Water gate control system based on multi-source information fusion

Abstract

The application relates to the technical field of water conservancy gate control, and discloses a water conservancy gate control system based on multi-source information fusion, which comprises the following steps: firstly, reciprocating movement of opening and closing of a gate is completed through driving, and a power sequence obtained is subjected to checking based on physical symmetry to establish a benchmark verified by internal quality; then, in actual operation, real-time power vibration is compared with the benchmark to diagnose the real-time operation state of the gate; the benchmark self-checking mechanism is introduced, the vulnerable mode of traditional control systems depending on the credibility assumption of initial data is avoided, control logic is evolved from passive result confirmation to active process audit, the system can diagnose the health degree of the operation process, the purity of the diagnosis benchmark is ensured, potential operation risks can be instantly warned, and the long-term operation reliability of hydraulic facilities is improved.

Description

TECHNICAL FIELD

[0001] The application relates to a water conservancy gate control system based on multi-source information fusion, and belongs to the technical field of water conservancy gate control. BACKGROUND

[0002] At present, in the application of water conservancy projects, reliable operation of large gates is the basis for realizing flood control scheduling and water resource management. At present, the technical scheme commonly used in this field is to use a gate position sensor as feedback to form a closed-loop control system, and a servo motor or other actuator is used to drive the gate to realize accurate movement between the preset opening or closing position. At the same time, in order to protect the driving motor, the system is usually also configured with a conventional overload protection function based on operation current monitoring. This technical combination has become a general technical basis for realizing automatic operation of the gate because of its direct composition and clear control target. However, the on-site operation conditions of water conservancy projects introduce a special physical constraint to the above general technical scheme, that is, the total load borne by the driving system is composed of the normal and dynamically changing hydraulic load and the occasional abnormal physical obstruction such as silt accumulation and floating object jamming. An inherent limitation of the existing control scheme is that the only basis for judging whether the operation is completed is the geometric position of the gate. However, there is a lack of effective identification and analysis capability for the power cost paid by the driving system to achieve this position. The value of the driving power under the normal range of high water level in the flood season may be several times that of the power when serious mechanical jamming occurs at low water level in the dry season. This makes it difficult for the overload protection function based on fixed or simple variable threshold to effectively operate in actual application. If the threshold is set too high, the equipment damage jamming at low water level may be missed. If the threshold is set too low, false alarms will frequently occur at high water level, making it difficult to play the preset protection role.

[0003] The above limitations result in the system being able to determine the completion of the operation only according to the position information, and being unable to know whether there is an abnormal physical action in the process. The cumulative damage of the motor transmission mechanism and even the gate structure caused by the over-stress driving due to encountering obstacles each time cannot be monitored by the current system, forming a potential operation risk. Therefore, a direct technical idea is to improve the safety redundancy of the driving system and the gate structure, but this not only significantly increases the engineering cost, but also does not solve the problem of lack of perception of abnormal events in principle, and may even exacerbate the structural damage when an abnormal event occurs due to stronger driving force. The root cause of the above physical limitations lies in the inherent defects of the control logic. Even if some existing technologies try to optimize the hardware structure, they cannot break through this bottleneck. For example, the Chinese invention patent with the authorization announcement number CN217997998U discloses a water conservancy gate control device. Although the device adds a slope waterproof mechanism to the mechanical structure to improve the hardware protection effect, the core control logic still stays at the level of closed-loop control of the geometric position of the gate. It only relies on the information fed back by the displacement sensor to determine whether the operation is completed. However, the power cost paid by the driving system to achieve this position is a key physical process, and the device completely lacks effective identification and analysis capabilities to distinguish between normal hydraulic load and abnormal physical obstacles, thereby leaving potential operation risks to the physical structure itself.

[0004] Specifically, the existing technologies mainly have the following deficiencies: 1. The control logic is based on the normal assumption of the driving process, and cannot identify abnormal stress that exceeds the normal physical law when the system executes instructions; 2. The safety protection mechanism only faces the electrical parameters of the driving motor itself, rather than the comprehensive operation health status of the entire water-mechanical-electrical coupling system, and lacks direct consideration of the safety of the hydraulic structure; 3. The response to faults is passive, and only interrupts after damage may have formed due to overload. For early-stage faults or progressive system performance degradation, there is a lack of effective monitoring means. Therefore, how to enable the control system to utilize its existing information to accurately interpret the power cost paid by the driving gate in real time, and effectively separate the abnormal component generated by the abnormal physical obstacles, and then realize online diagnosis and early warning of the gate operation status, becomes a technical problem to be solved by the present application. SUMMARY

[0005] The present application provides a water conservancy gate control system based on multi-source information fusion, which mainly aims to solve the problem that the existing control method cannot accurately interpret the driving power, and cannot distinguish between normal hydraulic load and abnormal physical obstacles, thereby being unable to effectively diagnose and warn the potential operation risk of the gate.

[0006] To achieve the above object, the application provides a water gate control system based on multi-source information fusion, which comprises:

[0007] a data acquisition module configured to synchronously acquire a working condition parameter sequence representing the working condition of the water gate and an actuator power cost sequence representing the driving load of the water gate during the movement of the water gate;

[0008] a fingerprint construction module connected with the data acquisition module, the fingerprint construction module being configured to instruct an actuator to drive the water gate to complete at least one reciprocating movement including an opening process and a closing process, and acquire corresponding opening power cost sequence and closing power cost sequence from the data acquisition module; then, perform symmetry check on the opening power cost sequence and the closing power cost sequence, the check is to obtain two net resistance power sequences respectively reflecting friction and additional resistance by stripping the asymmetric power part in the two sequences due to gravity or buoyancy effect, and perform mirror symmetry comparison on the two net resistance power sequences; and only when the mirror symmetry comparison result meets a preset symmetry standard, the acquired opening and closing power cost sequences are confirmed as valid reference data, and a reference health fingerprint is established based on the valid reference data;

[0009] a real-time diagnosis module configured to determine a reference power cost from the reference health fingerprint established by the fingerprint construction module according to the actual working condition parameters acquired in real time, and diagnose the running state of the water gate based on the deviation between the actual power cost acquired in real time and the reference power cost.

[0010] Preferably, the working condition parameter sequence comprises a gate position parameter sequence, a running speed parameter sequence and a running direction parameter sequence, and an upstream water level parameter sequence and a downstream water level parameter sequence associated with the water gate; the fingerprint construction module is configured to establish the reference health fingerprint based on the corresponding relationship between the working condition parameter sequence and the valid reference data, wherein the reference health fingerprint is a multi-dimensional database mapping the working condition parameters and the power cost.

[0011] Preferably, the system further comprises an active detection module, the active detection module being configured to instruct the actuator to drive the water gate to complete a preset small diagnostic stroke at a diagnostic speed lower than the normal running speed of the system under a preset diagnostic triggering condition; the real-time diagnosis module is further configured to acquire a diagnostic power cost sequence during the diagnostic stroke, and compare the diagnostic power cost sequence with a reference friction curve stored in the reference health fingerprint, so as to evaluate the long-term running health trend of the water gate.

[0012] Preferably, the reference friction curve is synchronously acquired and stored in the reference health fingerprint during the first establishment of the reference health fingerprint by performing the detection procedure of the active detection module.

[0013] Preferably, the real-time diagnosis module is specifically configured to determine the deviation by calculating a shape similarity distance between an actual power cost sequence formed by the actual power cost and a reference power cost sequence determined from the reference health fingerprint by using a dynamic time warping algorithm, and diagnose the running state as an abnormal state when the shape similarity distance exceeds a shape similarity threshold determined according to the statistical distribution characteristics of the reference health fingerprint.

[0014] Preferably, the real-time diagnosis module is further configured to calculate a health aging factor representing the long-term change of the system friction based on the comparison result of the diagnostic power cost sequence and the reference friction curve. , the calculation rule of which is , wherein is a current friction feature value calculated from the diagnostic power cost sequence, is a reference friction feature value calculated from the reference friction curve; the system further comprises a maintenance warning module, the maintenance warning module being configured to output a warning instruction when the health aging factor continuously exceeds 1.5 for two or more consecutive diagnostic cycles.

[0015] Preferably, the real-time diagnosis module is specifically configured to diagnose the running state as a resistive abnormal state when the value of the actual power cost exceeds the reference power cost by a preset first threshold, and diagnose the running state as a load loss abnormal state when the value of the actual power cost is lower than the reference power cost by a preset second threshold.

[0016] Preferably, the system further comprises a failure protection module, the failure protection module being configured to perform a preset failure protection action after the real-time diagnosis module diagnoses the resistive abnormal state or the load loss abnormal state, the failure protection action including stopping the actuator from running, instructing the actuator to run in reverse, or sending an alarm message to an upper monitoring system.

[0017] Preferably, the real-time diagnosis module is further configured to call an interpolation calculation unit when the real-time acquired actual working condition parameter has no directly mapped reference power cost in the multi-dimensional database, the interpolation calculation unit being configured to select a plurality of reference working condition points adjacent to the actual working condition parameter in the multi-dimensional space in the multi-dimensional database, calculate an interpolated reference power cost corresponding to the actual working condition parameter by a preset interpolation algorithm based on the reference power costs corresponding to the plurality of reference working condition points, and use the interpolated reference power cost as the reference power cost.

[0018] Preferably, the symmetry checking operation is specifically configured to: establish a gravity and buoyancy effect model based on the gate structure parameters and real-time hydrological parameters, and calculate theoretical power components generated by gravity and buoyancy in the opening process and the closing process respectively by using the model; then subtract the corresponding theoretical power components from the opening power cost sequence to obtain a first net resistance power sequence, and subtract the corresponding theoretical power components from the closing power cost sequence to obtain a second net resistance power sequence, and finally perform mirror symmetry comparison on the first net resistance power sequence and the second net resistance power sequence.

[0019] Compared with the prior art, the beneficial effects of the present application are:

[0020] 1. By collecting the driving power of the water conservancy gate under a specific operating condition, a power cost benchmark corresponding to the hydraulic boundary condition is established. On this basis, the method compulsorily performs a symmetry checking step before adopting any benchmark data, that is, the power sequences of the gate opening and closing strokes are obtained respectively, the power sequences mainly reflecting the friction resistance after stripping the effects of two deterministic physical quantities, gravity and buoyancy, are mirror compared, and only when the two exhibit a predetermined symmetry, the data is confirmed as an effective health fingerprint. The combination of a series of technical actions makes the system no longer rely on the credible assumption of the initial state, but establishes an internal quality inspection mechanism based on physical principles for diagnosing the effectiveness of the benchmark itself, thereby solving the potential problem that the control system fails to diagnose due to learning an unhealthy initial sample.

[0021] 2. While using the above-mentioned checked health fingerprint to diagnose the sudden resistance in the gate operation in real time, it also contains an active system health trend evaluation mechanism. The mechanism drives the gate to complete a small reciprocating motion at a preset diagnosis speed lower than the normal running speed when the gate is in a stable condition of non-task state. Under this specific physical condition, the main part of the driving power directly reflects the static and dynamic friction characteristics of the system, while the influence of high dynamic variables such as hydraulic load is effectively suppressed. By comparing the diagnosis power obtained this time with the benchmark friction curve recorded under the initial health state, the control system can actively and regularly evaluate the long-term evolution trend of its mechanical lubrication and wear state when it does not perform the regular opening and closing tasks, expanding the dimension of health management from coping with immediate failures to predicting gradual and systemic risks.

[0022] 3. When performing the comparison step of real-time diagnosis, instead of comparing the instantaneous values ​​of the two sets of power data at the same location point, the dynamic time warping algorithm is preferred to calculate the overall morphological similarity between the actual operating power sequence and the power sequence in the benchmark health fingerprint database. The introduction of this algorithm changes the core of the comparison logic from pursuing absolute numerical equivalence to judging the macroscopic conformity of the inherent trend and rhythm of the two curves. Therefore, for non-faulty small speed changes caused by power grid fluctuations or controller response differences in real engineering, the system can automatically absorb its local scaling on the time axis during the comparison process, avoiding a large number of false alarms caused by such time-domain noise. This transforms the power curve-based diagnosis method from a theoretical model into a stable solution with high reliability and practicality in real complex engineering environments.

[0023] 4. By combining a benchmark self-verification mechanism based on physical symmetry with an active detection mechanism based on diagnostic perturbation, a logically closed-loop health management system with self-updating and dynamic adaptability is constructed. The former ensures that the starting point for each system learning is reliable, guaranteeing the purity of the diagnostic benchmark from the source. The latter provides the system with the ability to continuously monitor its own state as it slowly drifts from this reliable starting point. When the long-term trend monitoring shows a significant but still safe change in the system's frictional characteristics, a fingerprint update process including self-verification can be triggered again after planned maintenance confirms the restoration of the physical state. The synergistic effect of this series of mechanisms enables the entire control system to dynamically adapt to the natural performance degradation throughout its entire life cycle, and its operational reliability no longer depends solely on the ideal state at the time of initial installation. Attached Figure Description

[0024] Fig. 1 This is a functional architecture diagram of the closed-loop health management system of the present invention;

[0025] Fig. 2 This is a schematic diagram of the health fingerprint verification principle based on power symmetry of the present invention;

[0026] Fig. 3 This is a timing diagram of the abnormal diagnosis and response interaction of the present invention. Detailed Implementation

[0027] To make the objectives, technical solutions, and advantages of the present invention clearer, the present invention will be described in further detail below. It should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0028] The application relates to a water conservancy gate control system based on multi-source information fusion, which mainly comprises a data acquisition module, a fingerprint construction module, a real-time diagnosis module, an active detection module and a failure protection module. The data acquisition module is responsible for synchronously acquiring a working condition parameter sequence representing the current working condition of a gate and an actuator power cost sequence representing the load state of a driving system during the operation of the water conservancy gate. The fingerprint construction module establishes a reference health fingerprint capable of reflecting the operation characteristics of the gate system under a preset health state through a set of rules based on physical symmetry verification according to the output of the data acquisition module. The core task of the real-time diagnosis module is to compare the real-time collected power cost with the reference power cost retrieved from the reference health fingerprint according to the real-time working condition during the daily operation of the gate, so as to instantly diagnose the health state of the operation process. The active detection module provides the ability of actively quantitatively evaluating the long-term performance evolution trend of the system during the idle period of the system as a supplement to the real-time diagnosis. The failure protection module is the execution end of the diagnosis result, and executes the preset protective action after the system is diagnosed as an abnormal state, thereby jointly constituting a complete closed-loop control system from the establishment of the reference, the state monitoring, the trend prediction to the failure protection.

[0029] In one specific application scenario, for example, the cluster scheduling control of the flood discharge gate of a large reservoir, in order to solve the technical problem that the traditional control method cannot accurately distinguish normal hydraulic load from abnormal physical obstacles such as silt and floating objects, resulting in a lack of perception of potential operation risks of the gate, the system claimed in the present application is configured to work according to the following procedures; first, in the fingerprint construction stage, in order to ensure the effectiveness of the reference data on which all subsequent diagnoses are based, the fingerprint construction module is configured to perform a set of symmetry-based verification procedures, which instruct the executor to drive the water gate to complete at least one complete opening-closing reciprocating motion. During this process, the data acquisition module will obtain the opening power cost sequence of the opening process and the closing power cost sequence of the closing process respectively. Then, the fingerprint construction module calls a gravity and buoyancy effect model established based on gate structure parameters such as the weight and volume of the gate leaf, and real-time hydrological parameters such as upstream water level and downstream water level, uses the model to calculate the theoretical power component generated by gravity and buoyancy during opening and closing, and then subtracts the corresponding theoretical power component from the original opening power cost sequence to obtain a first net resistance power sequence that mainly reflects friction and additional resistance. In the same way, the second net resistance power sequence is obtained from the closing power cost sequence. Finally, the module performs mirror symmetry comparison on the two net resistance power sequences. Only when the coincidence degree of the two curves after mirror flipping is higher than a preset symmetry standard, for example, the root mean square value of the difference between the corresponding points of the two curves is less than 5% of the total power mean value, it is determined that the learning process is not disturbed by one-way fixed obstacles, and the originally obtained complete opening and closing power cost sequences are adopted as effective reference data and stored in a multidimensional database that maps working condition parameters and power cost, forming a reference health fingerprint.

[0030] Further, after the system enters the real-time diagnosis phase of daily routine, in order to solve the technical problem that the actual operation speed curve of the gate and the reference curve cannot coincide on the time axis due to voltage fluctuation of the power grid or small differences in controller response in the real water conservancy engineering environment, and then the instantaneous power value comparison method based on the same position point is prone to false positives, the real-time diagnosis module of the present application is configured to perform comparison operation by using dynamic time warping algorithm; specifically, when the gate performs a lowering task once, the data acquisition module obtains the actual power cost sequence formed by it in real time, at the same time, the real-time diagnosis module determines the reference power cost sequence matched with the working condition according to the actual working condition parameters obtained synchronously, such as the gate position changing from 10 meters to 2 meters, the average speed being 0.1 meters per second, and the upstream water level being 50 meters, from the multi-dimensional database of the reference health fingerprint, and then the dynamic time warping algorithm takes the two time sequences as inputs, finds the optimal matching path between the two sequence data points, which allows local fast forward or slow play on the time axis, so as to calculate a minimum warping distance value that can reflect the overall shape similarity of the two curves, and the diagnosis logic of the system is based on the distance value, for example, if the minimum warping distance value calculated is 0.85, and the shape similarity threshold value determined according to historical statistical data is 1.5, then the system determines that the power curve shape of this operation process conforms to the health reference, and the running state is healthy; on the contrary, if the actual power curve appears a sharp fluctuation that does not exist in the reference curve due to foreign matter jamming, the dynamic time warping algorithm cannot offset this shape distortion through stretching of the time axis, so as to calculate a minimum warping distance value much larger than 1.5, and the system diagnoses the running state as a resistive abnormal state.

[0031] In addition, in order to make up for the limitation of passive real-time diagnosis that it is not capable of early sensing the gradual and slow increasing systematic friction, such as sand compaction in the guide rail and failure of the lubrication system, the present system also integrates an active detection module, which is configured to automatically execute a perturbation health diagnosis process under a preset diagnosis triggering condition, for example, at 2 o'clock in the morning every day in the non-flood season, in which process, the module instructs the servo motor to drive the gate to complete a small stroke, such as moving up 20 centimeters and returning, at a constant diagnosis speed lower than the normal operation speed, for example, 10% of the normal speed, since the speed is very low and constant, the influence of inertial force and water load change can be ignored, therefore, the diagnosis power cost sequence collected during this period can directly reflect the current static friction and dynamic friction characteristics of the system, and the system compares the friction characteristic curve obtained by this detection with the reference friction curve obtained and stored by the same detection process when the reference health fingerprint is first established; in order to realize quantitative evaluation, the real-time diagnosis module is also configured to calculate a health aging factor which represents the long-term change of the system friction, and the calculation rule is wherein, is a friction feature value calculated from the current diagnostic power cost sequence, such as the average power, is a reference friction feature value calculated from the reference friction curve, when the health aging factor the value of the health aging factor, for example, continuously exceeds 1.5 for three consecutive diagnostic cycles, the system built-in maintenance warning module will output a warning instruction to suggest maintenance and lubrication. This way of using the drive system to perform diagnostic actions under certain working conditions provides the system with the ability to predictively maintain the long-term health trend of the system without increasing hardware.

[0032] Example 1: In a large water conservancy hub, the control system instructs the No. 3 gate to be lowered from 50% opening to 20% opening during flood discharge scheduling in the flood season, and at this time the upstream water level is 35.2 meters; During the lowering of the gate, a piece of floating object wedges between the guide rail on the side of the gate and the gate leaf. Although the additional resistance generated by the floating object has caused the drive mechanism to bear abnormal stress, the instantaneous value of the overall actuator power cost is still lower than the fixed overload protection threshold set to cope with high water level conditions; At this time, the real-time diagnostic module in the control system of the application is continuously comparing the actual power cost sequence obtained by the data acquisition module with the reference power cost sequence determined from the reference health fingerprint according to the current gate position, speed and 35.2 meters water level and other actual working condition parameters; It should be noted that the reason why the reference health fingerprint is accepted by the system as a high-reliability comparison reference is that it has passed the verification procedure based on physical symmetry performed by the fingerprint construction module at the beginning of its establishment. This procedure filters out all possible reference data pollution caused by minor deformation or one-way obstacles in the initial state by comparing the high symmetry of the net resistance power sequence of the gate after stripping the effects of gravity and buoyancy in reciprocating motion, which ensures that the reference power cost sequence currently used for comparison can truly reflect the physical process of the gate under this working condition without failure. Therefore, although the current total power value does not trigger the overload protection, the dynamic time warping algorithm used by the real-time diagnostic module identifies a significant difference in the shape of the two curves that cannot be bridged by local stretching of the time axis when calculating the overall shape similarity between the actual power cost sequence and the reference power cost sequence. The minimum warping distance value obtained by the calculation exceeds the pre-set shape similarity threshold, which is not based on the size of a single value, but on the fact that the energy dissipation pattern of the entire physical process has deviated from its health state image, thereby avoiding the technical contradiction between the insufficient sensitivity of the protection threshold at high water level and the easy false alarm at low water level in the traditional way.

[0033] Based on the calculation result, the real-time diagnosis module diagnoses the operation state of the gate as a resistive abnormal state, and immediately transmits the diagnosis result to the failure protection module; the failure protection module immediately executes the preset failure protection action, instructs the actuator to stop running, and simultaneously sends alarm information to the upper monitoring system, indicating that the No. 3 gate has an operation abnormality at a specific position; the operation personnel conducts on-site troubleshooting according to the information, and clears the floating obstacle; in this process, the system does not equate power abnormality to motor overload, but converts the driving power cost, a physical quantity, from an electrical parameter for judging the safety of the motor itself into a diagnostic basis for auditing the health degree of the entire hydraulic structure operation process, so that an initial fault that is easily ignored in the traditional technical framework and may cause cumulative structural damage is identified and intervened in a timely manner; it should be noted that in the scenario of the present embodiment, the preset failure protection action of the failure protection module after receiving the resistive abnormality diagnosis result is further configured as a sequenced procedure containing logical judgment; the module first executes the instruction to stop the actuator running, so that the kinetic energy of the gate movement is unloaded instantaneously, and the actuator power cost is continuously monitored in this static state; if the power cost remains at a value higher than the no-load benchmark after stopping, the system determines that the resistive abnormality is caused by a hard obstacle that continuously exists and wedges the gate leaf and the gate slot; in view of this, to avoid the possibility that reverse operation may aggravate the structural stress, the failure protection module will no longer execute subsequent actions, and only maintains the alarm state; in another optional embodiment, if the system monitors that the power cost rapidly falls to the no-load benchmark after stopping running, it is determined that the resistive abnormality may be caused by a non-fixed obstacle wedged at a specific angle; at this time, the failure protection module is configured to execute the second step instruction, that is, instruct the actuator to run in reverse for a small stroke, such as 20 cm, at a lower speed; the purpose of this is to attempt to make the non-fixed obstacle fall under the impact of the reverse water flow or its own gravity, so that the system has the opportunity to automatically recover to the normal operation state; this protection action selection procedure containing diagnostic logic changes the fault handling mode of the system from a single passive cut-off to a dynamic process with a preliminary self-repair attempt.

[0034] Example 2: To objectively verify the diagnostic ability of the control system claimed in the present application for typical operation abnormalities under different hydraulic operating conditions, a test platform capable of simulating a hydraulic environment is built; the platform is mainly composed of a scaled-down steel gate model, a gate hoist driven by a servo motor, and a water tank with adjustable upstream and downstream water levels. The drive controller of the servo motor is integrated with a power monitoring unit, and its data acquisition module can record the actuator power cost sequence at a sampling frequency of 100 Hz and a resolution of 0.1 W. At the same time, a laser displacement sensor with a measurement range of 0 meters to 2 meters and an accuracy of 1 millimeter is configured in the system to obtain the gate position parameters, and an ultrasonic level meter with a measurement accuracy of 5 millimeters is used to obtain the water level parameters. To simulate typical fault scenarios, a set of electromagnetic brakes that can generate different damping forces under program control are installed at the gate guide to simulate different degrees of resistive abnormalities, and an electrically controlled clutch is integrated in the transmission chain to simulate the loss of load abnormality. This test sets up a test group using the technical solution of the present application and a control group using the traditional fixed value overload protection technology, and compares the test results under three typical operating conditions. The overload protection threshold of the control group is set to 120% of the rated power of the motor according to conventional engineering practice, i.e. 5.0 kW. The test group first performs complete opening-closing reciprocating motion under three operating conditions of high water level 65 meters, medium water level 50 meters and low water level 35 meters without any artificial fault settings, and establishes and solidifies its baseline health fingerprint through the verification procedure based on physical symmetry. The specific operating condition settings and diagnostic results of the test are shown in Table 1.

[0035] Table 1: Comparison of diagnostic results of two control systems under different operating conditions.

[0036]

[0037] In the condition number 1, the system simulates the normal flood discharge operation under high water level, and the actual peak power measured by the test group reaches 5.2 kW, which exceeds the threshold of 5.0 kW set by the control group, so the control group system reports an overload false alarm, while the real-time diagnosis module of the test group determines that the corresponding reference peak power should be 5.1 kW according to the high water level condition of 65.0 meters, and the deviation between the two is within the normal range, and the minimum regularization distance calculated is 0.45, which is less than the set shape similarity threshold of 1.5, so the system determines that the operation is healthy; in the condition number 2, the system simulates the medium-intensity silting or jamming under low water level, and the actual peak power is 4.8 kW, which does not reach the protection threshold of the control group, so the control group fails to detect this risk, but the test group system determines that the reference peak power should be 3.2 kW according to the low water level of 35.0 meters, and there is a significant deviation between the two, and the minimum regularization distance increases to 3.86 due to the distortion of the power curve shape, so the system diagnoses the state as a resistive abnormality; in the condition number 3, the system simulates the transmission shaft fracture when running at medium water level, which causes the actual power to drop to 1.5 kW, and the control group has no response, while the test group system finds that the value is much lower than the reference value of 4.1 kW determined according to the condition, and the minimum regularization distance also exceeds the threshold, so it is determined as a loss of load abnormality; the test data shows that the test group using the technical scheme of the present application can effectively identify various operating abnormal states under high dynamic hydraulic load that cannot be covered by traditional fixed value protection methods by correlating real-time working condition parameters with reference health fingerprints verified by internal quality, and using comparison logic based on shape similarity, and the diagnosis result is not disturbed by water level changes.

[0038] Embodiment 3: The embodiment combines Figs. 1 to 3 the water conservancy gate control system based on multi-source information fusion, as shown in the figure, the architecture is based on the water conservancy gate and the actuator of the physical device layer, and the running state is synchronously acquired by the sensor data of the data acquisition module, the module divides the collected original power and working condition sequence into two parts, one part is sent to the fingerprint construction module, which is responsible for performing symmetry verification and establishing the reference health fingerprint as the diagnosis reference, the other part is sent to the real-time diagnosis module, which compares the real-time sequence with the reference fetched from the reference health fingerprint to diagnose the running state, the diagnosis result is sent to the failure protection module, which receives the diagnosis result and performs the preset protection action, and sends control instructions to the physical device layer, at the same time, the system also includes an active detection module, which performs micro-motion detection on the physical device according to the control instruction to evaluate the long-term health trend, and can issue a fingerprint update or calibration instruction to the fingerprint construction module based on the evaluation result, thereby forming a logically closed-loop health management system. Fig. 1 ​

[0039] As Fig. 2 shown, the relationship between the opening power sequence, the mirror-processed closing power sequence, and the calculated net resistance power sequence in a complete reciprocating motion is demonstrated, where the horizontal coordinate is the gate position / %, and the vertical coordinate is the power cost / kW. The solid line in the figure represents the opening power sequence, the long dashed line represents the closing power sequence mirror, and the dotted line represents the net resistance power sequence. By removing the asymmetric components generated by gravity, buoyancy, etc. from the original opening and closing power sequences, the two net resistance power sequences obtained should be highly coincident in form, as shown in the figure. Only when this mirror symmetry meets the preset standard, the system will accept the collected data as valid and healthy benchmark.

[0040] As Fig. 3 shown, the participants of the figure include the water gate, the data acquisition module, the real-time diagnosis module, the benchmark health fingerprint, the failure protection module, and the upper monitoring system. The process begins with the normal operation of the water gate. The data acquisition module obtains the real-time working condition parameter sequence and the actual power cost sequence, and transmits them to the real-time diagnosis module. The module then queries the benchmark power cost to the benchmark health fingerprint and obtains the returned data. Then, the dynamic time warping method is used to compare and calculate the shape similarity distance. If the similarity distance is normal, the monitoring continues. If the similarity distance exceeds the threshold, it is diagnosed as an abnormal state, and the abnormal diagnosis result is sent to the failure protection module, which executes the failure protection action and issues an order to the water gate. At the same time, an alarm information is sent to the upper monitoring system until the abnormal processing is completed.

[0041] Embodiment 4: To avoid the uncertainty caused by empirical setting of the key parameters relied by the core diagnostic logic of the control system of the present invention after its initial deployment or major maintenance, such as the symmetry criterion for judging the validity of the reference data and the morphological similarity threshold for real-time diagnosis, this embodiment discloses a systematic off-line calibration and parameter self-tuning procedure; the initial state of the procedure is a water gate system that has been physically inspected and confirmed to be in a mechanically sound and flow passage clean state, as well as a control and data acquisition hardware environment with functional specifications; after the procedure is started, the system first performs a preliminary acquisition and verification process of the reference health fingerprint, in which the controller instructs the actuator to perform 10 complete opening and closing reciprocating movements at a standard speed covering the main working interval, and the data acquisition module synchronously records the working condition parameter sequence and actuator power cost sequence of all 20 strokes; for each reciprocating movement, the fingerprint construction module calculates the mirror symmetry comparison result between the two net resistance power sequences of the opening and closing strokes according to the method in the specific embodiment, which is quantified by the root mean square error of the difference between the corresponding position points of the two curves, thereby obtaining 10 root mean square error values, and the system immediately calculates the statistical mean of these 10 error values and the standard deviation , and determines the symmetry criterion as Any stroke data whose symmetry error exceeds this criterion in the preliminary acquisition will be considered as being disturbed by random interference and discarded.

[0042] On the basis of utilizing the power cost sequence set in multiple health states screened out by the above-mentioned process, the system further performs calibration of the shape similarity threshold; the real-time diagnosis module is configured to call the dynamic time warping algorithm, and perform similarity calculation on all power cost sequences of the same running direction in the set in pairs, for example, if there are 8 effective opening trip power sequences, the system will perform 28 dynamic time warping calculations, thereby obtaining a statistical sample consisting of 28 minimum warping distance values; the system then calculates the statistical distribution characteristics of the sample, and sets the shape similarity threshold to the value corresponding to the 99th percentile of the sample. In this way, the threshold becomes a limit that can reflect the inherent variation range of the power curve of the specific gate system in the healthy state. At the same time, when constructing a multidimensional database for storing reference health fingerprints, the system is configured to index the working condition parameters using a k-d tree structure for subsequent nearest neighbor search, and when the actual working condition parameters obtained in real time have no direct mapping reference power cost in the database, the interpolation calculation unit called by the system is configured to use a trilinear interpolation algorithm, that is, according to the relative position of the actual working condition point in the three-dimensional space consisting of gate position, running speed and upstream water level, select the nearest 8 reference working condition points around it, and based on the reference power costs corresponding to the 8 points, perform weighted average calculation to obtain the interpolated reference power cost corresponding to the actual working condition. After this series of calibration procedures, the core judgment basis of the entire control system is given a traceable source, and the system thus enters a standby state of parameter state determination and diagnosis logic closed loop.

[0043] Embodiment 5: In a regulation gate project containing multiple water gates running side by side, to solve the problem that each gate has its specific friction characteristics even under the same working condition due to manufacturing tolerances, installation differences and uneven wear during long-term operation, the control system of the present application is configured to independently perform the offline calibration and parameter self-tuning procedures in Embodiment 3 for each gate when first deployed; specifically, the system will establish a set of independent reference health fingerprints, symmetry standards and shape similarity thresholds for No. 1 gate, No. 2 gate to No. N gate, which are uniquely corresponding to the physical entity of each gate, and bind and store these parameter sets with the unique device identification code of the gate. In the subsequent real-time diagnosis process, when the system needs to assess the state of any one of the gates, such as No. 2 gate, it will first read the device identification code of the gate, and then call the parameter set exclusively for No. 2 gate from the storage according to the identification code for comparison operation.

[0044] Further, to adapt to the performance drift of the hydraulic structure due to mechanical wear or change in lubrication state in the whole life cycle, the system is also configured with a set of dynamic updating procedures of the benchmark health fingerprint based on the active detection results; as the specific embodiment, the system periodically acquires the health aging factor reflecting the long-term change of the system friction through the active detection module When the numerical value of a certain gate When the numerical value of a certain gate When the numerical value of a certain gate

[0045] When the numerical value of a certain gate When the numerical value of a certain gate .

[0046] When the numerical value of a certain gate When the numerical value of a certain gate When the numerical value of a certain gate The numerical value, i.e. 1.5, is set as the preset maintenance threshold for the system to output the scheduled maintenance instruction, and this procedure anchors the basis of the maintenance decision from an empirical estimate to a reproducible parameter associated with the specific physical wear degree; at the same time, to deal with the possible unnoticeable persistent physical abnormalities that may exist when the system is initially deployed, such as slight permanent deformation of the guide rail, the fingerprint construction module of the present application is configured to, when performing the symmetry check, if the root mean square error value calculated in the preliminary sampling of 10 consecutive reciprocating movements exceeds the stroke data more than 5 times, or the standard deviation of all error values itself exceeds an upper threshold value representing the degree of data dispersion, the system will suspend the establishment procedure of the baseline health fingerprint, and send an alarm to a higher monitoring system that the baseline learning environment is abnormal, which can avoid the system mistakenly learning an initial state with disease as a healthy baseline.

[0047] To further verify the key role of the symmetry-based checking procedure in the system claimed in the present application in ensuring the purity of the baseline data, the following Comparative Example 1 is provided.

[0048] Comparative Example 1: The only difference between this comparative example and the test group in Example 2 is that the control system does not perform the symmetry-based checking procedure of the present application when establishing the baseline health fingerprint, but instead adopts the conventional technical path known in the art, i.e. assuming that the system is in perfect condition when initially deployed, and directly taking the first collected power cost sequence as the baseline; the test process is as follows: when the system is initially deployed and baseline data is collected, an obstacle is artificially set in the guide rail on the side of the gate to simulate an unnoticeable initial fault in the field, which only produces significant friction resistance during the closing (lowering) stroke of the gate; in this state, the instruction system performs a complete opening-closing reciprocating motion to collect baseline data, and measures that the peak power during the opening process under the high water level 65.0 meter working condition is 5.1 kW, which is consistent with the healthy state; but the peak power during the closing process increases to 5.8 kW due to the influence of the one-way obstacle. The control system of this comparative example, which does not have the symmetry checking capability, confirms the collected asymmetric data, which has been contaminated, as valid baseline, and establishes an incorrect baseline health fingerprint based on it, which stores the incorrect record that the baseline peak power under the high water level 65.0 meter working condition is 5.8 kW; after that, the obstacle is removed, and the gate returns to a completely healthy physical state. To directly compare with Working Condition No. 1, the same high water level normal operation test as Working Condition No. 1 is performed again. The diagnostic results of this comparative example are compared with those of Working Condition No. 1 in Example 2 of the present application, which are shown in Table 2.

[0049] Table 2: Comparison table of diagnostic results of Comparative Example 1 and the present application in the scenario of initial baseline contamination.

[0050]

[0051] The result of Comparative Example 1 shows that without the reference self-checking mechanism proposed by the present application, the control system cannot identify the pollution in the initial reference data, and it will mistakenly learn a high power value (5.8 kW) polluted by a one-way fault as a healthy reference; therefore, when the gate is running in a subsequent real healthy state, its normal power cost (5.2 kW) is mistakenly judged as a loss of load anomaly by the system because it is significantly lower than this false reference. This test result confirms that without the preposed, physics-symmetry-based checking link, the conventional technical solution cannot guarantee the purity of the diagnostic reference, and when facing the non-ideal engineering reality of the initial state, it has the inherent risk of outputting a serious false diagnosis.

[0052] It is obvious for those skilled in the art that the present application is not limited to the details of the above exemplary embodiments, and the present application can be implemented in other specific forms without departing from the spirit or essential characteristics of the present application.

[0053] Finally, it should be noted that the above examples are only used to illustrate the technical solutions of the present application and are not limiting. Although the present application has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solutions of the present application can be modified or replaced equivalently without departing from the spirit and scope of the technical solutions of the present application.

Claims

1. A hydraulic gate control system based on multi-source information fusion, characterized in that, The system includes: A data acquisition module is configured to simultaneously acquire a sequence of operating parameters characterizing the operating condition of the hydraulic gate and a sequence of actuator power costs characterizing its driving load during the operation of the hydraulic gate. A fingerprint construction module, connected to a data acquisition module, is configured to: instruct an actuator to drive a hydraulic gate to complete at least one reciprocating motion including an opening and closing process, and obtain the corresponding opening power cost sequence and closing power cost sequence from the data acquisition module; then, perform a symmetry check on the opening power cost sequence and closing power cost sequence, which is done by stripping the asymmetric power part caused by gravity or buoyancy effect from the opening power cost sequence and closing power cost sequence to obtain two net resistance power sequences reflecting friction and additional resistance respectively, and perform a mirror symmetry comparison on the two net resistance power sequences; and only when the result of the mirror symmetry comparison meets a preset symmetry standard are the obtained opening and closing power cost sequences confirmed as valid reference data, and a reference health fingerprint is established based on the valid reference data; A real-time diagnostic module is configured to determine a baseline power cost from the baseline health fingerprint established by the fingerprint construction module based on the actual operating parameters acquired in real time, and diagnose the operating status of the hydraulic gate based on the deviation between the actual power cost acquired in real time and the baseline power cost. In addition, the system also includes an active detection module, which is configured to: under a preset diagnostic trigger condition, the instruction executor drives the hydraulic gate to complete a preset micro-diagnostic stroke at a diagnostic speed lower than the normal operating speed of the system; the real-time diagnostic module is also configured to acquire the diagnostic power cost sequence during the diagnostic stroke and compare the diagnostic power cost sequence with a benchmark friction curve stored in the benchmark health fingerprint; The baseline friction curve is acquired and stored in the baseline health fingerprint during the initial establishment of the baseline health fingerprint by executing the detection process of the active detection module.

2. A hydraulic gate control system based on multi-source information fusion according to claim 1, characterized in that, The operating condition parameter sequence includes the gate position parameter sequence, the operating speed parameter sequence, and the operating direction parameter sequence, as well as the upstream water level parameter sequence and the downstream water level parameter sequence associated with the hydraulic gate; the fingerprint construction module is configured to establish a benchmark health fingerprint based on the correspondence between the operating condition parameter sequence and the effective benchmark data, wherein the benchmark health fingerprint is a multi-dimensional database that maps the operating condition parameters to the power cost.

3. A hydraulic gate control system based on multi-source information fusion according to claim 1, characterized in that, The real-time diagnostic module is specifically configured to: determine the deviation by using a dynamic time warping algorithm to calculate the morphological similarity distance between the actual power cost sequence formed by the actual power cost and the benchmark power cost sequence determined from the benchmark health fingerprint; Furthermore, when the morphological similarity distance exceeds the morphological similarity threshold determined based on the statistical distribution characteristics of the baseline health fingerprint, the operating status will be diagnosed as an abnormal state.

4. A hydraulic gate control system based on multi-source information fusion according to claim 1, characterized in that, The real-time diagnostic module is also configured to calculate a health aging factor characterizing the long-term frictional changes of the system based on the comparison results between the diagnostic power cost sequence and the baseline friction curve. The calculation rule is as follows ,in, The current friction characteristic value is calculated from the diagnostic power cost sequence. The reference friction characteristic value is calculated from the reference friction curve; the system also includes a maintenance early warning module, which is configured to detect health aging factors. If the value exceeds 1.5 for two or more consecutive diagnostic cycles, an early warning command will be output.

5. A hydraulic gate control system based on multi-source information fusion according to claim 1, characterized in that, The real-time diagnostic module is specifically configured to: diagnose the operating state as a resistive abnormal state when the actual power cost exceeds the reference power cost by a preset first threshold; and diagnose the operating state as an off-load abnormal state when the actual power cost is lower than the reference power cost by a preset second threshold.

6. A hydraulic gate control system based on multi-source information fusion according to claim 5, characterized in that, The system also includes a failure protection module, which is configured to execute a preset failure protection action after the real-time diagnostic module detects a resistive abnormality or an underload abnormality. The failure protection action includes stopping the actuator, instructing the actuator to run in reverse, or sending an alarm message to a higher-level monitoring system.

7. A hydraulic gate control system based on multi-source information fusion according to claim 2, characterized in that, The real-time diagnostic module is also configured to: when the actual operating parameters acquired in real time do not have a directly mapped reference power cost in the multidimensional database, call an interpolation calculation unit. The interpolation calculation unit is configured to select multiple reference operating points in the multidimensional database that are adjacent to the actual operating parameters in the multidimensional space, and calculate the interpolated reference power cost corresponding to the actual operating parameters based on the reference power cost corresponding to the multiple reference operating points through a preset interpolation algorithm, and use the interpolated reference power cost as the reference power cost.

8. A hydraulic gate control system based on multi-source information fusion according to claim 1, characterized in that, The symmetry verification operation is specifically configured as follows: a gravity and buoyancy effect model is established based on the gate structure parameters and real-time hydrological parameters, and the theoretical power components generated by gravity and buoyancy during the opening and closing processes are calculated using this model; then, the corresponding theoretical power components are subtracted from the opening power cost sequence to obtain the first net resistance power sequence, and the corresponding theoretical power components are subtracted from the closing power cost sequence to obtain the second net resistance power sequence; finally, a mirror symmetry comparison is performed between the first net resistance power sequence and the second net resistance power sequence.

Images