Pressing plate state monitoring method, device and equipment and storage medium

Abstract

The invention discloses a pressing plate state monitoring method and device, equipment and a storage medium. According to the method, the real-time voltage data, the historical voltage data and the initial particle set of the pressing plate are acquired, and then the weight value of each particle in the initial particle set is updated according to the real-time voltage data and the historical voltage data, so that the weight value of each particle in the initial particle set is calculated according to two dimensions of long-term rules and short changes in the voltage data of the pressing plate; according to the method, each particle can represent the state of the pressing plate more accurately, then the initial particle set is iteratively updated through weight values and a preset state transition model, the rule of state transformation of the pressing plate is captured through the preset state transition model, and iteration updating is carried out in combination with the weight values, so that the state of the pressing plate can be represented more accurately. Therefore, misjudgment of the state of the pressing plate caused by the single number of times of a single particle is avoided, so that each particle can more accurately represent the possible state of the pressing plate, and then the state of each particle in the first particle set is synthesized to realize accurate monitoring of the state of the pressing plate.

Description

Technical Field

[0001] The present invention belongs to the technical field of power equipment monitoring, and particularly relates to a method, device, equipment and storage medium for monitoring the state of a pressure plate. Background Art

[0002] The normal working state of a relay protection device directly affects the safe and stable operation of the entire substation and even the power grid system. In order to be able to judge the connection status of the tripping circuit in the relay protection device, currently, a pressure plate is usually installed on the secondary circuit. As a key component of a visible electrical breakpoint, the state of the pressure plate is not only related to the functional integrity of the relay protection device, but also provides a basis for the maintenance of power equipment in the substation.

[0003] Currently, for the detection of the state of the pressure plate of a relay protection device, it is usually based on manual inspection. During the inspection process, factors such as the skill level and inspection experience of the operator will lead to misjudgment and misoperation of the state of the pressure plate, thereby reducing the accuracy of the judgment of the state of the pressure plate and seriously affecting the stable operation of the substation. Moreover, there are a large number of pressure plates in the substation. Relying solely on manual inspection has a large workload, resulting in low efficiency and unable to ensure the timeliness of the monitoring of the state of the pressure plate. Therefore, there is an urgent need for a method, device, equipment and storage medium for monitoring the state of the pressure plate to solve the defects of the existing technology. Summary of the Invention

[0004] The present invention aims to provide a method, device, equipment and storage medium for monitoring the state of a pressure plate to solve the above technical problems. By iteratively updating the initial particle set with the real-time voltage data and historical voltage data of the pressure plate, the accuracy of the judgment of the state of the pressure plate is improved.

[0005] To solve the above technical problems, an embodiment of the present invention provides a method for monitoring the state of a pressure plate, including:

[0006] Obtaining the real-time voltage data, historical voltage data and initial particle set of the pressure plate;

[0007] Updating the weight value of each particle in the initial particle set according to the real-time voltage data and historical voltage data;

[0008] Iteratively updating the initial particle set according to the weight value of each particle and a preset state transition model to determine a first particle set;

[0009] Determining the state of the pressure plate according to the state of each particle in the first particle set.

[0010] It can be understood that, compared with the prior art, the present invention obtains the real-time voltage data, historical voltage data and initial particle set of the pressing plate, and then updates the weight value of each particle in the initial particle set according to the real-time voltage data and historical voltage data. From the two dimensions of the long-term law and short-term change in the pressing plate voltage data, each particle can more accurately represent the state of the pressing plate. Then, through the weight value and the preset state transition model, the initial particle set is iteratively updated. The preset state transition model captures the law of the pressing plate state transformation, and combined with the weight value for iterative update, avoiding the misjudgment of the pressing plate state caused by a single particle and a single number of times. Thus, each particle can more accurately represent the possible states of the pressing plate. Then, by synthesizing the states of each particle in the first particle set, the accurate monitoring of the pressing plate state is realized. The present invention only needs to collect the voltage data of the pressing plate to realize the accurate monitoring of the pressing plate state, avoiding the low efficiency and untimely monitoring of the pressing plate state caused by manual inspection in the prior art, and improving the efficiency of monitoring the pressing plate state.

[0011] As a preferred solution, the process of obtaining the initial particle set specifically includes:

[0012] Obtain a number of particles, and initialize the weight value of each particle according to the number of the particles;

[0013] Obtain the state set of the pressing plate, and initialize the state of each particle according to the state set;

[0014] Update the state of each particle according to the preset state transition model, and determine the initial particle set based on the updated particles.

[0015] This preferred solution initializes the particle weight value and initializes the state of each particle according to the state set of the pressing plate, ensuring that the initial particle distribution covers all possible states of the pressing plate, ensuring the effectiveness of subsequent iteration of the initial particle set; and updates the state of the particles through the state transition model, providing a reasonable prior distribution for subsequent iteration of the initial particle set, avoiding the problems of slow convergence speed or divergence caused by unreasonable particle distribution, and improving the overall stability and reliability of the iteration, thereby improving the accuracy of judging the pressing plate state.

[0016] As a preferred solution, the updating of the weight value of each particle in the initial particle set according to the real-time voltage data and historical voltage data specifically includes:

[0017] Calculate the voltage distribution data set of the pressing plate in each state according to the historical voltage data, and determine the observation model of the pressing plate according to the voltage distribution data set;

[0018] Calculate the likelihood value of each particle in the initial particle set at the real-time voltage data according to the real-time voltage data of the pressure plate and the current state of each particle in the initial particle set, and in combination with the observation model;

[0019] Update the weight value of each particle in the initial particle set according to the likelihood value.

[0020] This preferred solution constructs an observation model of the pressure plate through historical voltage data, which can accurately reflect the relationship between the pressure plate and the voltage. Then, by combining the real-time voltage data and the observation model to calculate the particle likelihood value, dynamic observation data fusion can be achieved, ensuring that the weight value of the particle can accurately imply the state information of the pressure plate, thereby improving the effectiveness of the subsequent iteration of the initial particle set and thus improving the accuracy of the judgment of the pressure plate state.

[0021] As a preferred solution, the calculation of the voltage distribution data set of the pressure plate in each state according to the historical voltage data and the determination of the observation model of the pressure plate according to the voltage distribution data set specifically include:

[0022] Determine the rated voltage range of the pressure plate in each state according to the historical voltage data;

[0023] Determine the voltage mean value of the pressure plate in each state according to the historical voltage data;

[0024] Determine the voltage standard deviation of the pressure plate in each state according to the historical voltage data;

[0025] Determine the voltage distribution data set of the pressure plate in each state according to the rated voltage range, voltage mean value and voltage standard deviation;

[0026] Construct a Gaussian distribution model of the pressure plate in each state according to the voltage distribution data set of the pressure plate in each state, and determine the observation model of the pressure plate.

[0027] This preferred solution constructs an observation model of the pressure plate through historical voltage data, which can accurately reflect the relationship between the pressure plate and the voltage, thus providing a reference for historical data for the subsequent update of the pressure plate weight value, improving the accuracy of the update of the pressure plate weight value, ensuring that the weight value of the particle can accurately imply the state information of the pressure plate, and further improving the effectiveness of the subsequent iteration of the initial particle set and thus improving the accuracy of the judgment of the pressure plate state.

[0028] As a preferred solution, the iterative update of the initial particle set according to the weight value of each particle and the preset state transition model to determine the first particle set specifically includes:

[0029] Determine the cumulative weight value of each particle according to the weight value of each particle, and construct a particle weight value distribution diagram of the initial particle set according to the cumulative weight value of each particle;

[0030] Determine the particle weight distribution threshold according to the preset weight distribution threshold generation algorithm;

[0031] According to the particle weight distribution threshold and the particle weight value distribution diagram, combined with the preset state transition model, iteratively update the initial particle set until the number of iterations of the initial particle set meets the preset iteration requirements, complete the iterative update of the initial particle set, and determine the first particle set.

[0032] In this preferred solution, a particle weight value distribution diagram is constructed through the cumulative weight value, the weight value is converted into an intuitive probability distribution structure, and the initial particle set can be screened by combining the particle weight distribution threshold. Then, the initial particle set is iteratively updated through the state transition model, and the distribution of the initial particle set is gradually corrected, so that the first particle set can more accurately represent the actual state of the platen, improving the accuracy of the platen state judgment.

[0033] As a preferred solution, the step of according to the particle weight distribution threshold and the particle weight value distribution diagram, combined with the preset state transition model, iteratively update the initial particle set until the number of iterations of the initial particle set meets the preset iteration requirements, complete the iterative update of the initial particle set, and determine the first particle set specifically includes:

[0034] Eliminate the particles in the initial particle set according to the particle weight distribution threshold and the particle weight value distribution diagram;

[0035] Construct a second particle set according to the preset particle swarm construction algorithm;

[0036] Merge the second particle set into the initial particle set, update the state of each particle in the initial particle set according to the state transition model, then update the second particle set, the particle weight distribution threshold and the particle weight value distribution diagram according to the iteratively updated initial particle set, and further iteratively update the initial particle set according to the updated second particle set, the particle weight distribution threshold and the particle weight value distribution diagram until the number of iterations of the initial particle set meets the preset iteration requirements, and determine the first particle set.

[0037] In this preferred solution, the initial particle set is screened through the particle weight distribution threshold. By introducing a second particle set, it is avoided that the update of the initial particle set falls into the error of local optimality. Combined with the state transition model, the initial particle set is iteratively updated, and the distribution of the initial particle set is gradually corrected, so that the first particle set can more accurately represent the actual state of the platen, improving the accuracy of the platen state judgment.

[0038] As a preferred solution, determining the state of the platen according to the state of each particle in the first particle set specifically includes:

[0039] According to the state of each particle in the first particle set, determine the quantity corresponding to the state of each particle;

[0040] Perform weighted calculation on the quantity corresponding to the state of each particle, and determine the state of the platen according to the weighted calculation result.

[0041] Correspondingly, an embodiment of the present invention provides a platen state monitoring device, including: a data acquisition module, a particle weight value update module, a particle set update module, and a platen state determination module;

[0042] Among them, the data acquisition module is used to acquire the real-time voltage data, historical voltage data, and initial particle set of the platen;

[0043] The particle weight value update module is used to update the weight value of each particle in the initial particle set according to the real-time voltage data and historical voltage data;

[0044] The particle set update module is used to iteratively update the initial particle set according to the weight value of each particle and the preset state transition model to determine the first particle set;

[0045] The platen state determination module is used to determine the state of the platen according to the state of each particle in the first particle set.

[0046] It can be understood that, compared with the prior art, the present device obtains the real-time voltage data, historical voltage data and initial particle set of the pressure plate, and then updates the weight value of each particle in the initial particle set according to the real-time voltage data and historical voltage data. From the two dimensions of the long-term law and short-term change in the pressure plate voltage data, each particle can more accurately represent the state of the pressure plate. Then, through the weight value and the preset state transition model, the initial particle set is iteratively updated. The preset state transition model captures the law of the pressure plate state transformation and is iteratively updated in combination with the weight value, avoiding the misjudgment of the pressure plate state caused by a single particle for a single time. Thus, each particle can more accurately represent the possible states of the pressure plate. Then, by synthesizing the states of each particle in the first particle set, the accurate monitoring of the pressure plate state is realized. The present device only needs to collect the voltage data of the pressure plate to achieve the accurate monitoring of the pressure plate state, avoiding the low efficiency and untimely monitoring of the pressure plate state caused by manual inspection in the prior art, and improving the efficiency of monitoring the pressure plate state.

[0047] Correspondingly, an embodiment of the present invention provides a terminal device, including:

[0048] One or more processors;

[0049] A memory, coupled to the processor, for storing one or more programs;

[0050] When the one or more programs are executed by the one or more processors, the one or more processors implement a method for monitoring the state of a pressure plate as described above.

[0051] Correspondingly, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, and the computer program is executed by a processor to implement a method for monitoring the state of a pressure plate as described above. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 : A flowchart of the steps of a method for monitoring the state of a pressure plate provided by an embodiment of the present invention;

[0053] Figure 2 : A schematic structural diagram of a device for monitoring the state of a pressure plate provided by an embodiment of the present invention;

[0054] Figure 3 : A schematic structural diagram of a system for monitoring the state of a pressure plate provided by an embodiment of the present invention;

[0055] Wherein, 201: Data acquisition module; 202: Particle weight value update module; 203: Particle set update module; 204: Pressure plate state determination module; 301: Sensor module; 302: Communication module; 303: Host computer module; 304: Display module. Specific Embodiments

[0056] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without making creative efforts belong to the scope of protection of the present invention.

[0057] Embodiment 1

[0058] Please refer to Figure 1 , which is a flowchart of the steps of a method for monitoring the state of a pressure plate provided by an embodiment of the present invention, including steps S101 to S104.

[0059] Step S101: Obtain the real-time voltage data, historical voltage data, and initial particle set of the pressure plate.

[0060] In this embodiment, the process of obtaining the initial particle set specifically includes:

[0061] Obtain a number of particles and initialize the weight value of each particle according to the number of the particles;

[0062] Obtain the state set of the pressure plate and initialize the state of each particle according to the state set;

[0063] Update the state of each particle according to a preset state transition model, and determine the initial particle set based on the updated particles.

[0064] In an optional embodiment, 1000 particles are obtained, and then the weight value of each particle is initialized to a uniform distribution according to the number of particles, that is, the weight value of each particle is initialized to 1 / 1000; then the state set of the pressure plate is obtained. The state set of the pressure plate in this embodiment has two states: closed (defined as state 1) and open (defined as state 0). Then, the state of each particle is assigned according to these two states of the closed state and the open state, that is, each particle has one of the closed state or the open state, and the initialization of each particle is completed.

[0065] It should be noted that the number of particles described in this embodiment is only an exemplary description. Those skilled in the art can also adaptively adjust the number of particles according to actual iteration requirements, judgment accuracy requirements, etc.; the initialization of the weight value of each particle and the specific content of the state set of the pressure plate described in this embodiment can also be further adjusted by those skilled in the art according to requirements.

[0066] It should be noted that the state transition model is a mathematical model or logical framework used to describe the transitions of a system between different states. The state transition model is used to describe the state change rules of a system, process, or event. It can predict future states or infer previous states based on observed states. The state transition model usually uses probabilities to represent the transition relationships between states and is therefore also called a probabilistic state transition model.

[0067] In an optional embodiment, the form of the preset state transition model is set as a state transition matrix: This state transition matrix is used to represent the particles of the platen. There is a 90% probability that they will continue to remain closed and a 10% probability that they will change to open; more specifically, the state transition matrix of this embodiment can be obtained based on the historical state information of the platen. The number of times the platen is in the open and closed states is collected over a period of time, and then information such as the number and distribution of the platen is calculated based on mathematical statistics methods to determine this state transition matrix.

[0068] In an optional embodiment, please refer to Table 1, which is a state prediction schematic diagram for updating the particle state based on the state transition model provided in this embodiment; as shown in Table 1, the current state of the particles is calculated according to the state transition model to obtain the predicted state, and then the particle state is updated according to the predicted state to obtain the initial particle set.

[0069] Table 1

[0070]

[0071] In this embodiment, by initializing the particle weight values and initializing the state of each particle according to the state set of the platen, it is ensured that the initial particle distribution covers all possible states of the platen, ensuring the effectiveness of subsequent iteration of the initial particle set; and the state of the particles is updated through the state transition model, providing a reasonable prior distribution for subsequent iteration of the initial particle set, avoiding problems such as slow convergence or divergence caused by unreasonable particle distribution, and enhancing the overall stability and reliability of the iteration, thereby improving the accuracy of platen state judgment.

[0072] Step S102: Update the weight value of each particle in the initial particle set according to the real-time voltage data and historical voltage data.

[0073] In this embodiment, the updating the weight value of each particle in the initial particle set according to the real-time voltage data and historical voltage data specifically includes:

[0074] Calculate the voltage distribution dataset of the pressure plate in each state based on the historical voltage data, and determine the observation model of the pressure plate according to the voltage distribution dataset;

[0075] Calculate the likelihood value of each particle in the initial particle set at the real-time voltage data according to the real-time voltage data of the pressure plate and the current state of each particle in the initial particle set, and in combination with the observation model;

[0076] Update the weight value of each particle in the initial particle set according to the likelihood value.

[0077] In this embodiment, an observation model of the pressure plate is constructed through historical voltage data, which can accurately reflect the relationship between the pressure plate and the voltage. Then, by combining the real-time voltage data and the observation model to calculate the particle likelihood value, dynamic observation data fusion can be achieved, ensuring that the weight value of the particle can accurately imply the state information of the pressure plate, thereby improving the effectiveness of the subsequent iteration of the initial particle set and improving the accuracy of the pressure plate state judgment.

[0078] In this embodiment, the step of calculating the voltage distribution dataset of the pressure plate in each state based on the historical voltage data and determining the observation model of the pressure plate according to the voltage distribution dataset specifically includes:

[0079] Determine the rated voltage range of the pressure plate in each state according to the historical voltage data;

[0080] Determine the voltage mean value of the pressure plate in each state according to the historical voltage data;

[0081] Determine the voltage standard deviation of the pressure plate in each state according to the historical voltage data;

[0082] Determine the voltage distribution dataset of the pressure plate in each state according to the rated voltage range, voltage mean value and voltage standard deviation;

[0083] Construct a Gaussian distribution model of the pressure plate in each state according to the voltage distribution dataset of the pressure plate in each state, and determine the observation model of the pressure plate.

[0084] In an optional embodiment, historical voltage data of the pressure plate in the closed state is obtained. Then, based on this historical voltage data, the rated voltage range of the pressure plate in the closed state is calculated to be 400 mV to 500 mV, the voltage mean value is 450 mV, and the voltage standard deviation is 10 mV; historical voltage data of the pressure plate in the open state is obtained. Then, based on this historical voltage data, the rated voltage range of the pressure plate in the open state is calculated to be about 300 mV, the voltage mean value is 300 mV, and the voltage standard deviation is 20 mV; then, based on the rated voltage range, voltage mean value, and voltage standard deviation, a voltage distribution data set of the pressure plate in the closed state and the open state is determined, and then the corresponding Gaussian distribution model is determined to obtain an observation model of the pressure plate.

[0085] In an optional embodiment, the calculation process of the likelihood value is as follows:

[0086]

[0087] In the formula, w j represents the likelihood value at the j-th update, z i represents the real-time voltage corresponding to the i-th particle, V is the real-time voltage, x i represents the current state of the i-th particle, K is the current state, m is the voltage standard deviation corresponding to the current state; n is the voltage mean value corresponding to the current state.

[0088] Assume that the real-time voltage data of the pressure plate is 410 mV. For the first particle (the current state is the closed state, that is, state 1), the calculation process of its likelihood value at the real-time voltage data is as follows:

[0089]

[0090] For the second particle (the current state is the open state, that is, state 0), the calculation process of its likelihood value at the real-time voltage data is as follows:

[0091]

[0092] As described above, the likelihood value of each particle is used as the new weight value corresponding to each particle.

[0093] It should be noted that the likelihood values of the remaining particles are similar to the above calculation process of the likelihood value.

[0094] In this embodiment, an observation model of the pressure plate is constructed through historical voltage data, which can accurately reflect the relationship between the pressure plate and the voltage, thereby providing a reference of historical data for the subsequent update of the weight value of the pressure plate, improving the accuracy of the update of the weight value of the pressure plate, ensuring that the weight value of the particle can accurately imply the state information of the pressure plate, and then improving the effectiveness of the subsequent iteration of the initial particle set, and thus improving the accuracy of the judgment of the pressure plate state.

[0095] Step S103: Iteratively update the initial particle set according to the weight value of each particle and the preset state transition model to determine the first particle set.

[0096] In this embodiment, the iteratively updating the initial particle set according to the weight value of each particle and the preset state transition model to determine the first particle set specifically includes:

[0097] Determine the cumulative weight value of each particle according to the weight value of each particle, and construct a particle weight value distribution diagram of the initial particle set according to the cumulative weight value of each particle;

[0098] Determine the particle weight distribution threshold according to the preset weight distribution threshold generation algorithm;

[0099] Iteratively update the initial particle set according to the particle weight distribution threshold, the particle weight value distribution diagram, and in combination with the preset state transition model until the number of iterations of the initial particle set meets the preset iteration requirement, complete the iterative update of the initial particle set, and determine the first particle set.

[0100] In this embodiment, a particle weight value distribution diagram is constructed through the cumulative weight value, the weight value is converted into an intuitive probability distribution structure, and the initial particle set can be screened in combination with the particle weight distribution threshold. Then, the initial particle set is iteratively updated through the state transition model, and the distribution of the initial particle set is gradually corrected, so that the first particle set can more accurately represent the actual state of the platen, improving the accuracy of the platen state judgment.

[0101] In this embodiment, the iteratively updating the initial particle set according to the particle weight distribution threshold, the particle weight value distribution diagram, and in combination with the preset state transition model until the number of iterations of the initial particle set meets the preset iteration requirement, complete the iterative update of the initial particle set, and determine the first particle set specifically includes:

[0102] Eliminate the particles in the initial particle set according to the particle weight distribution threshold and the particle weight value distribution diagram;

[0103] Construct a second particle set according to the preset particle swarm construction algorithm;

[0104] Merge the second particle set into the initial particle set, update the state of each particle in the initial particle set according to the state transition model, and then update the second particle set, the particle weight distribution threshold, and the particle weight value distribution diagram based on the iteratively updated initial particle set. Furthermore, iteratively update the initial particle set based on the updated second particle set, particle weight distribution threshold, and particle weight value distribution diagram until the number of iterations for the initial particle set meets the preset iteration requirements, and determine the first particle set.

[0105] In an optional embodiment, by iteratively updating the initial particle set, resampling of the particles can be achieved, so that the state distribution of the particles in the initial particle set is more reasonable and can more accurately reflect the actual state of the platen. First, accumulate the weight values corresponding to each update of the particles to obtain the cumulative weight values of the particles, and then construct a particle weight value distribution diagram (including: bar chart, scatter plot, line chart, etc.) based on the cumulative weight values. Then, use a random number generation algorithm (i.e., the preset weight distribution threshold generation algorithm) to select a value from uniformly distributed random numbers as the particle weight distribution threshold; the particle weight distribution threshold generated in this embodiment is 0.3. Therefore, according to this example weight distribution threshold and the particle weight value distribution diagram, eliminate the particles corresponding to the weight values lower than 0.3 in the initial particle set.

[0106] Then construct a second particle set according to the preset particle swarm construction algorithm and the preset state transition model; specifically, determine that the number of particles in the second particle set is the number of particles eliminated from the initial particle set, then generate the corresponding number of particles, and initialize the weights and states of these particles; then merge the particles in the second particle set into the initial particle set to obtain the updated initial particle set; then update the state of each particle in the initial particle set according to the state transition model, and then update the weight value of each particle in the initial particle set again according to the real-time voltage value of the platen, as well as update the particle weight distribution threshold and the particle weight value distribution diagram, and then eliminate the particles in the initial particle set and generate a new second particle set, thereby updating the initial particle set again. Repeat the above operations until the number of iterations for the initial particle set meets 50 times, and determine the first particle set.

[0107] In this embodiment, the initial particle set is screened by the particle weight distribution threshold, the introduction of the second particle set is used to avoid falling into the error of local optimum in the update of the initial particle set, and the initial particle set is iteratively updated in combination with the state transition model to gradually correct the distribution of the initial particle set, so that the first particle set can more accurately represent the actual state of the platen and improve the accuracy of judging the state of the platen.

[0108] Step S104: Determine the state of the pressing plate according to the states of each particle in the first particle set.

[0109] In this embodiment, the determining the state of the pressing plate according to the states of each particle in the first particle set specifically includes:

[0110] Determine the quantity corresponding to the state of each particle according to the states of each particle in the first particle set;

[0111] Perform weighted calculation on the quantity corresponding to the state of each particle, and determine the state of the pressing plate according to the weighted calculation result.

[0112] In an alternative embodiment, it is obtained that the number of particles in the first particle set in the closed state (i.e., state 1) is 850, and the number of particles in the open state (i.e., state 0) is 150. Then weighted calculation is performed to obtain the state of the pressing plate. Taking the above as an example, the process of weighted calculation is as follows:

[0113]

[0114] The obtained state estimate value X is 0.85, which is closer to the state value 1 corresponding to the closed state. Therefore, the state of this pressing plate is determined to be in the closed state.

[0115] In this embodiment, by acquiring the real-time voltage data, historical voltage data of the pressing plate, and the initial particle set, and then updating the weight value of each particle in the initial particle set according to the real-time voltage data and historical voltage data, from two dimensions of the long-term law and short-term change in the pressing plate voltage data, each particle can more accurately represent the state of the pressing plate. Then, through the weight value and the preset state transition model, the initial particle set is iteratively updated. The preset state transition model captures the law of the pressing plate state transformation, and iterative update is combined with the weight value to avoid misjudgment of the pressing plate state caused by a single particle and a single number of times. Thus, each particle can more accurately represent the possible states of the pressing plate. Then, by synthesizing the states of each particle in the first particle set, accurate monitoring of the state of the pressing plate is realized. This embodiment only needs to collect the voltage data of the pressing plate to achieve accurate monitoring of the state of the pressing plate, avoiding the low efficiency and untimely monitoring of the pressing plate state caused by manual inspection in the prior art, and improving the efficiency of monitoring the state of the pressing plate.

[0116] Embodiment 2

[0117] Please refer to Figure 2 , which is a schematic structural diagram of a pressing plate state monitoring device provided by an embodiment of the present invention, including: a data acquisition module 201, a particle weight value update module 202, a particle set update module 203, and a pressing plate state determination module 204;

[0118] Among them, the data acquisition module 201 is used to acquire the real-time voltage data, historical voltage data, and initial particle set of the pressure plate.

[0119] In this embodiment, the data acquisition module 201 includes: an initial particle set acquisition unit;

[0120] The initial particle set acquisition unit is used to acquire a number of particles and initialize the weight value of each particle according to the number of the particles;

[0121] Acquire the state set of the pressure plate and initialize the state of each particle according to the state set;

[0122] Update the state of each particle according to a preset state transition model, and determine the initial particle set based on the updated particles.

[0123] The particle weight value update module 202 is used to update the weight value of each particle in the initial particle set according to the real-time voltage data and historical voltage data.

[0124] In this embodiment, the particle weight value update module 202 includes: a particle weight value update unit;

[0125] The particle weight value update unit is used to calculate the voltage distribution data set of the pressure plate in each state according to the historical voltage data, and determine the observation model of the pressure plate according to the voltage distribution data set;

[0126] According to the real-time voltage data of the pressure plate and the current state of each particle in the initial particle set, and in combination with the observation model, calculate the likelihood value of each particle in the initial particle set at the real-time voltage data;

[0127] Update the weight value of each particle in the initial particle set according to the likelihood value.

[0128] In this embodiment, the particle weight value update unit includes: an observation model construction sub-unit;

[0129] The observation model construction sub-unit is used to determine the rated voltage range of the pressure plate in each state according to the historical voltage data;

[0130] Determine the voltage mean value of the pressure plate in each state according to the historical voltage data;

[0131] Determine the voltage standard deviation of the pressure plate in each state according to the historical voltage data;

[0132] Determine the voltage distribution data set of the pressure plate in each state according to the rated voltage range, voltage mean value, and voltage standard deviation;

[0133] Construct a Gaussian distribution model of the pressure plate in each state according to the voltage distribution data set of the pressure plate in each state, and determine the observation model of the pressure plate.

[0134] The particle set update module 203 is used to iteratively update the initial particle set according to the weight value of each particle and the preset state transition model, and determine the first particle set.

[0135] In this embodiment, the particle set update module 203 includes: a particle set update unit;

[0136] The particle set update unit is used to determine the cumulative weight value of each particle according to the weight value of each particle, and construct a particle weight value distribution diagram of the initial particle set according to the cumulative weight value of each particle;

[0137] Determine the particle weight distribution threshold according to the preset weight distribution threshold generation algorithm;

[0138] According to the particle weight distribution threshold and the particle weight value distribution diagram, combined with the preset state transition model, iteratively update the initial particle set until the number of iterations of the initial particle set meets the preset iteration requirements, complete the iterative update of the initial particle set, and determine the first particle set.

[0139] In this embodiment, the particle set update unit includes: a first particle set determination subunit;

[0140] The first particle set determination subunit is used to eliminate the particles in the initial particle set according to the particle weight distribution threshold and the particle weight value distribution diagram;

[0141] Construct a second particle set according to the preset particle swarm construction algorithm;

[0142] Merge the second particle set into the initial particle set, update the state of each particle in the initial particle set according to the state transition model, then update the second particle set, particle weight distribution threshold, and particle weight value distribution diagram according to the iteratively updated initial particle set, and further iteratively update the initial particle set according to the updated second particle set, particle weight distribution threshold, and particle weight value distribution diagram until the number of iterations of the initial particle set meets the preset iteration requirements, and determine the first particle set.

[0143] The platen state determination module 204 is configured to determine the state of the platen according to the state of each particle in the first particle set.

[0144] In this embodiment, the platen state determination module 204 includes: a platen state determination unit;

[0145] The platen state determination unit is configured to determine the quantity corresponding to the state of each particle according to the state of each particle in the first particle set;

[0146] Perform a weighted calculation on the quantity corresponding to the state of each particle, and determine the state of the platen according to the weighted calculation result.

[0147] In this embodiment, by acquiring the real-time voltage data, historical voltage data, and initial particle set of the platen, and then updating the weight value of each particle in the initial particle set according to the real-time voltage data and historical voltage data, from two dimensions of the long-term law and short-term change in the platen voltage data, each particle can more accurately represent the state of the platen. Then, through the weight value and the preset state transition model, the initial particle set is iteratively updated, and the preset state transition model captures the law of the platen state transformation and is iteratively updated in combination with the weight value, avoiding the misjudgment of the platen state caused by a single particle and a single number of times. Thus, each particle can more accurately represent the possible states of the platen. Then, by synthesizing the states of each particle in the first particle set, accurate monitoring of the platen state is achieved. This embodiment only needs to collect the voltage data of the platen to achieve accurate monitoring of the platen state, avoiding the low efficiency and untimely monitoring of the platen state caused by manual inspection in the prior art, and improving the efficiency of monitoring the platen state.

[0148] Embodiment Three

[0149] Please refer to Figure 3 , which is a schematic structural diagram of a platen state monitoring system provided by an embodiment of the present invention, including a sensor module 301, a communication module 302, a host computer module 303, and a display module 304;

[0150] Among them, the sensor module 301 is used to obtain the real-time voltage data and historical voltage data of the pressure plate; the communication module 302 is used to receive the data transmitted by the sensor module 301 and transmit the real-time voltage data and historical voltage data of the pressure plate to the upper computer module 303; the upper computer module 303 is used to obtain the initial particle set, update the weight value of each particle in the initial particle set according to the real-time voltage data and historical voltage data, and perform iterative update on the initial particle set according to the weight value of each particle and the preset state transition model to determine the first particle set; determine the state of the pressure plate according to the state of each particle in the first particle set; the display module 304 is used to display the state of the pressure plate.

[0151] In an alternative embodiment, the sensor module 301 includes several sensors, which are installed directly below or on the right side of each pressure plate. The types of sensors include: miniature photoelectric sensors or microswitches; the sensor module adopts a cascaded mode, and each sensor module 301 includes 2 RS232 communication interfaces and 9 sensors.

[0152] In an alternative embodiment, the communication module 302 adopts the standard Modbus protocol RTU mode, and its communication driver is fully compatible with the Modbu-RTU format. Its communication interface is RS232, and the communication specification is one start bit, 8 data bits, one stop bit, no parity bit, and the baud rate is 115200; its address is 0x01; this protocol supports reading 16-word length data at a time. Each byte contains 8-bit binary code, and a start bit (0) and a stop bit (1) are added during transmission, for a total of 10 bits. When communicating, the data is sent back in the form of words (WORD - 2 bytes). In each word sent back, the high byte is in front and the low byte is behind. If 2 words are sent back continuously (such as: floating point or long integer), then the high word is in front and the low word is behind.

[0153] Embodiment Four

[0154] The embodiment of the present invention provides a terminal device, including:

[0155] One or more processors;

[0156] A memory, coupled to the processor, for storing one or more programs;

[0157] When the one or more programs are executed by the one or more processors, the one or more processors implement a method for monitoring the state of a pressure plate as described in Embodiment One above.

[0158] The embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, and the computer program is executed by a processor to implement a method for monitoring the state of a pressure plate as described in Embodiment One above.

[0159] In summary, in the embodiment of the present invention, the real-time voltage data, historical voltage data, and initial particle set of the pressure plate are obtained. Then, according to the real-time voltage data and historical voltage data, the weight value of each particle in the initial particle set is updated. From the two dimensions of the long-term law and short-term change in the pressure plate voltage data, each particle can more accurately represent the state of the pressure plate. Then, through the weight value and the preset state transition model, the initial particle set is iteratively updated. The preset state transition model captures the law of the pressure plate state transformation and is iteratively updated in combination with the weight value, avoiding the misjudgment of the pressure plate state caused by a single particle and a single number of times. Thus, each particle can more accurately represent the possible states of the pressure plate. Then, by synthesizing the states of each particle in the first particle set, the accurate monitoring of the pressure plate state is realized. In the embodiment of the present invention, only by collecting the voltage data of the pressure plate can the accurate monitoring of the pressure plate state be realized, avoiding the low efficiency and untimely monitoring of the pressure plate state caused by manual inspection in the prior art, and improving the efficiency of the pressure plate state monitoring.

[0160] In the specific embodiments described above, the purpose, technical solution, and beneficial effects of the present invention have been further described in detail. It should be understood that the above description is only for the specific embodiments of the present invention and is not used to limit the protection scope of the present invention. In particular, for those skilled in the art, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for monitoring the state of a pressing plate, characterized in that, Including: Obtaining real-time voltage data, historical voltage data of the pressure plate, and an initial particle set; Updating the weight value of each particle in the initial particle set according to the real-time voltage data and the historical voltage data; Iteratively updating the initial particle set according to the weight value of each particle and a preset state transition model to determine a first particle set; Determining the state of the pressure plate according to the state of each particle in the first particle set.

2. The method for monitoring the state of a pressing plate according to claim 1, wherein The process of obtaining the initial particle set specifically includes: Obtaining a number of particles and initializing the weight value of each particle according to the number of the particles; Obtaining a state set of the pressure plate and initializing the state of each particle according to the state set; Updating the state of each particle according to a preset state transition model and determining an initial particle set based on the updated particles.

3. The method for monitoring the state of a pressing plate according to claim 1, characterized in that, The updating the weight value of each particle in the initial particle set according to the real-time voltage data and the historical voltage data specifically includes: Calculating a voltage distribution data set of the pressure plate in each state according to the historical voltage data, and determining an observation model of the pressure plate according to the voltage distribution data set; Calculating the likelihood value of each particle in the initial particle set at the real-time voltage data according to the real-time voltage data of the pressure plate, the current state of each particle in the initial particle set, and in combination with the observation model; Updating the weight value of each particle in the initial particle set according to the likelihood value.

4. The method for monitoring the state of a pressing plate according to claim 3, characterized in that, The calculating a voltage distribution data set of the pressure plate in each state according to the historical voltage data, and determining an observation model of the pressure plate according to the voltage distribution data set specifically includes: Determining a rated voltage interval of the pressure plate in each state according to the historical voltage data; Determining the voltage mean value of the pressure plate in each state according to the historical voltage data; Determining the voltage standard deviation of the pressure plate in each state according to the historical voltage data; Determining a voltage distribution data set of the pressure plate in each state according to the rated voltage interval, the voltage mean value, and the voltage standard deviation; Constructing a Gaussian distribution model of the pressure plate in each state according to the voltage distribution data set of the pressure plate in each state, and determining the observation model of the pressure plate.

5. A method for monitoring the state of a pressing plate according to claim 3 or 4, characterized in that The iteratively updating the initial particle set according to the weight value of each particle and the preset state transition model to determine a first particle set specifically includes: Determining the cumulative weight value of each particle according to the weight value of each particle, and constructing a particle weight value distribution diagram of the initial particle set according to the cumulative weight value of each particle; Determining a particle weight distribution threshold according to a preset weight distribution threshold generation algorithm; Iteratively updating the initial particle set according to the particle weight distribution threshold and the particle weight value distribution diagram, in combination with the preset state transition model, until the number of iterations of the initial particle set meets a preset iteration requirement, completing the iterative update of the initial particle set, and determining a first particle set.

6. The method for monitoring the state of a pressing plate according to claim 5, wherein Iteratively update the initial particle set according to the particle weight distribution threshold and the particle weight value distribution diagram, in combination with the preset state transition model, until the number of iterations of the initial particle set meets the preset iteration requirements, complete the iterative update of the initial particle set, and determine the first particle set. Specifically, it includes: Eliminate the particles in the initial particle set according to the particle weight distribution threshold and the particle weight value distribution diagram; Construct a second particle set according to a preset particle swarm construction algorithm; Merge the second particle set into the initial particle set, update the state of each particle in the initial particle set according to the state transition model, and then update the second particle set, the particle weight distribution threshold, and the particle weight value distribution diagram according to the iteratively updated initial particle set. Furthermore, iteratively update the initial particle set according to the updated second particle set, particle weight distribution threshold, and particle weight value distribution diagram until the number of iterations of the initial particle set meets the preset iteration requirements to determine the first particle set.

7. The method for monitoring the state of a pressing plate according to claim 1, characterized in that Determine the state of the platen according to the state of each particle in the first particle set. Specifically, it includes: Determine the quantity corresponding to the state of each particle according to the state of each particle in the first particle set; Perform weighted calculation on the quantity corresponding to the state of each particle, and determine the state of the platen according to the weighted calculation result.

8. A pressing plate state monitoring device, characterized in that, It includes: A data acquisition module, a particle weight value update module, a particle set update module, and a platen state determination module; Among them, the data acquisition module is used to acquire the real-time voltage data, historical voltage data, and initial particle set of the platen; The particle weight value update module is used to update the weight value of each particle in the initial particle set according to the real-time voltage data and historical voltage data; The particle set update module is used to iteratively update the initial particle set according to the weight value of each particle and the preset state transition model to determine the first particle set; The platen state determination module is used to determine the state of the platen according to the state of each particle in the first particle set.

9. A terminal device, characterized in that, It includes: One or more processors; A memory coupled to the processor for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement a platen state monitoring method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, The computer program is executed by the processor to implement a platen state monitoring method according to any one of claims 1 to 7.

Images