The Partially Ordered Workflow Language (POWL) has recently emerged as a process modeling notation, offering strong quality guarantees and high expressiveness. While early versions of POWL relied on strict block-structured operators for choices and loops, the language has recently evolved into POWL 2.0, introducing choice graphs to enable the modeling of non-block-structured decisions and cycles. To bridge the gap between the theoretical advantages of POWL and the practical need for compatibility with established notations, robust model transformations are required. This paper presents a novel algorithm for transforming safe and sound workflow nets (WF-nets) into equivalent POWL 2.0 models. The algorithm recursively identifies structural patterns within the WF-net and translates them into their POWL representation. Unlike the previous approach that required separate detection strategies for exclusive choices and loops, our new algorithm utilizes choice graphs to capture generalized decision and cyclic patterns. We formally prove the correctness of our approach, showing that the generated POWL model preserves the language of the input WF-net. Furthermore, we prove the completeness of our algorithm on the class of separable WF-nets, which corresponds to nets constructed via the hierarchical nesting of state machines and marked graphs. We evaluate our algorithm on large-scale process models to demonstrate its high scalability. Furthermore, to test its practical expressiveness, we applied it to a benchmark of 1,493 industrial and synthetic process models. Our algorithm successfully transformed all models in this benchmark, suggesting that POWL 2.0's expressive power is generally sufficient to capture the complex logic found in real-world business processes. This work paves the way for broader adoption of POWL in practical process analysis and improvement applications.

翻译：部分有序工作流语言（POWL）近期作为一种流程建模符号涌现，具备强大的质量保证能力与高表现力。尽管早期版本的POWL依赖严格的块结构算子来处理选择与循环，该语言已演进为POWL 2.0，引入选择图以实现非块结构决策与循环的建模。为弥合POWL理论优势与既有符号兼容性实际需求之间的鸿沟，亟需鲁棒的模型转换方法。本文提出一种新颖算法，用于将安全且合理的工作流网（WF-nets）转化为等价的POWL 2.0模型。该算法递归识别WF-net中的结构模式，并将其转换为POWL表示。与先前需针对互斥选择与循环分别采用检测策略的方法不同，新算法利用选择图捕获广义化决策与循环模式。我们形式化证明了方法的正确性，表明生成的POWL模型能够保留输入WF-net的语言性质。此外，我们证明了算法在可分离WF-net类别上的完备性，该类网络对应通过状态机与标记图的层次化嵌套构建的流程。通过大规模流程模型评估表明算法具有高度可扩展性。进一步地，为检验其实践表现力，我们将算法应用于包含1,493个工业与合成流程模型的基准测试集。算法成功转换了基准测试中所有模型，表明POWL 2.0的表现力足以捕获现实业务流程中的复杂逻辑。本工作为POWL在流程分析与改进实践中的广泛采用奠定了基础。