A method and system for implementing energy management strategies for hybrid mining trucks

Abstract

This invention relates to a method and system for implementing an energy management strategy for hybrid mining trucks, comprising: constructing a power system model of the hybrid mining truck based on its dynamic parameters; modeling the driving conditions of the hybrid mining truck at each stage based on the power system model to form an objective function; solving the objective function using a dynamic programming algorithm to obtain the globally optimal energy management strategy of the hybrid mining truck under each operating condition; inputting the globally optimal energy management strategy under each operating condition as training data into a BP neural network model for training to obtain an energy allocation model; and optimizing the energy management strategy of the target hybrid mining truck using the energy allocation model. This invention, by using dynamic programming and a BP neural network, can dynamically adjust the energy management strategy of the hybrid mining truck according to different operating conditions, improving the truck's adaptability to various environments.

Description

Technical Field

[0001] This invention relates to the field of hybrid vehicle energy management technology, and in particular to a method and system for implementing energy management strategies for hybrid mining trucks. Background Technology

[0002] Hybrid mining trucks are key equipment in mining operations, and their performance directly impacts mine production efficiency and operating costs. Due to the complexity and variability of the mining environment, hybrid mining trucks face various operating conditions, such as heavy-load uphill driving, light-load downhill driving, and low-speed, high-torque driving. These conditions place extremely high demands on energy management strategies, requiring both efficient energy utilization and real-time response to meet the actual needs of mining operations.

[0003] Traditional energy management strategies are mostly based on rule-based control or simple optimization algorithms, which are difficult to adapt to complex and ever-changing operating conditions, leading to unreasonable energy allocation and poor fuel economy. In recent years, with the rapid development of machine learning technology, more and more researchers have begun to explore the application of machine learning algorithms to the energy management of hybrid vehicles. However, directly applying existing machine learning algorithms to the energy management of hybrid mining trucks still faces many challenges, such as high algorithm model complexity, poor real-time performance, and insufficient generalization ability. Summary of the Invention

[0004] To address the aforementioned problems, the purpose of this invention is to provide a method and system for implementing energy management strategies for hybrid mining trucks.

[0005] A method for implementing an energy management strategy for hybrid mining trucks includes:

[0006] A power system model for hybrid mining trucks is constructed based on their dynamic parameters.

[0007] Based on the aforementioned power system model, the driving conditions of the hybrid mining truck at each stage are modeled to form an objective function.

[0008] The objective function is solved using a dynamic programming algorithm to obtain the globally optimal energy management strategy for hybrid mining trucks under various operating conditions.

[0009] The global optimal energy management strategy under each working condition is used as training data and input into the BP neural network model for training to obtain the energy allocation model;

[0010] The energy management strategy for the target hybrid mining truck is optimized using the energy allocation model described above.

[0011] Preferably, the objective function is constructed using engine fuel consumption as the performance index function, the running time under driving conditions as the system stage variable, the hydraulic accumulator pressure change rate as the system state variable, and the driving torque of the hydraulic pump / motor as the system control variable.

[0012] Preferably, the step of inputting the globally optimal energy management strategy under each operating condition as training data into the BP neural network model for training to obtain the energy allocation model includes:

[0013] The globally optimal energy management strategies under various operating conditions are classified to obtain a set of operating condition categories;

[0014] The set of each working condition category is input into the BP neural network model for training to obtain the energy allocation model under each working condition category.

[0015] Preferably, a fuzzy C-means clustering algorithm based on simulated annealing genetic algorithm is used to classify the global optimal energy management strategies under each working condition to obtain a set of working condition categories.

[0016] Preferably, the set of each working condition category is input into the BP neural network model, and the BP neural network is optimized using a nested genetic algorithm to obtain the energy allocation model under each working condition category.

[0017] Preferably, when using a nested genetic algorithm to optimize the parameter configuration of a BP neural network, the outer loop is responsible for optimizing the number of hidden layer neurons, while the inner genetic algorithm is responsible for optimizing the initial weights and biases of the BP neural network.

[0018] The present invention also provides a system for implementing energy management strategies for hybrid mining trucks, comprising:

[0019] The dynamic model building module is used to build a power system model of a hybrid mining truck based on its dynamic parameters.

[0020] The objective function construction module is used to model the driving conditions of the hybrid mining truck at each stage using the power system model to form an objective function;

[0021] The optimal energy management strategy solution module is used to solve the objective function using a dynamic programming algorithm to obtain the global optimal energy management strategy for the hybrid mining truck under various operating conditions.

[0022] The training module is used to input the globally optimal energy management strategy under various operating conditions as training data into the BP neural network model to obtain the energy allocation model.

[0023] An energy management strategy optimization module is used to optimize the energy management strategy of the target hybrid mining truck using the energy allocation model.

[0024] The present invention also provides an electronic device, including a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, characterized in that the computer program, when executed by the processor, implements the steps in the above-described method for implementing a hybrid power mining truck energy management strategy.

[0025] The present invention also provides a computer-readable storage medium having a computer program stored thereon, characterized in that the computer program, when executed by a processor, implements the steps in the above-described method for implementing an energy management strategy for a hybrid mining truck.

[0026] According to specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0027] This invention relates to a method for implementing energy management strategies for hybrid mining trucks. Compared with the prior art, this invention uses dynamic programming algorithms and BP neural networks to dynamically adjust the energy management strategies of hybrid mining trucks according to different working conditions, thereby improving the trucks' adaptability in various environments.

[0028] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0029] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0030] Figure 1 The structural diagram of the hybrid mining truck system provided by the present invention shows the core components of the hybrid mining truck and their connection methods.

[0031] Figure 2 The diagram of the hybrid powertrain system for mining trucks provided by this invention illustrates the construction process of the hybrid powertrain system model for mining trucks.

[0032] Figure 3The diagram illustrating the overall solution process of the DP-based energy management strategy provided by this invention demonstrates the calculation process of finding the globally optimal energy management strategy for hybrid mining trucks through inverse and forward calculations using a dynamic programming algorithm.

[0033] Figure 4 The BP neural network topology diagram provided by this invention illustrates the basic structure and parameter configuration of the BP neural network.

[0034] Figure 5 The block diagram of the multi-BP neural network model based on working condition recognition provided by the present invention illustrates the structure of the multi-BP neural network model based on working condition recognition. Detailed Implementation

[0035] In the description of this invention, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," and "counterclockwise," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention.

[0036] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0037] In this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," "linking," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0038] Please see Figure 1-5 A method for implementing an energy management strategy for hybrid mining trucks, comprising:

[0039] Step 1: Construct a power system model for the hybrid mining truck based on its dynamic parameters;

[0040] like Figure 1 As shown, this invention first constructs a power system model based on the structure and working principle of a hybrid mining truck. This model encompasses mathematical models of key components such as the engine, transmission, clutch, hydraulic pump / motor, hydraulic accumulator, and feedback elements. These mathematical models allow for the accurate simulation of the hybrid mining truck's operating conditions under various circumstances, including but not limited to heavy-load uphill driving, light-load downhill driving, and low-speed, high-torque driving. This step provides a solid foundation for subsequent energy management strategy design.

[0041] Specifically, the construction of the powertrain model involves a detailed description of the dynamic and static characteristics of each key component. For example, this includes the relationship between engine fuel consumption rate, power output, and speed and torque; the speed ratio changes and transmission efficiency of the transmission; the impact of clutch engagement and disengagement on power transmission; the relationship between flow rate, pressure, and torque of the hydraulic pump / motor; and the charging and discharging process of the hydraulic accumulator. These models not only consider the interactions between components but also the impact of changing operating conditions on component performance, thus ensuring high fidelity and practicality. Specific powertrain models are attached. Figure 2 As shown.

[0042] Step 2: Based on the power system model, model the driving conditions of the hybrid mining truck at each stage to form an objective function;

[0043] In this invention, engine fuel consumption is used as the performance index function, the running time of the driving condition is selected as the system stage variable, the hydraulic accumulator pressure change rate is the system state variable, and the driving torque of the hydraulic pump / motor is the system control variable. The driving conditions of each stage of the hybrid mining truck are modeled to form the objective function.

[0044] Step 3: Use dynamic programming algorithm to solve the objective function to obtain the global optimal energy management strategy for hybrid mining trucks under various working conditions;

[0045] Dynamic programming algorithms can find the globally optimal energy management strategy, i.e., the torque distribution ratio between the engine and the hydraulic pump / motor under different operating conditions. The reverse calculation process starts from the final state and progressively calculates the optimal control decision for each stage; the forward calculation process, based on the optimal control decision sequence obtained from the reverse calculation, progressively calculates the system's state trajectory and performance indicators. To achieve this goal, the control variable T for each stage needs to be... p / m_k The optimization is to arrive at a globally optimal control sequence. This process can be viewed as a multi-stage decision problem, where the entire driving condition is divided into N stages, and the state variable SOC of each stage is further subdivided into multiple grid points [SOC1, SOC2…SOC…]. i…]. Therefore, the problem of finding the globally optimal energy management strategy is transformed into finding the optimal control variable decision [T] at each state variable grid point in each stage. p / m_1 ,T p / m_2 …T p / m_j …] Corresponding fuel consumption [J1, J2…J j The problem of … is addressed within the dynamic programming framework through a reverse solution process. Specifically, for the final stage N-1, the fuel cost corresponding to each control variable point at each state point is calculated, and the minimum fuel cost J for each state point is determined. i *. Subsequently, the process is recursively applied to stage N-2, finding the next stage state point corresponding to each control variable point, and calculating the minimum fuel cost J of their sum. i * represents the minimum cumulative fuel cost at time N-2. This process continues until stage 0, thus deriving the minimum cumulative fuel cost J for each state. i * This reverse calculation process is shown in the attached figure. Figure 3 As shown, the solid line represents the reverse solution path from stage N-1 to stage 0. After the reverse calculation is completed, the forward calculation is performed. This calculation process starts from stage 0, and based on the initial state given by the system (such as SOC3), the cumulative value J3* of the minimum fuel consumption is found, and the corresponding state point SOC3 and the optimal control variable T are recorded. p / m_1 And the optimal fuel cost J1. Then, the state point values ​​for stage 1 are calculated. If an exact corresponding point cannot be found, interpolation or the nearest minimum point is used for calculation, and the corresponding state value, optimal control variable value, and fuel cost value are recorded. This process continues until stage N-1, finally obtaining the optimal state value, optimal control variable value, and optimal fuel cost value for each stage. This forward calculation process is shown in the attached figure. Figure 3 As shown, the dashed line represents the forward solution path from stage 0 to stage N-1.

[0046] Step 4: Input the globally optimal energy management strategy under each working condition as training data into the BP neural network model to obtain the energy allocation model;

[0047] Because dynamic programming algorithms have high computational complexity, they are difficult to apply directly to real-time control. Therefore, this invention uses a backpropagation (BP) neural network to approximate the globally optimal energy management strategy obtained by dynamic programming. A BP neural network is a multi-layer feedforward neural network that adjusts network weights and thresholds through backpropagation to minimize output error.

[0048] In this invention, a training sample set for a backpropagation (BP) neural network is first constructed based on the globally optimal solution obtained by a dynamic programming algorithm. Then, the structure and parameters of the BP neural network are designed, including the number of neurons in the input layer, hidden layers, and output layer, the activation functions, and the initialization methods for weights and thresholds. The input layer contains state information such as the current torque demand, vehicle speed, and the previous state of charge (SOC) value; the output layer contains the current engine torque distribution ratio. The number of neurons in the hidden layers and the choice of activation functions have a significant impact on the network's performance and therefore require optimization in subsequent steps.

[0049] like Figure 4-5 As shown, to improve the performance of the BP neural network, this invention employs a nested genetic algorithm to optimize the parameter configuration of the BP neural network. The nested genetic algorithm is an optimization method combining genetic algorithms and local search algorithms, characterized by strong global search capabilities and fast convergence speed. In this invention, a nested genetic algorithm framework is designed, combining the advantages of genetic algorithms with the training process of the BP neural network. This framework consists of two nested parts: an outer loop and an inner genetic algorithm. The outer loop is responsible for optimizing the number of hidden layer neurons, finding the optimal neuron configuration by continuously changing the number of neurons and evaluating network performance; the inner genetic algorithm is responsible for optimizing the initial weights and thresholds of the network, finding the optimal weight and threshold configuration through genetic operations (such as selection, crossover, and mutation) and local search algorithms (such as gradient descent).

[0050] By optimizing nested genetic algorithms, the optimal number of hidden layer neurons, initial weights, and thresholds can be determined automatically and efficiently, thereby improving the learning efficiency and performance of BP neural networks.

[0051] The specific process of optimizing the BP neural network is as follows:

[0052] (1) Initialization: Set the parameters of the genetic algorithm (population size is 40, crossover rate is 0.7, mutation rate is 0.01, number of iterations is 100) and the number of neurons in the outer loop search range.

[0053] (2) Outer loop operation: For each candidate value of the number of neurons, start the inner genetic algorithm.

[0054] (3) Running the inner genetic algorithm:

[0055] ① Encoding: Encode the initial weights and thresholds of the network into chromosomes.

[0056] ② Fitness evaluation: Train the BP neural network using the training data and calculate the error on the validation set, which is used as the fitness of the individual.

[0057] ③ Genetic operations: Selection, crossover, and mutation operations are performed based on fitness to generate new populations.

[0058] ④ Iteration: Repeat the genetic operation until the stopping condition is met.

[0059] (4) Result evaluation and selection: After the outer loop ends, the optimal fitness under different numbers of neurons is compared, and the optimal configuration is selected as the final parameter of the BP neural network.

[0060] (5) Network training and testing: Retrain the BP neural network with the optimal parameters and evaluate its performance on the test set.

[0061] Specifically, before training the BP neural network model, this invention proposes a multi-BP neural network model based on working condition identification to address the energy management problem of hybrid mining trucks under complex and variable open-air working conditions. This model uses an intelligent working condition identification module to determine the working condition category of the current input sample in real time and automatically calls the corresponding BP neural network sub-model for calculation.

[0062] First, a fuzzy C-means clustering algorithm based on simulated annealing genetic algorithm is used to classify the operating conditions, dividing the complex and varied operating conditions into several representative categories. Then, for each operating condition category, an optimized BP neural network sub-model is independently constructed and trained. These sub-models have the same network structure and parameter configuration optimization method, but the training sample set and training process are customized according to the characteristics of their respective operating condition categories.

[0063] The multi-BP neural network model based on working condition identification has two processes: offline training and online simulation.

[0064] (1) Offline training process

[0065] 1) Dataset acquisition: The optimal energy management rule dataset under various driving conditions is obtained through the DP algorithm.

[0066] 2) Cluster analysis: The dataset was divided into 10 categories using the FCM-GASA algorithm.

[0067] 3) Sub-model construction: For each category, construct a BP neural network sub-model and set appropriate network structure and parameters according to the NGA-BP algorithm.

[0068] 4) Sub-model training: Use the training data of the corresponding category to train each sub-model fully and save the trained model parameters.

[0069] (2) Online simulation process

[0070] 1) Real-time data input: Obtain the current demand torque (Tr(k)), vehicle speed (v(k)) and the SOC value of the previous moment (SOC(k-1)).

[0071] 2) Operating condition identification: The current data is classified by fuzzy C-means clustering algorithm of simulated annealing genetic algorithm to determine its operating condition category.

[0072] 3) Sub-model invocation: Based on the working condition category, the corresponding BP neural network sub-model is invoked for calculation.

[0073] 4) Optimized distribution: Each sub-model outputs the optimized torque distribution results under its own working conditions, and the total output torque distribution of the hybrid mining truck is obtained by integration.

[0074] In practical applications, the operating condition identification module determines the operating condition category of the current input sample based on current demand torque, vehicle speed, and the previous state of charge (SOC) value, and then calls the corresponding BP neural network sub-model for calculation. This mechanism not only greatly improves the model's processing efficiency and flexibility and enhances its generalization ability, but also ensures stable and accurate control results under different operating conditions.

[0075] Step 5: Optimize the energy management strategy for the target hybrid mining truck using the energy allocation model.

[0076] Based on the BP neural network model and operating condition identification module constructed in the above steps, this invention realizes an adaptive machine learning energy management strategy for hybrid mining trucks. During real-time control, the system first acquires state information such as the current torque demand, vehicle speed, and the previous state of charge (SOC) value. Then, the operating condition identification module determines the current operating condition category and calls the corresponding BP neural network sub-model for calculation. Finally, based on the output of the BP neural network sub-model, the engine torque distribution ratio for the current moment is determined, achieving real-time and efficient energy management.

[0077] This energy management strategy is highly adaptive and real-time, automatically adjusting the energy allocation ratio according to the needs of different operating conditions, thereby maximizing the fuel economy of hybrid mining trucks. Furthermore, thanks to the use of advanced machine learning techniques such as BP neural networks and nested genetic algorithms, the strategy also exhibits good generalization ability and robustness, enabling it to adapt to complex and ever-changing mining operating environments.

[0078] The present invention also provides a system for implementing energy management strategies for hybrid mining trucks, comprising:

[0079] The dynamic model building module is used to build a power system model of a hybrid mining truck based on its dynamic parameters.

[0080] The objective function construction module is used to model the driving conditions of the hybrid mining truck at each stage using the power system model to form an objective function;

[0081] The optimal energy management strategy solution module is used to solve the objective function using a dynamic programming algorithm to obtain the global optimal energy management strategy for the hybrid mining truck under various operating conditions.

[0082] The training module is used to input the globally optimal energy management strategy under various operating conditions as training data into the BP neural network model to obtain the energy allocation model.

[0083] An energy management strategy optimization module is used to optimize the energy management strategy of the target hybrid mining truck using the energy allocation model.

[0084] The present invention also provides an electronic device, including a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor. The transceiver, the memory, and the processor are connected via the bus. The computer program, when executed by the processor, implements the steps in the above-described method for implementing a hybrid power mining truck energy management strategy. Compared with the prior art, the beneficial effects of the electronic device provided by the present invention are the same as those of the above-described method for implementing a hybrid power mining truck energy management strategy, and will not be elaborated upon here.

[0085] The present invention also provides a computer-readable storage medium having a computer program stored thereon, characterized in that, when the computer program is executed by a processor, it implements the steps in the above-described method for implementing an energy management strategy for a hybrid mining truck. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present invention are the same as the beneficial effects of the above-described method for implementing an energy management strategy for a hybrid mining truck, and will not be repeated here.

[0086] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for implementing an energy management strategy for hybrid mining trucks, characterized in that, include: A power system model for hybrid mining trucks is constructed based on their dynamic parameters. Based on the aforementioned power system model, the driving conditions of the hybrid mining truck at each stage are modeled to form an objective function; the engine fuel consumption is used as the performance index function, the running time of the driving condition is used as the system stage variable, the hydraulic accumulator pressure change rate is used as the system state variable, and the driving torque of the hydraulic pump / motor is used as the system control variable to construct the objective function. The objective function is solved using a dynamic programming algorithm to obtain the globally optimal energy management strategy for hybrid mining trucks under various operating conditions. The global optimal energy management strategy under each working condition is used as training data and input into the BP neural network model for training to obtain the energy allocation model; The set of each working condition category is input into the BP neural network model, and the BP neural network is optimized using a nested genetic algorithm to obtain the energy allocation model under each working condition category; When using a nested genetic algorithm to optimize the parameter configuration of a BP neural network, the outer loop is responsible for optimizing the number of hidden layer neurons, while the inner genetic algorithm is responsible for optimizing the initial weights and biases of the BP neural network. The outer loop is responsible for optimizing the number of neurons in the hidden layer. It finds the optimal number of neurons by continuously changing the number of neurons and evaluating the network performance. The inner genetic algorithm is responsible for optimizing the initial weights and thresholds of the network. It finds the optimal weight and threshold configuration through genetic operations and local search algorithms. The energy management strategy for the target hybrid mining truck is optimized using the energy allocation model described above.

2. The method for implementing a hybrid mining truck energy management strategy according to claim 1, characterized in that, The step of using the globally optimal energy management strategy under various operating conditions as training data to train a BP neural network model to obtain an energy allocation model includes: The globally optimal energy management strategies under various operating conditions are classified to obtain a set of operating condition categories; The set of each working condition category is input into the BP neural network model for training to obtain the energy allocation model under each working condition category.

3. The method for implementing a hybrid mining truck energy management strategy according to claim 2, characterized in that, A fuzzy C-means clustering algorithm based on simulated annealing genetic algorithm is used to classify the global optimal energy management strategies under each working condition to obtain a set of working condition categories.

4. A system for implementing energy management strategies for hybrid mining trucks, characterized in that, include: The dynamic model building module is used to build a power system model of a hybrid mining truck based on its dynamic parameters. The objective function construction module is used to model the driving conditions of the hybrid mining truck at each stage using the power system model to form an objective function; the objective function is constructed with engine fuel consumption as the performance index function, the running time of the driving condition as the system stage variable, the hydraulic accumulator pressure change rate as the system state variable, and the driving torque of the hydraulic pump / motor as the system control variable. The optimal energy management strategy solution module is used to solve the objective function using a dynamic programming algorithm to obtain the global optimal energy management strategy for the hybrid mining truck under various operating conditions. The training module is used to input the globally optimal energy management strategy under various operating conditions as training data into the BP neural network model to obtain the energy allocation model. The set of each working condition category is input into the BP neural network model, and the BP neural network is optimized using a nested genetic algorithm to obtain the energy allocation model under each working condition category; When using a nested genetic algorithm to optimize the parameter configuration of a BP neural network, the outer loop is responsible for optimizing the number of hidden layer neurons, while the inner genetic algorithm is responsible for optimizing the initial weights and biases of the BP neural network. The outer loop is responsible for optimizing the number of neurons in the hidden layer. It finds the optimal number of neurons by continuously changing the number of neurons and evaluating the network performance. The inner genetic algorithm is responsible for optimizing the initial weights and thresholds of the network. It finds the optimal weight and threshold configuration through genetic operations and local search algorithms. An energy management strategy optimization module is used to optimize the energy management strategy of the target hybrid mining truck using the energy allocation model.

5. An electronic device comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, characterized in that, When the computer program is executed by the processor, it implements the steps in the method for implementing a hybrid mining truck energy management strategy as described in any one of claims 1-3.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps in the method for implementing a hybrid mining truck energy management strategy as described in any one of claims 1-3.

Images