity of environmental interference, the compensation control of a single parameter is often difficult to completely eliminate signal anomalies. In order to improve the compensation accuracy and robustness, the system can try a multi-parameter collaborative compensation strategy based on the optimal dominant parameter. After selecting the second largest fluctuation range parameter as the dominant parameter, the system can combine it with the original dominant parameter to form a multi-dimensional compensation control vector to jointly guide the parameter adjustment of the signal conditioning circuit. In the collaborative compensation process, the system needs to reasonably allocate the compensation weights of different parameters, not only to give play to the compensation role of the new parameters, but also to take into account the influence of the original parameters to avoid the mutual cancellation of compensation effects. The weight allocation can be dynamically generated by weighted averaging, product aggregation and other methods based on factors such as the fluctuation range of the parameter and the prior importance score, and adjusted in time according to the compensation effect evaluation results.

[0060] In the above embodiment, by collecting the output signal and environmental parameter value of the photoelectric sensor, and dividing the signal into sequence segments to calculate the energy value, the dynamic change characteristics of the signal energy can be obtained. According to the energy attenuation curve, the mutation point is detected and the environmental response interval is divided. The dominant environmental parameter is determined in combination with the extreme difference of environmental parameter fluctuations, and the key environmental factors affecting the signal fluctuation can be accurately identified. The reverse compensation trend is set based on the change trend characteristics of the dominant environmental parameter, and the compensation control is implemented through the signal conditioning circuit, which can suppress the signal fluctuation caused by environmental changes. Compare the number of energy mutation points before and after compensation, evaluate the compensation effect and update the environmental parameter priority table. When the compensation effect of a certain environmental parameter is not ideal, the system will automatically switch to other candidate environmental parameters for compensation attempts. This iterative optimization method enables the system to continuously adjust the compensation strategy, thereby achieving continuous improvement of signal stability and improving the detection accuracy of the photoelectric sensor in extreme environments.

[0061] Through the above embodiments, the system can realize accurate identification and compensation control of a single environmental parameter. However, in practical applications, extreme environments often manifest as complex coupling effects of multiple environmental parameters. In order to better cope with such complex situations, it is necessary to group and manage environmental parameters and establish a more systematic compensation control mechanism. Figure 2 , another adaptive control method of a photoelectric sensor in an extreme environment in an embodiment of the present application is described: See also Figure 2 , is another flow chart of an adaptive control method of a photoelectric sensor in an extreme environment in an embodiment of the present application.

[0062] S201, when the number of environmental parameters in the environmental parameter priority table reaches a preset threshold, grouping the environmental parameters to obtain a plurality of environmental parameter groups; When the number of environmental parameters in the environmental parameter priority table reaches a preset threshold, the system groups the environmental parameters to obtain several environmental parameter groups. Specifically: the fluctuation period of each environmental parameter is obtained, and the correlation coefficient between the environmental parameters is calculated; an affinity matrix is ​​constructed based on the fluctuation period and the correlation coefficient; and environmental parameters with correlation are divided into the same environmental parameter group according to the affinity matrix to obtain several environmental parameter groups.

[0063] When the number of parameters in the environmental parameter priority table accumulates to a certain extent and reaches the preset threshold, the system will automatically trigger parameter grouping processing. The purpose of grouping is to classify parameters with similar characteristics or strong correlations into one category to form several environmental parameter groups. The parameters within each group have a significant impact on each other, while the impact of parameters between groups is relatively weak. The specific grouping method is that the system first obtains the historical fluctuation data of each environmental parameter, and calculates the dominant fluctuation cycle of each parameter through time series analysis; then, the Pearson correlation coefficient between any two parameters is calculated to obtain the correlation matrix of the parameters; finally, considering the similarity of the fluctuation cycle and the size of the correlation coefficient, the affinity matrix of the parameters is constructed, and cluster analysis is performed based on the matrix to automatically classify parameters with high affinity into the same group to form several environmental parameter groups.

[0064] In practical applications, the system can flexibly set the threshold of the number of parameters that trigger grouping, ensuring that sufficient samples are accumulated to support reliable correlation analysis, while avoiding too many parameters that lead to overly complex grouping and excessive calculations. The selection of thresholds can be dynamically adjusted based on factors such as sensor type, application scenario, and computing resources. At the same time, for the calculation of fluctuation period and correlation coefficient, the system can use a variety of time series analysis and correlation measurement algorithms, such as wavelet transform, mutual information, etc., to characterize the correlation characteristics between parameters from different angles. In the cluster analysis of affinity matrix, the system can select a variety of algorithms such as hierarchical clustering and spectral clustering, and dynamically optimize clustering parameters through clustering evaluation indicators to obtain high-quality parameter grouping results.

[0065] S202, establishing a priority relationship between groups based on the compensation effect of each environmental parameter group; For each environmental parameter group, the system selects the parameter with the highest priority in the group as the representative parameter, uses this parameter to perform single-group compensation control, and evaluates the number and amplitude of signal energy mutation points after compensation. By comparing the compensation effects of different parameter groups, the key parameter group with the greatest impact on signal fluctuations can be found. The system sorts the compensation effects of each group, establishes the priority relationship of the parameter groups, and forms an inter-group priority table. Parameter groups with high priority have more significant compensation effects under complex environmental interference and should be given priority; while the effects of parameter groups with low priority are relatively minor and can be used as supplementary means.

[0066] In the specific implementation, the system can design a variety of evaluation indicators for compensation effects to quantitatively characterize the compensation performance of each parameter group. In addition to the number and amplitude of energy mutation points, indicators such as the peak factor and spectral entropy of the signal can also be introduced to judge the quality of compensation control from multiple angles. For specific application scenarios, a weighted scoring mechanism for compensation effects can also be customized to comprehensively consider various indicators and obtain a comprehensive priority ranking of parameter groups. At the same time, since the importance of the impact of environmental parameters may change over time, the system needs to regularly update the evaluation results of the compensation effect, dynamically adjust the priority relationship between groups, and adapt to environmental changes in a timely manner.

[0067] S203, determining a master control environment parameter group according to the priority relationship between the groups, and determining the impact of changes in the master control environment parameter group on other environment parameter groups; The system first selects the parameter group at the top level with the highest priority as the main control environment parameter group from the directed priority graph between groups. The main control group usually has the most significant impact on signal compensation, and its change trend and compensation effect have a certain guiding and constraining effect on the downstream parameter group. After determining the main control group, the system analyzes the change characteristics of the key parameters in the main control group, and constructs an impact model of the main control parameters and other parameter groups through big data mining, causal reasoning and other technologies. The model can take the form of qualitative association rules, quantitative regression equations, etc. to characterize the response mode and amplitude of other parameters caused by changes in the main control parameters. Based on the impact model, the system can estimate the ideal response trajectory of other parameter groups under a given change trend of the main control group, and use it as a target reference in collaborative compensation.

[0068] In the specific implementation, the analysis of the impact of the main control parameters on other parameters can be based on the mining of historical data or obtained through specially designed experiments. Data-driven impact analysis focuses more on discovering implicit correlation patterns, while experiment-driven impact analysis emphasizes the exploration of physical mechanisms. The system can make comprehensive use of the two analysis paradigms to complement their respective advantages and disadvantages. When data is sufficient, data mining methods are preferred to extract impact models; when data is scarce or the mechanism is complex, causal experiments are focused on revealing deep-level mechanisms of action. At the same time, in order to ensure the interpretability and reliability of the analysis results, the system should also introduce causal discovery and counterfactual analysis methods to screen and verify truly causal impact relationships and improve the generalization ability of the model.

[0069] S204, when the actual changes and impacts of other environmental parameter groups are different, updating the priority relationship between the groups; After the start of collaborative compensation control, the system continuously monitors the real-time changes of each environmental parameter group. Through the data reported by the sensors in each parameter group, the system can learn the current status and change trend of each group. At the same time, based on the changes in the master control parameters, the system uses the influence model to calculate the theoretical change values ​​of other parameter groups. By comparing the actual changes of each parameter group with the theoretical changes, the system can evaluate the effectiveness of the influence of the master control group. If there is a significant difference between the two, especially when the actual change is much smaller than the theoretical change, it means that the influence of the master control group on other parameters has weakened, and the current collaborative compensation strategy may deviate from the optimal state and needs to be adjusted in time. At this time, the system will start the update mechanism of the priority relationship between groups. Through influence anomaly detection, weak master-slave relationships are identified, and the priority score of the master control group is reduced accordingly. At the same time, the system re-evaluates the compensation effect of each parameter group in the current state, improves the priority of the group with excellent performance, and generates a dynamically updated directed priority graph between groups to provide a basis for subsequent collaborative decision-making.

[0070] In specific implementation, the detection of abnormal influence of the master control can adopt a multi-indicator comprehensive analysis strategy. In addition to the deviation between the actual change and the theoretical value, the synchronization and stability between parameter groups can also be evaluated to comprehensively characterize the effectiveness of the influence of the master control group. In terms of quantitative criteria for influence anomalies, the system can set dynamic thresholds. When the deviation or other evaluation indicators exceed the threshold, the priority update is triggered. The threshold can be set based on historical experience, or adaptive calculation can be used, such as generating a confidence interval as a basis for judgment based on the statistical significance of parameter changes. In terms of the strategy selection for priority updates, the system can preset multiple sets of plans, and take adjustments of different intensities according to the severity of the influence anomaly to achieve gradient and contextualization of priority corrections.

[0071] S205 . Adjust compensation parameters based on the updated priority relationship between groups, and use the adjusted compensation parameters to perform compensation control on the signal conditioning circuit.

[0072] The system adjusts the compensation parameters based on the updated priority relationship between the groups, and uses the adjusted compensation parameters to perform compensation control on the signal conditioning circuit. After that, the system obtains the output signal of the signal conditioning circuit and calculates the fluctuation amplitude of the output signal. When the fluctuation amplitude exceeds the preset threshold, the fluctuation amplitude change trend is extracted. Specifically, a fluctuation trend analysis window is set, and the fluctuation extreme value points of the fluctuation amplitude are extracted within the analysis window. Calculate the slope between adjacent extreme points and statistically analyze the changing pattern of the slope; Determine the changing trend of the fluctuation range according to the changing rules; The adjustment direction of the compensation parameter is determined based on the change trend, and the priority relationship between the groups is adjusted according to the adjustment direction to obtain the adjusted priority relationship between the groups.

[0073] After obtaining the updated priority relationship of the environmental parameter groups, the system needs to adjust the parameter settings of the compensation control accordingly. Specifically, the system determines the parameter group with the highest priority as the main control group, extracts the compensation coefficients of each parameter in the group, and forms a multi-dimensional compensation control vector. Then, according to the influence relationship between the main control group and other parameter groups, the system makes an associated adjustment to the compensation coefficients of other parameters, so that the compensation effects of each group of parameters are coordinated with each other to avoid over-compensation or under-compensation. The adjusted compensation coefficient is input into the compensation module of the signal conditioning circuit, and the sensor output signal is compensated in real time to dynamically offset the influence of environmental interference.

[0074] In the implementation process, the compensation coefficient can be adjusted by a variety of strategies. A simple method is to weight the average of the compensation coefficients of the main control group according to the priority to obtain a comprehensive compensation coefficient, and then multiply it by a proportional factor to act on other parameter groups to achieve synchronous adjustment of the compensation intensity. The proportional factor can be estimated based on the influence coefficient between the main control group and other groups. Another more sophisticated strategy is to establish an independent compensation control model for different parameter groups, introduce the main control group parameters as influencing factors in the model, and dynamically update the compensation coefficients of each group through online learning to achieve more accurate and adaptive compensation control. Regardless of the strategy adopted, the system needs to continuously monitor the quality of the compensated signal, optimize the compensation coefficient through the feedback mechanism, and ensure the stability of the signal output.

[0075] In the above embodiment, by grouping the parameters in the environmental parameter priority table, a priority relationship between groups based on the compensation effect is established, and hierarchical management of environmental parameters is achieved. By determining the influence relationship of the main control environmental parameter group on other environmental parameter groups, a correlation model between environmental parameters is constructed. When the actual change does not match the expected impact, the system can update the priority relationship and adjust the compensation parameters in time, thereby improving the adaptability of the control strategy, reducing the control complexity under the coupling of multiple environmental parameters, and improving the system's comprehensive processing ability for multiple environmental changes.

[0076] The following describes the system in the embodiment of the present invention from the perspective of hardware processing. Figure 3 , which is a schematic diagram of the physical device structure of an adaptive control system of a photoelectric sensor in an extreme environment provided in an embodiment of the present application.

[0077] It should be noted that Figure 3 The structure of the system shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0078] like Figure 3As shown, the system includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 302 or the program loaded from the storage part 308 to the random access memory (RAM) 303, such as executing the method in the above embodiment. In RAM 303, various programs and data required for system operation are also stored. CPU 301, ROM 302 and RAM 303 are connected to each other through a bus 304. Input / output (I / O) interface 305 is also connected to bus 304.

[0079] The following components are connected to the I / O interface 305: an input section 306 including a camera, an infrared sensor, etc.; an output section 307 including a liquid crystal display (LCD) and a speaker, etc.; a storage section 308 including a hard disk, etc.; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I / O interface 305 as needed. A removable medium 311, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 310 as needed so that a computer program read therefrom is installed into the storage section 308 as needed.

[0080] In particular, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication part 309, and / or installed from a removable medium 311. When the computer program is executed by the central processing unit (CPU) 301, various functions defined in the present invention are performed.

[0081] It should be noted that the computer-readable medium shown in the embodiment of the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable computer program. Such a propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing.

[0082] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. Among them, each box in the flowchart or block diagram can represent a module, a program segment, or a part of the code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0083] As another aspect, the present invention further provides a computer-readable storage medium, which may be included in the system described in the above embodiment; or may exist independently without being assembled into the system. The above storage medium carries one or more computer programs, and when the above one or more computer programs are executed by a processor of a system, the system implements the method provided in the above embodiment.

[0084] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

[0085] As used in the above embodiments, the term "when..." may be interpreted to mean "if..." or "after..." or "in response to determining..." or "in response to detecting...", depending on the context. Similarly, the phrases "upon determining..." or "if (the stated condition or event) is detected" may be interpreted to mean "if determining..." or "in response to determining..." or "upon detecting (the stated condition or event)" or "in response to detecting (the stated condition or event)", depending on the context.

[0086] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state hard disk), etc.

[0087] Those skilled in the art can understand that to implement all or part of the processes in the above-mentioned embodiments, the processes can be completed by computer programs to instruct related hardware, and the programs can be stored in computer-readable storage media. When the programs are executed, they can include the processes of the above-mentioned method embodiments. The aforementioned storage media include: ROM or random access memory RAM, magnetic disk or optical disk and other media that can store program codes.

Claims

1. An adaptive control method for a photoelectric sensor in an extreme environment, characterized in that: include: Collecting the output signal of the photoelectric sensor and the environmental parameter value, and dividing the output signal into a plurality of signal sequence segments in sequence according to a preset time interval; Calculating the signal average energy value of each signal sequence segment to obtain a signal energy sequence; generating an energy decay curve according to the signal energy sequence, and detecting energy mutation points on the energy decay curve; Dividing the signal sequence segment between two adjacent energy mutation points into an environmental response interval; In each of the environmental response intervals, calculating the fluctuation range of each of the environmental parameter values; Determine the environmental parameter value corresponding to the largest fluctuation range as the dominant environmental parameter, and obtain the dominant environmental parameter of each environmental response interval; Extracting the change trend characteristics of the dominant environmental parameters, and determining the reverse compensation trend according to the change trend characteristics; Setting compensation parameters of a signal conditioning circuit based on the reverse compensation trend, and using the compensation parameters to perform compensation control on the signal conditioning circuit; Recalculate the energy decay curve of the compensated signal sequence segment to obtain the compensation energy mutation point; When the number of the compensation energy mutation points is less than the number of the energy mutation points, recording the current dominant environmental parameters and compensation parameters; Writing the current dominant environmental parameters and compensation parameters into an environmental parameter priority table; When the number of the compensation energy mutation points is not less than the number of the energy mutation points, the environmental parameter with the second largest fluctuation range is selected as the dominant environmental parameter, and the step of setting the compensation parameters of the signal conditioning circuit based on the reverse compensation trend is returned to execute.

2. The method according to claim 1, characterized in that Generating an energy decay curve according to the signal energy sequence and detecting an energy mutation point on the energy decay curve specifically includes: Perform sliding averaging on the signal energy sequence within a preset time window to obtain a smoothed energy sequence, wherein the length of the preset time window is an integer multiple of the time interval between two adjacent signal sequence segments; The smoothed energy sequence is used to perform least square fitting to obtain an energy baseline that represents the long-term variation trend of signal energy; Calculating the difference between the smoothed energy sequence and the energy baseline to obtain a deviation sequence; Performing a first-order difference operation on the deviation sequence to obtain a difference sequence; Based on the local mean of the energy baseline, calculating a dynamic threshold proportional to the local mean; Determine the inflection point position of the energy decay curve according to the position where the sign of the differential sequence changes from positive to negative or from negative to positive; When the energy deviation amplitude at the inflection point position exceeds the dynamic threshold, the inflection point corresponding to the inflection point position is determined as an energy mutation point.

3. The method according to claim 1, characterized in that The extracting the change trend characteristics of the dominant environmental parameters and determining the reverse compensation trend according to the change trend characteristics specifically includes: Performing wavelet decomposition and reconstruction on the dominant environmental parameters to obtain a characteristic waveform; Calculate energy distribution based on the characteristic waveform and extract the main feature with the maximum energy value; Constructing a frequency domain feature matrix according to the main features, and inputting the frequency domain feature matrix into a preset adaptive neural network to obtain a change trend prediction of the dominant environmental parameters; Generate a compensation basis function based on the change trend prediction, wherein the change direction of the compensation basis function is opposite to the predicted trend; The compensation basis function is normalized to obtain a reverse compensation trend.

4. The method according to claim 1, characterized in that: When the number of the compensation energy mutation points is not less than the number of the energy mutation points, the environmental parameter with the second largest fluctuation range is selected as the dominant environmental parameter, and after returning to execute the step of setting the compensation parameter of the signal conditioning circuit based on the reverse compensation trend, the method further includes: When the number of environmental parameters in the environmental parameter priority table reaches a preset threshold, the environmental parameters are grouped to obtain a plurality of environmental parameter groups; Establishing a priority relationship between groups based on the compensation effect of each of the environmental parameter groups; Determine a master control environment parameter group according to the priority relationship between the groups, and determine the impact of changes in the master control environment parameter group on other environment parameter groups; When the actual change of the other environmental parameter groups is different from the impact, updating the priority relationship between the groups; adjusting compensation parameters based on the updated priority relationship between the groups; The signal conditioning circuit is compensated and controlled using the adjusted compensation parameters.

5. The method according to claim 4, characterized in that The environmental parameters are grouped to obtain a plurality of environmental parameter groups, specifically including: Obtaining the fluctuation period of each of the environmental parameters, and calculating the correlation coefficient between the environmental parameters; Constructing an affinity matrix based on the fluctuation period and the correlation coefficient; According to the affinity matrix, the associated environmental parameters are divided into the same environmental parameter group to obtain a plurality of environmental parameter groups.

6. The method according to claim 4, characterized in that After the signal conditioning circuit is compensated and controlled by using the adjusted compensation parameters, the method further includes: Obtaining an output signal of the signal conditioning circuit, and calculating a fluctuation amplitude of the output signal; When the fluctuation amplitude exceeds the preset threshold, extracting the change trend of the fluctuation amplitude; An adjustment direction of the compensation parameter is determined based on the change trend, and the priority relationship between the groups is adjusted according to the adjustment direction to obtain an adjusted priority relationship between the groups.

7. The method according to claim 6, characterized in that The extracting the variation trend of the fluctuation amplitude specifically includes: Setting a fluctuation trend analysis window, and extracting fluctuation extreme value points of the fluctuation amplitude within the analysis window; Calculating the slope between adjacent extreme value points and statistically analyzing the variation pattern of the slope; The changing trend of the fluctuation amplitude is determined according to the changing rule.

8. An adaptive control system for a photoelectric sensor in an extreme environment, characterized in that: The system comprises: One or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to cause the system to execute the method as described in any one of claims 1-7.

9. A computer-readable storage medium comprising instructions, characterized in that: When the instructions are executed on a system, the system is caused to execute the method according to any one of claims 1 to 7.

10. A computer program product, characterized in that When the computer program product is run on a system, the system is caused to execute the method according to any one of claims 1 to 7.

Images